Over- or underestimating sales is detrimental to marketing and sales efforts as well as
inventories and cash flow management. Thus the purpose of this investigation is to evaluate the forecasting
accuracy of three competing multivariate time-series models that take into account existing
A lesson in Chapter 4 that includes two parts: Marketing Research and Sales Forecasting. This is the part I of Lesson 4 in Chapter 4 which specifically discusses primer of Marketing Research and Analysis.
APPLICATION OF FACEBOOK'S PROPHET ALGORITHM FOR SUCCESSFUL SALES FORECASTING ...ijnlc
This paper presents a framework capable of accurately forecasting future sales in the retail industry and classifying the product portfolio according to the expected level of forecasting reliability. The proposed framework, that would be of great use for any company operating in the retail industry, is based on Facebook's Prophet algorithm and backtesting strategy. Real-world sales forecasting benchmark data obtained experimentally in a production environment in one of the biggest retail companies in Bosnia and Herzegovina is used to evaluate the framework and demonstrate its capabilities in a real-world use case scenario
A lesson in Chapter 4 that includes two parts: Marketing Research and Sales Forecasting. This is the part I of Lesson 4 in Chapter 4 which specifically discusses primer of Marketing Research and Analysis.
APPLICATION OF FACEBOOK'S PROPHET ALGORITHM FOR SUCCESSFUL SALES FORECASTING ...ijnlc
This paper presents a framework capable of accurately forecasting future sales in the retail industry and classifying the product portfolio according to the expected level of forecasting reliability. The proposed framework, that would be of great use for any company operating in the retail industry, is based on Facebook's Prophet algorithm and backtesting strategy. Real-world sales forecasting benchmark data obtained experimentally in a production environment in one of the biggest retail companies in Bosnia and Herzegovina is used to evaluate the framework and demonstrate its capabilities in a real-world use case scenario
The aim of marketing controlling is to measure and increase the effectiveness and efficiency of implemented marketing actions. With the help of our templates on this topic, you can align your company with future developments in an intelligent and flexible way.
Marketing controlling is essential for results-based management and control of your marketing. Use the marketing controlling tools to ensure long-term profitability from your investment decisions.
Download our new templates for Marketing Controlling here: http://www.presentationload.com/marketing-controlling-powerpoint-template.html
and make an impact with your next presentation.
The study of the effects of the pricing policies on an organizations profit: ...EECJOURNAL
The main purpose of this research is to examine the influence of pricing policies on organizations’ profit. The researcher applied a quantitative method to analyze the data in this study, the researcher prepared questionnaire and distributed in the different organizations located in Erbil. The survey was divided into two sections; the first section was demographic analysis which started with respondent’s age, gender, and level of education. The second section of survey consisted of 32 questions concerning pricing policies and its impact on organization profit. 89 participants were involved in the current study; however the researcher used SPSS software in order to analyze the gathered data. Moreover, the researcher aimed to develop the main research hypothesis which stated that there is a positive and significant impact of pricing policies on organization profit. The result of a simple regression analysis demonstrates that the value B for pricing policy is .712 which is greater than .0001 this proves that the main research hypothesis is supported which stated that the there is a positive and significant impact of pricing policy on organization profit.
NEW MARKET SEGMENTATION METHODS USING ENHANCED (RFM), CLV, MODIFIED REGRESSIO...ijcsit
A widely used approach for gaining insight into the heterogeneity of consumer’s buying behavior is market segmentation. Conventional market segmentation models often ignore the fact that consumers’ behavior may evolve over time. Therefore retailers consume limited resources attempting to service unprofitable consumers. This study looks into the integration between enhanced Recency, Frequency, Monetary (RFM) scores and Consumer Lifetime Value (CLV) matrix for a medium size retailer in the State of Kuwait. A modified regression algorithm investigates the consumer purchase trend gaining knowledge from a pointof-sales data warehouse. In addition, this study applies enhanced normal distribution formula to remove outliers, followed by soft clustering Fuzzy C-Means and hard clustering Expectation Maximization (EM) algorithms to the analysis of consumer buying behavior. Using cluster quality assessment shows EM algorithm scales much better than Fuzzy C-Means algorithm with its ability to assign good initial points in the smaller dataset.
International Journal of Business and Management Invention (IJBMI)inventionjournals
International Journal of Business and Management Invention (IJBMI) is an international journal intended for professionals and researchers in all fields of Business and Management. IJBMI publishes research articles and reviews within the whole field Business and Management, new teaching methods, assessment, validation and the impact of new technologies and it will continue to provide information on the latest trends and developments in this ever-expanding subject. The publications of papers are selected through double peer reviewed to ensure originality, relevance, and readability. The articles published in our journal can be accessed online.
The Journal will bring together leading researchers, engineers and scientists in the domain of interest from around the world. Topics of interest for submission include, but are not limited to
AUTOMATION OF BEST-FIT MODEL SELECTION USING A BAG OF MACHINE LEARNING LIBRAR...ijaia
Sales forecasting became crucial for industries in past decades with rapid globalization, widespread adoption of information technology towards e-business, understanding market fluctuations, meeting business plans, and avoiding loss of sales. This research precisely predicts the automotive industry sales using a bag of multiple machine learning and time series algorithms coupled with historical sales and auxiliary features. Three-year historical sales data (from 2017 till 2020) were used for the model building or training, and one-year (2020-2021) predictions were computed for 900 unique SKU's (stock-keeping units). In the present study, the SKU is a combination of sales office, core business field, and material customer group. Various data cleaning and exploratory data analysis algorithms were implemented over raw datasets before use for modeling. Mean absolute percentage error (mape) were estimated for individual predictions from time series and machine learning models. The best model was selected for unique SKU's as per the most negligible mape value.
The aim of marketing controlling is to measure and increase the effectiveness and efficiency of implemented marketing actions. With the help of our templates on this topic, you can align your company with future developments in an intelligent and flexible way.
Marketing controlling is essential for results-based management and control of your marketing. Use the marketing controlling tools to ensure long-term profitability from your investment decisions.
Download our new templates for Marketing Controlling here: http://www.presentationload.com/marketing-controlling-powerpoint-template.html
and make an impact with your next presentation.
The study of the effects of the pricing policies on an organizations profit: ...EECJOURNAL
The main purpose of this research is to examine the influence of pricing policies on organizations’ profit. The researcher applied a quantitative method to analyze the data in this study, the researcher prepared questionnaire and distributed in the different organizations located in Erbil. The survey was divided into two sections; the first section was demographic analysis which started with respondent’s age, gender, and level of education. The second section of survey consisted of 32 questions concerning pricing policies and its impact on organization profit. 89 participants were involved in the current study; however the researcher used SPSS software in order to analyze the gathered data. Moreover, the researcher aimed to develop the main research hypothesis which stated that there is a positive and significant impact of pricing policies on organization profit. The result of a simple regression analysis demonstrates that the value B for pricing policy is .712 which is greater than .0001 this proves that the main research hypothesis is supported which stated that the there is a positive and significant impact of pricing policy on organization profit.
NEW MARKET SEGMENTATION METHODS USING ENHANCED (RFM), CLV, MODIFIED REGRESSIO...ijcsit
A widely used approach for gaining insight into the heterogeneity of consumer’s buying behavior is market segmentation. Conventional market segmentation models often ignore the fact that consumers’ behavior may evolve over time. Therefore retailers consume limited resources attempting to service unprofitable consumers. This study looks into the integration between enhanced Recency, Frequency, Monetary (RFM) scores and Consumer Lifetime Value (CLV) matrix for a medium size retailer in the State of Kuwait. A modified regression algorithm investigates the consumer purchase trend gaining knowledge from a pointof-sales data warehouse. In addition, this study applies enhanced normal distribution formula to remove outliers, followed by soft clustering Fuzzy C-Means and hard clustering Expectation Maximization (EM) algorithms to the analysis of consumer buying behavior. Using cluster quality assessment shows EM algorithm scales much better than Fuzzy C-Means algorithm with its ability to assign good initial points in the smaller dataset.
International Journal of Business and Management Invention (IJBMI)inventionjournals
International Journal of Business and Management Invention (IJBMI) is an international journal intended for professionals and researchers in all fields of Business and Management. IJBMI publishes research articles and reviews within the whole field Business and Management, new teaching methods, assessment, validation and the impact of new technologies and it will continue to provide information on the latest trends and developments in this ever-expanding subject. The publications of papers are selected through double peer reviewed to ensure originality, relevance, and readability. The articles published in our journal can be accessed online.
The Journal will bring together leading researchers, engineers and scientists in the domain of interest from around the world. Topics of interest for submission include, but are not limited to
AUTOMATION OF BEST-FIT MODEL SELECTION USING A BAG OF MACHINE LEARNING LIBRAR...ijaia
Sales forecasting became crucial for industries in past decades with rapid globalization, widespread adoption of information technology towards e-business, understanding market fluctuations, meeting business plans, and avoiding loss of sales. This research precisely predicts the automotive industry sales using a bag of multiple machine learning and time series algorithms coupled with historical sales and auxiliary features. Three-year historical sales data (from 2017 till 2020) were used for the model building or training, and one-year (2020-2021) predictions were computed for 900 unique SKU's (stock-keeping units). In the present study, the SKU is a combination of sales office, core business field, and material customer group. Various data cleaning and exploratory data analysis algorithms were implemented over raw datasets before use for modeling. Mean absolute percentage error (mape) were estimated for individual predictions from time series and machine learning models. The best model was selected for unique SKU's as per the most negligible mape value.
150 word minimum for each paper.. give your feedback(your opinion)MatthewTennant613
150 word minimum for each paper.. give your feedback(your opinion) on each paper. Should be two separate 150 word feedbacks.
PAPER#1 Shan
In today's world, Strategic Management is becoming more intensified. Businesses can no longer depend on reducing prices and improving the quality of their products. (Mandych, Mykytas, Ustik, Zaika, & Zaika, 2021, pg.22). The world around us is becoming more internet-driven, and we are relying on how fast things are accomplished. Businesses have to respond faster with their decisions. Management is becoming more challenged to produce results and conclusions rapidly.
Businesses that have a better approach tend to have the upper hand. Strategic Management must analyze the business's external environments to seize all advantages that can help them determine their threats and opportunities. These strategies can make or break a business. This approach is where the business will determine the company's visions and directions. The system will help determine the goals and objectives they will follow, allowing them to maintain that competitive edge. The process assessments involve planning, monitoring, and analysis. These processes are ongoing. Investigation analysis ensures that the business environment is supported by monitoring the strengths and weaknesses along with the objectives. The business must execute its strategies and control them by adjusting them when needed. This is maintained by developing strategic strategies that align with the external environment's opportunities and threats with their internal strengths and weaknesses. This analysis relates to Porter's Five Forces Model by allowing the company to have the upper hand to increase their competitive advantages with successful thought-out strategies. This analysis relates to Porter's Five Forces Model by enabling the company to have the upper hand to improve its competitive advantages with a successful thought-out plan.
In 1979, Porter transformed the field of strategies with the Five Forces Model (Ryall, 2013, pg.83). The relationship between Strategic Management and Porter's Five Forces Model is that the model allows for aiding managers in evaluating threats that could hurt the business. This guidance will enable companies to plan and neutralize the problem before they occur (Rice,2022, pg.130). The model allows businesses to structure their organization that will enable them to protect their future returns and perform above standard returns. The model can provide businesses with some insight into profit-seeking opportunities, which they could potentially overlook if they failed to have a process before events happen. The surrounding environment is going to be vital in delivering results. Strategic planning is crucial before implantation. Strategies have been used for many things throughout history. The processes used can help determine how successful or unsuccessful the company is or becomes.
References
Mandych, O., Mykytas, A., Ustik, ...
150 word minimum for each paper.. give your feedback(your opinion)AnastaciaShadelb
150 word minimum for each paper.. give your feedback(your opinion) on each paper. Should be two separate 150 word feedbacks.
PAPER#1 Shan
In today's world, Strategic Management is becoming more intensified. Businesses can no longer depend on reducing prices and improving the quality of their products. (Mandych, Mykytas, Ustik, Zaika, & Zaika, 2021, pg.22). The world around us is becoming more internet-driven, and we are relying on how fast things are accomplished. Businesses have to respond faster with their decisions. Management is becoming more challenged to produce results and conclusions rapidly.
Businesses that have a better approach tend to have the upper hand. Strategic Management must analyze the business's external environments to seize all advantages that can help them determine their threats and opportunities. These strategies can make or break a business. This approach is where the business will determine the company's visions and directions. The system will help determine the goals and objectives they will follow, allowing them to maintain that competitive edge. The process assessments involve planning, monitoring, and analysis. These processes are ongoing. Investigation analysis ensures that the business environment is supported by monitoring the strengths and weaknesses along with the objectives. The business must execute its strategies and control them by adjusting them when needed. This is maintained by developing strategic strategies that align with the external environment's opportunities and threats with their internal strengths and weaknesses. This analysis relates to Porter's Five Forces Model by allowing the company to have the upper hand to increase their competitive advantages with successful thought-out strategies. This analysis relates to Porter's Five Forces Model by enabling the company to have the upper hand to improve its competitive advantages with a successful thought-out plan.
In 1979, Porter transformed the field of strategies with the Five Forces Model (Ryall, 2013, pg.83). The relationship between Strategic Management and Porter's Five Forces Model is that the model allows for aiding managers in evaluating threats that could hurt the business. This guidance will enable companies to plan and neutralize the problem before they occur (Rice,2022, pg.130). The model allows businesses to structure their organization that will enable them to protect their future returns and perform above standard returns. The model can provide businesses with some insight into profit-seeking opportunities, which they could potentially overlook if they failed to have a process before events happen. The surrounding environment is going to be vital in delivering results. Strategic planning is crucial before implantation. Strategies have been used for many things throughout history. The processes used can help determine how successful or unsuccessful the company is or becomes.
References
Mandych, O., Mykytas, A., Ustik, ...
Before 1900, despite its weaknesses in effective management of worke.pdfarishaenterprises12
Before 1900, despite its weaknesses in effective management of workers, manufacturing
leadership was well provided by top management. They were technological entrepreneurs,
archictects of productive systems, veritable lions of industry. But when they delegated their
production responsibilities to a second-level department, the factory institution never recovered
its vitality. The lion was tamed. It\'s management systems became protective and generally were
neither enterpreneual nor strategic. Production managers since then have typically had little to do
with initiating substantially new process technology-in contrast to their predecessors before 1900
(skinner 1985).
D) how is Japan (or Germany) different from (or the same as) America with regards to this trend
in manufacturing leadership?
E) taking the structural charestaristics of manufacturing enterprises (e.g., scale, complexity, pace
of technological change) as given, what can be done to revitalize manufacturing leadership?
Solution
Strategic Windows: their nature.
The nature and purpose of strategy and how it is formulated. The nature of marketing strategy
and how this should take account of the interests of various stakeholders when involving such
things as, product/service development and delivery, promotional mix, support services,
manufacturing and production processes, R&D, and material purchasing affect the stakeholders.
Other factors in the business environment that influence marketing strategy: political, economic,
socio-cultural and technological (PEST).
Marketing and competitors: how a firm must be able to position itself competitively in the minds
of its customers so that its products and services stand out very favourably in important respects
in relationship to competitors.
Matching the firm’s products / services with opportunities and threats in the market place. The
limited periods during which the fit between the key requirements of a market and the particular
competencies of a firm competing in that market are at an optimum. Investment in a product line
or a market area should be timed to coincide with periods during which a strategic window is
open. Correspondingly, withdrawal should be considered where something which was a good fit,
is no longer a good fit. Ways in which a market can evolve and how firms might develop a
competitive strategy to take advantage of Strategic Windows.
Portfolio Analysis
How organisations create their own environments rather than simply adapt to existing ones. How
they select the strategic windows of opportunities and threats through which they want to look
out into the world and develop and market product and services to meet the needs of what they
observe to be required in the face of environmental turbulence.
How well the fit between an organization’s products/services meet the needs presented by the
windows of opportunities and threats is a fitting start for exploring the subject of strategic
marketing. It introduces the many factors t.
This is a presentation covering the concepts of demand forecasting. it includes the meaning of demand forecasting, purpose, scope and factors affecting demand forecasting. It also covers the methods of forecasting for both new and existing products.
DATA OUTPUT.docx
GRAPHS FOR QUESTION ONE
MONTHLY STOCK RETURNS
SCATTERPLOT PLUS REGRESSION LINE
TABLE FOR QUESTION TWO (REGRESSION OUTPUT FOR MODEL ONE)
GRAPHS FOR QUESTION THREE
TABLES AND FIGURES FOR QUESTION TWO WHICH REQUIRES USE OF DIAGNOSTIC TOOLS
1.TEST FOR NORMALITY
2.HETEROSKEDASTICTY TEST USING THE WHITE METHOD
3.TEST FOR SERIAL CORRELATION USING LM TEST
USING HAC METHOD TO CORRECT HETEROSKEDASTICITY AND SERIAL CORRELATION (FIXING THE ERRORS)
QUESTION 5-USING CHOW TEST TO TEST WHETHER THE FINANCIAL CRISIS AFFECTED THE RELATIONSHIP
QUESTION 6-REGRESSION OUTPUT FOR MODEL 2
QUESTION 7: WALD TEST FOR TESTING JOINT HYPOTHESIS
-.3
-.2
-.1
.0
.1
.2
.3
-.3
-.2
-.1
.0
.1
.2
.3
808284868890929496980002040608
ResidualActualFitted
0
20
40
60
80
100
808284868890929496980002040608
General Dynamics Corp S
0
4
8
12
16
20
808284868890929496980002040608
Federal Funds Rate (Effective) FED
-.3
-.2
-.1
.0
.1
.2
.3
808284868890929496980002040608
NRSt
PROFESSOR'S COMMENTS.docx
1. In question 2, the model requires you to use the monthly stock returns to do the regression. By contrast, it is evident that you have used nominal stock prices instead of returns. This is totally wrong. You have not even made reference to the Discounted Cash flow model
2. In question 3 you are required to plot the actual values, the fitted values (predicted values) and the residuals and comment on model fitting. I am afraid that it apparently appears that you have not done so
3. You have not answered question four
4. You have not answered question five
5. Where is the answers for questions 6 and 7. To be precise the test for joint hypothesis required in question 7 is not shown and the outcome and the conclusions there in.
ECONOMETRICS ASSIGNMENT.pdf
INSTRUCTIONS
Word Limit 2500 words (excluding appendix and reference list)
Refer to the Journal Article Attached in the email as a guide on how to report
the results of the data analysis.
E-VIEWS is the preferred software for data analysis but if you are not
conversant with it you can use STATA or SPSS.
The deadline for this assignment is midday 21
st
,November 2016.
1
You have been allocated monthly time-series data for the United States
over the period January 1980-December 2009. The data refer to the following
variables:
S :the nominal stock price of a given company;
FED :the nominal short-term interest rate, measured by the effective federal
funds ratea (yields in percentage per annum);
IP :the level of industrial production.
Let NSRt be the monthly stock returns of the assigned company. Consider
the following regression model:
NSRt = β1 + β2 · FEDt + ut, (1)
where FEDt is assumed to be a stationary series.
1. Report the time series plots of the series and the scatter plot. Comment
on the graphs. [10%]
2. Use Ordinary Least Squares (OLS) to estimat.
Cost Analysis ModelsUnit 3 Written AssignmentBUS .docxbobbywlane695641
Cost Analysis Models
Unit 3: Written Assignment
BUS 5110
Managerial Accounting
Unit 3
Introduction
Cost management is important for all businesses and is used to plan and control the budget. This is done by analysing business practices, predicting expenditures in advance and reducing the chance of over spending in relation to income. Using the client provided data for a business involved in the catering and events industry we can evaluate how productive and effective her business is.
Provide an accurate solution.
We can see from the data in the attached costing sheet that the company has a break even point of 3158 events. To come to this conclusion, we calculated the revenue per event (Current revenue / number of events) $22,500,000 / 5000 = $4,500. We also require our Contribution margin (Revenue per event - Variable cost per event) $4,500 - $2,600 = $1,900. To calculate the Breakeven point, we simply take the Fixed cost and divide that by the Contribution margin = 6,000,000 / 1,900 = 3157.89
Hypothetically, if the company decided they’d like to improve their revenue and increase their profits from $3,500,000 to $5,000,000 we can use the data to calculate the number of events required to reach that target. Using the Units to Achieve a Target Income formula (Total fixed costs + Target income) / Contribution margin per unit = (6,000,000 + 5,000,000) / 1,900 = 5789.47 = 5789 events (Walther, L. M. & Skousen, C.J., 2009).
Provide a narrative that defines and discusses the purpose of assigning cost categories of fixed and variable costs.
Operating a business incurs a range of costs. These can be defined as either fixed costs which don’t change in relation to activity and variable costs which do. These costing structures will likely differ between businesses and industries. Companies have even been known to use different costing structures between different internal departments. (CFI., n.d.)
Many fixed costs are going to be unavoidable and come from the simple operational side of your business. Costs such as depreciation, taxes and rent will likely remain unchanged however other fixed costs such as advertising budgets are more discretionary. Variable costs are also able to be altered depending on the size and scale of your business. For example, order quantities can be increased to bring unit costs down however before committing to such decisions forecasting your sales based on this should also be carried out to ensure you don’t end up grossly overstocked (Walther, L. M. & Skousen, C.J., 2009).
In order to maximise profits companies are required to minimise or eradicate unnecessary costs any way they can, ideally with no impact on the quality of the final product. A manager must understand both of these categories and the importance they play in the overall running of the business if they’re ever going to effectively improve the business model, reduce costs and remain profitable.
Provide a narrative that defines and discusses.
This study investigated the Effect of Market Segmentation on the performance of Micro, Small and
Medium Scale Enterprises (MSMEs) in Makurdi Metropolis, Benue state Nigeria
1
10
Marketing Management
Assignment Two – MKTM028
Segmenting, Targeting and Positioning (STP)
NAME
UON ID
SUBMISSION DATE
7/9/2022
MODULE
MKTM028
WORD COUNT
2,400
LECTURER
Ms. Sally Lo
Table of Contents
INTRODUCTION 3
ANALYSIS OF SEGMENTING, TARGETING AND POSITIONING 3
Market Segmentation 3
Market Targeting 5
Market Positioning 6
CASE STUDY 8
Vodafone 8
RECOMMENDATION 9
RRFERENCE 11
INTRODUCTION
With the use of target marketing, businesses may zero in on the most promising customer base. Rather of offering a comprehensive product line to accommodate all market groups, some companies may choose to focus on satisfying a narrower subset of clients who have a common business need (Supriono, 2018; Camilleri, 2017). One of the most important parts of any marketing plan is choosing the right target market. These procedures for making choices revolve on the time-tested marketing strategy framework of segmentation, targeting, and positioning (STP)]. Segmenting the market is a flexible strategy. Markets are broken down into subsets so that a corporation may target certain customer demographics with tailored product and service offerings. The word "targeting" refers to the method used to assess and choose the intended audience. Market positioning refers to the perceived position in the market where the company sees the product fitting (Orr et al, 2022). Due to its importance in determining a company's long-term performance, STP has been called "a critical necessity in marketing strategy". This report's primary purpose is to assess existing research on STP and to investigate the field's potential usefulness for industry by contrasting and contrasting a variety of sectors and companies.ANALYSIS OF SEGMENTING, TARGETING AND POSITIONING
Market Segmentation
One of the first steps in making an overall marketing strategy is to do a market segmentation study. This helps you keep track of how the strategy is being made and makes sure the plan will work. Market segmentation is the process of dividing a market into submarkets based on a characteristic of the market. Among the things that make up a market are demographic trends, segment needs, consumer preferences, and regional dynamics. For market segments to be useful, they must be easy to find, easy to tell apart, measurable, important, actionable, and stable. Several academics say that companies have used a wide range of segmentation techniques, from those that are specific to each country to those that create groups on a global scale and then use differences in each country to make the most money. Differentiating segmentation strategies for a given group of customers depends on how the group buys and how well the brands are known in the market. This is true, according to research (Samson, 2016; Leonidou et al., 2002). Cluster analysis software or segmentation trees can be used to look at the different subgroups. The next step is to decide how many market niches the co ...
110Marketing ManagementAssignment Two – MKTM028SantosConleyha
1
10
Marketing Management
Assignment Two – MKTM028
Segmenting, Targeting and Positioning (STP)
NAME
UON ID
SUBMISSION DATE
7/9/2022
MODULE
MKTM028
WORD COUNT
2,400
LECTURER
Ms. Sally Lo
Table of Contents
INTRODUCTION 3
ANALYSIS OF SEGMENTING, TARGETING AND POSITIONING 3
Market Segmentation 3
Market Targeting 5
Market Positioning 6
CASE STUDY 8
Vodafone 8
RECOMMENDATION 9
RRFERENCE 11
INTRODUCTION
With the use of target marketing, businesses may zero in on the most promising customer base. Rather of offering a comprehensive product line to accommodate all market groups, some companies may choose to focus on satisfying a narrower subset of clients who have a common business need (Supriono, 2018; Camilleri, 2017). One of the most important parts of any marketing plan is choosing the right target market. These procedures for making choices revolve on the time-tested marketing strategy framework of segmentation, targeting, and positioning (STP)]. Segmenting the market is a flexible strategy. Markets are broken down into subsets so that a corporation may target certain customer demographics with tailored product and service offerings. The word "targeting" refers to the method used to assess and choose the intended audience. Market positioning refers to the perceived position in the market where the company sees the product fitting (Orr et al, 2022). Due to its importance in determining a company's long-term performance, STP has been called "a critical necessity in marketing strategy". This report's primary purpose is to assess existing research on STP and to investigate the field's potential usefulness for industry by contrasting and contrasting a variety of sectors and companies.ANALYSIS OF SEGMENTING, TARGETING AND POSITIONING
Market Segmentation
One of the first steps in making an overall marketing strategy is to do a market segmentation study. This helps you keep track of how the strategy is being made and makes sure the plan will work. Market segmentation is the process of dividing a market into submarkets based on a characteristic of the market. Among the things that make up a market are demographic trends, segment needs, consumer preferences, and regional dynamics. For market segments to be useful, they must be easy to find, easy to tell apart, measurable, important, actionable, and stable. Several academics say that companies have used a wide range of segmentation techniques, from those that are specific to each country to those that create groups on a global scale and then use differences in each country to make the most money. Differentiating segmentation strategies for a given group of customers depends on how the group buys and how well the brands are known in the market. This is true, according to research (Samson, 2016; Leonidou et al., 2002). Cluster analysis software or segmentation trees can be used to look at the different subgroups. The next step is to decide how many market niches the co ...
Many countries have seen the importance of financial education by making financial
education a national strategy. In Vietnam, although the National Strategies for Inclusive Financial
Education has been proposed since 2017 and officially included in the National Financial Inclusion
Strategy in 2020, however, financial education is still quite new, and many people are not aware of
the necessity of financial l
Today, in the rapidly emerging globalization process, increasing the competitiveness of enterprises
depends on increasing of their firm performance. Although there are many methods and techniques affecting
firm performance, Information technology (IT) capabilities has become one of the most widely used method,
especially in dealing with supply chain matters of a firm. The aim of our study is to express whether innovation
and organization learning is effective as intermediate variable to the effects of IT capabilities at firm’s
performance. The opinion which claim
Globally, the number of startup companies has rapidly expanded during the last 5-8 years. Offering
products and/or services that greatly enhance the lives of its clients is a major focus for these firms. In India,
local and federal government initiatives have provided new enterprises and entrepreneurs with much
momentum and assistance, helping India become the world's top startup location. The Government of India
(GOI) launched the "Startup India" campaign in 2015 to promote entrepreneurship and support businesses to
achieve this goal (Babu, S., Sridevi, K.,2019). An IBM Center for Business Value and Oxford Economics study
in 2018 found that 90% of Indian companies fail within the first five years of operation. Potential difficulties
that startups may run across, both generally and specifically in the Indian market, have been described by
several authors.
Behaviour finance is the study of how psychological phenomena affect financial behaviour. This
financial science is used in making financial decisions. Amid the development of the digital economy, paylater
innovation has emerged. It is feared that the ease of use of paylater can have a negative impact, one of which is
the attitude of impulsive buying. This research will analyze the effect of financial literacy, self-control, risk
perception, and percieved ease of use on impulsive buying behaviour. This research is based on Decision Affect
Theory, which is a theory that discusses financial decision behaviour that is influenced by self-emotion. This
research is uses purposive sampling wi
Improving the business environment is one of the key strategies to promote local and regional
economic development. However, which factors affect the business environment of the provinces is still
controversial. Using survey data from 400 investors and managers and a multivariate regression analysis
method, this study has identified the factors affecting the business environment of Hai Phong province. The
analysis results show that there are 09 factors affecting the business environment of Hai Phong City, including
entry costs, land access and tenure, transparent, informal charges, time cost, pro-activeness, business support
services, labor training and legal institutions. In
The effect of work attitude and innovation ability on employee innovation performance is of great
significance for improving the innovation ability of manufacturing enterprises and building an "Innovative
Country" in China.This article theoretical analysis was conducted on the mechanism by which the work attitude
of employees in manufacturing enterprises affects innovation performance and the mediating mechanism of
innovation ability. Based on data from Chinese manufacturing enterprises, empirical analysis was conducted
using SEM models. Resear
The concept of organizational resilience continues to grow in focus and importance, but there
has yet to be an agreed upon measure of organizational resilience. Organizational resilience can be seen as a
corporation’s ability to adapt to change and maintain flexibility within their supply chain. Resilience and
flexibility at all organizational levels is necessary, in a proactive manner, to turn resilience into a competitive
advantage
In this paper, by using the basic method of differential geometry, combined with the optimization
theory and the basic technique of data analysis, the definition, basic properties and statistical characteristics of
nonlinear correlation coefficients on manifolds are studied and given, test the rationality and validity of the
nonlinear correlation coefficient defined in this paper. Therefore, the study of this paper has certain theoretical
value and potential practical significance.
This study aims to analyze and prove whether there is a positive and significant influence
between product quality and poki prices on purchasing decisions for Kobba brand coffee. The survey was
conducted using 53 respondents who were buyers who had purchased Kobba brand coffee more than once.
Information from respondents was obtained through a list of questions that were sent and returned by
respondents
In this paper, we introduce a universal framework for mean-distortion robust risk measurement and
portfolio optimization. We take accounts for the uncertainty based on Gelbrich distance and another uncertainty
set proposed by Delage & Ye. We also establish the model under the constraints of probabilistic safety
criteria and compare the different frontiers and the investment ratio to each asset. The empirical analysis in the
final part explores the impact of different parameters on the model results.
Despite the attainment of the famous Millennium Development Goals (MDGs) of reducing the number
of poor people across the globe a significant number still live below the poverty line. The problem of poverty is
more endemic in developing countries like Nigeria. Several intervention efforts have been in place to address
the poverty question which persists partly due to serious financial exclusion and unethical activities of informal
finance providers.
The focus of this research was to establish the effect of entrepreneurship Ecosystem in inculcating
entrepreneurial propensity for community development. Promotion of entrepreneurship in Kenya has existed
ever since independence. The Government has shown tremendous support to entrepreneurship growth. The
Government have channelled financial support through funding such as Women Enterprise fund, Youth
Enterprise Fund and Uwezo Fund
In this paper, we consider an AAI with two types of insurance business with p-thinning dependent
claims risk, diversify claims risk by purchasing proportional reinsurance, and invest in a stock with Heston
model price process, a risk-free bond, and a credit bond in the financial market with the objective of maximizing
the expectation of the terminal wealth index effect, and construct the wealth process of AAI as well as the the
model of robust optimal reinsurance-investment problem is obtained, using dynamic programming, the HJB
equation to obtain the pre-default and post-default reinsurance-investment strategies and the display expression
of the value function, respectively, and the sensitivity of the model parameters is analyzed through numerical
experiments to obtain a realistic economic interpretation. The model as well as the results in this paper are a
generalization and extension of the results of existing studies.
:Textiles and clothing are a fundamental part of everyday life and an important sector in the global
economy. It is hard to imagine a world without textiles. Clothes are worn by almost everyone, almost all the time
and it also becomes an important expression for an individuality. In 2015, emission from textiles production
totaled 1.2 billion tons of CO2 equivalent throughout its lifecycle. The fashion industry is a large consumer of
water, high volumes of water containing
In this paper, we construct a Credit Default Swap pricing model for default recovery rates under
distributional uncertainty based on a structured pricing model and distributional uncertainty theory. The model
is algorithmically transformed into a solvable semi-definite programming problem using the Lagrangian dual
method, and the solution of the model is given using the projection interior point method. Finally, an empirical
analysis is conducted, and the results show that the model constructed in this paper is reasonable and efficient
The closures of schools, colleges, and universities in many countries worldwide during the COVID19 pandemic have reshaped every aspect of our normal lives and educational experience. As a result of
extended periods of lockdown, whole populations have been advised to stay in their households and
communicate with others through distance electronic communications methods such as Zoom, Teams, Google
meetings etc. More than 1
Even though economists and academics have been studying money laundering for many years, there
are still gaps in the research because there is a dearth of trustworthy data on the activity as well as an absence
of specific sources and methods of collection in government-based reporting. The Walker-Unger gravity model
was used in this study to determine the countries that Russian-based money launderers used as funding
destinations between the years 2000 and 2020, as well as whether there are any variations in country rankings
during economic downturns. The investigation's findings indicated that even during recessionary times, money
launderers with Russian bases consistently preferred certain countries as their destination
This study will establish a scientific foundation for analyzing and assessing the development of
human resources in industrial parks of Hai Duong province. According to statistics and primary data, the
study analyzes the current situation of human resource development in the industrial parks in Hai Duong
province, states achievements, limitations and their causes, thereby giving solutions to improve the human
resource development in industrial parks of Hai Duong province in the future for the economic development
of industrial parks in particular and Hai Duong province in general.
Solar photovoltaic systems are becoming essential in renewable energy sources to help reduce
dependence on renewable energy sources, fossil fuels and mitigate climate change. In the world today, many
successful businesses bring efficiency to the environment as well as the global economy. However, to evaluate
the business performance of the global supply chain, it is necessary to find an appropriate method. This article
uses data envelopment analysis (DEA) and Malmquist Productivity Index (MPI) methods to compare
performance across businesses
The objective of this research is 1) to study social media usage behavior of the elderly and 2) to
examine the relationship between factors of the social media usage behavior of the elderly in Surat Thani
Province, Thailand. The data were collected from selected elderly aged 60 years and older in Surat Thani
Province. The number of the sample in this study was 400. The questionnaire was used as a tool to collect the
data. Statistics used were frequency, percentage, mean, standard deviation, and Chi-Square
More from International Journal of Business Marketing and Management (IJBMM) (20)
LA HUG - Video Testimonials with Chynna Morgan - June 2024Lital Barkan
Have you ever heard that user-generated content or video testimonials can take your brand to the next level? We will explore how you can effectively use video testimonials to leverage and boost your sales, content strategy, and increase your CRM data.🤯
We will dig deeper into:
1. How to capture video testimonials that convert from your audience 🎥
2. How to leverage your testimonials to boost your sales 💲
3. How you can capture more CRM data to understand your audience better through video testimonials. 📊
Enterprise Excellence is Inclusive Excellence.pdfKaiNexus
Enterprise excellence and inclusive excellence are closely linked, and real-world challenges have shown that both are essential to the success of any organization. To achieve enterprise excellence, organizations must focus on improving their operations and processes while creating an inclusive environment that engages everyone. In this interactive session, the facilitator will highlight commonly established business practices and how they limit our ability to engage everyone every day. More importantly, though, participants will likely gain increased awareness of what we can do differently to maximize enterprise excellence through deliberate inclusion.
What is Enterprise Excellence?
Enterprise Excellence is a holistic approach that's aimed at achieving world-class performance across all aspects of the organization.
What might I learn?
A way to engage all in creating Inclusive Excellence. Lessons from the US military and their parallels to the story of Harry Potter. How belt systems and CI teams can destroy inclusive practices. How leadership language invites people to the party. There are three things leaders can do to engage everyone every day: maximizing psychological safety to create environments where folks learn, contribute, and challenge the status quo.
Who might benefit? Anyone and everyone leading folks from the shop floor to top floor.
Dr. William Harvey is a seasoned Operations Leader with extensive experience in chemical processing, manufacturing, and operations management. At Michelman, he currently oversees multiple sites, leading teams in strategic planning and coaching/practicing continuous improvement. William is set to start his eighth year of teaching at the University of Cincinnati where he teaches marketing, finance, and management. William holds various certifications in change management, quality, leadership, operational excellence, team building, and DiSC, among others.
Kseniya Leshchenko: Shared development support service model as the way to ma...Lviv Startup Club
Kseniya Leshchenko: Shared development support service model as the way to make small projects with small budgets profitable for the company (UA)
Kyiv PMDay 2024 Summer
Website – www.pmday.org
Youtube – https://www.youtube.com/startuplviv
FB – https://www.facebook.com/pmdayconference
Tata Group Dials Taiwan for Its Chipmaking Ambition in Gujarat’s DholeraAvirahi City Dholera
The Tata Group, a titan of Indian industry, is making waves with its advanced talks with Taiwanese chipmakers Powerchip Semiconductor Manufacturing Corporation (PSMC) and UMC Group. The goal? Establishing a cutting-edge semiconductor fabrication unit (fab) in Dholera, Gujarat. This isn’t just any project; it’s a potential game changer for India’s chipmaking aspirations and a boon for investors seeking promising residential projects in dholera sir.
Visit : https://www.avirahi.com/blog/tata-group-dials-taiwan-for-its-chipmaking-ambition-in-gujarats-dholera/
Cracking the Workplace Discipline Code Main.pptxWorkforce Group
Cultivating and maintaining discipline within teams is a critical differentiator for successful organisations.
Forward-thinking leaders and business managers understand the impact that discipline has on organisational success. A disciplined workforce operates with clarity, focus, and a shared understanding of expectations, ultimately driving better results, optimising productivity, and facilitating seamless collaboration.
Although discipline is not a one-size-fits-all approach, it can help create a work environment that encourages personal growth and accountability rather than solely relying on punitive measures.
In this deck, you will learn the significance of workplace discipline for organisational success. You’ll also learn
• Four (4) workplace discipline methods you should consider
• The best and most practical approach to implementing workplace discipline.
• Three (3) key tips to maintain a disciplined workplace.
Digital Transformation and IT Strategy Toolkit and TemplatesAurelien Domont, MBA
This Digital Transformation and IT Strategy Toolkit was created by ex-McKinsey, Deloitte and BCG Management Consultants, after more than 5,000 hours of work. It is considered the world's best & most comprehensive Digital Transformation and IT Strategy Toolkit. It includes all the Frameworks, Best Practices & Templates required to successfully undertake the Digital Transformation of your organization and define a robust IT Strategy.
Editable Toolkit to help you reuse our content: 700 Powerpoint slides | 35 Excel sheets | 84 minutes of Video training
This PowerPoint presentation is only a small preview of our Toolkits. For more details, visit www.domontconsulting.com
Discover the innovative and creative projects that highlight my journey throu...dylandmeas
Discover the innovative and creative projects that highlight my journey through Full Sail University. Below, you’ll find a collection of my work showcasing my skills and expertise in digital marketing, event planning, and media production.
Affordable Stationery Printing Services in Jaipur | Navpack n PrintNavpack & Print
Looking for professional printing services in Jaipur? Navpack n Print offers high-quality and affordable stationery printing for all your business needs. Stand out with custom stationery designs and fast turnaround times. Contact us today for a quote!
Skye Residences | Extended Stay Residences Near Toronto Airportmarketingjdass
Experience unparalleled EXTENDED STAY and comfort at Skye Residences located just minutes from Toronto Airport. Discover sophisticated accommodations tailored for discerning travelers.
Website Link :
https://skyeresidences.com/
https://skyeresidences.com/about-us/
https://skyeresidences.com/gallery/
https://skyeresidences.com/rooms/
https://skyeresidences.com/near-by-attractions/
https://skyeresidences.com/commute/
https://skyeresidences.com/contact/
https://skyeresidences.com/queen-suite-with-sofa-bed/
https://skyeresidences.com/queen-suite-with-sofa-bed-and-balcony/
https://skyeresidences.com/queen-suite-with-sofa-bed-accessible/
https://skyeresidences.com/2-bedroom-deluxe-queen-suite-with-sofa-bed/
https://skyeresidences.com/2-bedroom-deluxe-king-queen-suite-with-sofa-bed/
https://skyeresidences.com/2-bedroom-deluxe-queen-suite-with-sofa-bed-accessible/
#Skye Residences Etobicoke, #Skye Residences Near Toronto Airport, #Skye Residences Toronto, #Skye Hotel Toronto, #Skye Hotel Near Toronto Airport, #Hotel Near Toronto Airport, #Near Toronto Airport Accommodation, #Suites Near Toronto Airport, #Etobicoke Suites Near Airport, #Hotel Near Toronto Pearson International Airport, #Toronto Airport Suite Rentals, #Pearson Airport Hotel Suites
Unveiling the Secrets How Does Generative AI Work.pdfSam H
At its core, generative artificial intelligence relies on the concept of generative models, which serve as engines that churn out entirely new data resembling their training data. It is like a sculptor who has studied so many forms found in nature and then uses this knowledge to create sculptures from his imagination that have never been seen before anywhere else. If taken to cyberspace, gans work almost the same way.
Implicitly or explicitly all competing businesses employ a strategy to select a mix
of marketing resources. Formulating such competitive strategies fundamentally
involves recognizing relationships between elements of the marketing mix (e.g.,
price and product quality), as well as assessing competitive and market conditions
(i.e., industry structure in the language of economics).
The Influence of Marketing Strategy and Market Competition on Business Perfor...
Forecasting accuracy of industrial sales with endogeneity in firm-level data
1. International Journal of Business Marketing and Management (IJBMM)
Volume 6 Issue 4 April 2021, P.P. 42-52
ISSN: 2456-4559
www.ijbmm.com
International Journal of Business Marketing and Management (IJBMM) Page 42
Forecasting accuracy of industrial sales with
endogeneity in firm-level data
Adriana Bruscato Bortoluzzo1
, Danny Pimentel Claro2
1
(Quantitative Methods / Insper, Brazil)
2
(Marketing / Insper, Brazil)
ABSTRACT : Over- or underestimating sales is detrimental to marketing and sales efforts as well as
inventories and cash flow management. Thus the purpose of this investigation is to evaluate the forecasting
accuracy of three competing multivariate time-series models that take into account existing endogeneity in
monthly firm-level data from an industrial manufacturing firm. Two-stage least squares transfer function model
including instrumental variables, Vector Autoregressive (VAR) model and Bayesian VAR are estimated and
their forecasting performances are compared to an autoregressive moving average model (benchmark). using
out of sample error measures. According to forecasting accuracy measures, models that take into account
endogeneity outperform the benchmark. They also performed better when applied to data that includes the 2008
financial crisis, reinforcing the use of these proposed models in turbulent times to forecast sales. Only a little
effort has been made in companies to model the endogeneity of the data, however great are the gains in sales
forecasting with such statistical tools. Whatever the company, these models can be applied since there exists
historical data. Previous literature in management has resorted to standard time series forecasting techniques,
but has not employed models that accommodate potential endogeneity among the explanatory variables in firm-
level data. Marketing effort affects sales as well as managers’ decisions regarding marketing investments and
project proposals can also be affected by sales.
KEYWORDS - Industrial sales, Forecasting, Endogeneity, Time series
I. Introduction
Firms of industrial products use sales forecasting to operate efficiently and meet customer demand. Substantial
over- or underestimates of demand can cause serious problems in various firm's management areas [1].
Forecasting sales volume is crucial for creating operating budgets, which play an important role in a firm’s
internal planning, motivation and performance management functions [2]. Industrial products primarily
constitute those used in the production of other products and are customized using a ‘made to order’ approach.
Inaccurate forecasting affects a range of a manufacturer’s activities from delivery schedules to capacity loss due
to overstocking, suboptimal capacity utilization and excessive and obsolete inventory [3]. The inaccurate
forecasts influence negatively efficiency and sales performance. Given the relevance of this issue, industrial
sales forecasting has been studied by researchers and addressed in various ways.
The majority of previous studies focusing on sales forecasting models sought to explain sales behavior
by examining time series of internal manufacturer variables, such as marketing expenses [4]. [5] and [6]
demonstrated the importance of macroeconomic variables (e.g., price, demand, exchange rate) to forecast a
firm’s sales in the consumer market. These variables have also been included in studies of industrial markets [7].
In the auto-parts industry, forecasting models are a component of complex support systems that need to be
parsimonious with respect to variable selection due to the cost of collecting and treating the data [8]. Even for
small firms, [9] showed that using a formal sales forecasting framework there is a gain, and they applied a
Bayesian decision theory in the production of sales forecasts.
Industrial products require particular attention of sales forecasting models. [10] noted differences
between the statistical approaches applied to consumer products and the statistical approaches applied to
industrial products. Sales forecasts in industrial markets are also modified using the opinions of the sales team
and management [4], [13]. [14] highlighted this tendency and found that only 6% of the 300 industrial firms
sampled used regressions as part of their forecasting method. [15] suggested that the accuracy of sales volume
2. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 43
forecasting can be improved by using statistical models in lieu of simple personal opinions that may be affected
by qualitative considerations and political maneuvering intended to appease conflicting objectives within the
firm. As an example, forecasts based on opinions can show negative bias, particularly if a fraction of the sales
team’s income or performance targets were linked to exceeding expected values [10]. In addition, research has
indicated that attempting to encourage the sales team to participate in forecasting is innocuous because linking
the forecast to the sales team’s input has no significant, positive influence on forecast accuracy [11]. While the
task is difficult, recent research has concentrated on modeling the effect of the opinions and judgment of
managers on improving the effectiveness of sales forecasts [12].
Previous studies have considered a range of variables to forecast sales, both managerial and economic,
and treated these variables as exogenous. However, various management decisions affect sales and the decisions
are also intimately affected by sales expectations. For instance, marketing investment decisions have a causal
effect on sales outcomes, and sales outcomes simultaneously affect marketing investment decisions. An
endogenous variable is both an input and an output variable. We believe that econometric models that properly
account for these important interrelationships may perform superiorly than standard models regarding sales
forecasting.
The main objective of this paper is to evaluate the forecasting accuracy of three competing multivariate
time-series models that take into account existing endogeneity: (1) two-stage least squares transfer function
model (2SLSTF) including instrumental variables, (2) vector autoregressive model (VAR) and (3) Bayesian
vector autoregressive model (BVAR). An autoregressive moving average model (ARMA) was estimated as a
benchmark for the forecasting comparisons. We calculate the out of sample root mean squared error (RMSE),
mean absolute error (MAE) and mean absolute percentage error (MAPE) to evaluate the relative performance of
the estimated models.
The paper makes two contributions. First, the data set used to estimate the models include firm-level
data as well as industry and economic public data. This is a unique data structure of industrial products that
represents the sales settings and includes relevant variables to forecasting (e.g., [16]). The firm level variables
include marketing expenditure and sales acquisition measurement (i.e. proposals). The data also include
economic variables such as reference rate, stock market index and exchange rate.
Second, the results show that the multivariate models are more accurate than the univariate ones,
specially the 2SLSTF model that outperforms the other models according to forecasting accuracy measures. The
results illustrate the importance of properly addressing endogeneity in industrial sales forecasting. The 2SLSTF
model also performed better when applied to data from the 2008 financial crisis, reinforcing the importance of
economic variables in such turbulent contexts [5], [17].
The remainder of the article proceeds as follows. In Section 2, there is a descriptive analysis of the data.
In Section 3, a detailed description of the models to forecast industrial sales is presented. In Section 4, it is
discussed the final versions of the models and their forecasting performance is compared. Finally, Section 5
concludes the paper.
II. Data description
The firm-level data were collected from the sales records of a European firm operating in South America. This
operation has a leading position in the market. We selected the best-selling product (between 45% and 55% of
total sales), which is made to order with a set of core components and one customized component to meet
customers’ needs and is applied in a wide variety of industries (e.g., mining, steel, pulp and paper, automotive,
oil and gas, power generation, textiles, food). In South America, we focused on Brazil, which is the most
representative market and hosts the largest plant in operation outside Europe. The Brazilian government requires
a minimum of 60% local content in these products, prohibiting direct imports and creating local investment
incentives. Once they have met this condition, customers are able to access investment capital with low interest
rates and an extended repayment period. The firm’s marketing campaigns generate product awareness and
highlight the product mix and integrated service features. Customers are accessed through major industry trade
shows and advertisements in specialized magazines and websites. A dedicated and stable (i.e., low turnover)
sales force engages in face-to-face selling and reinforces marketing efforts. The sales force visits customers and
develops customized offers to effectively satisfy customers’ needs.
Table 1 presents a description of the variables that are used in this study. The forecasting variable is
monthly sales volume from January 2004 to April 2012 (n=100 observations). This time series includes the
2008 financial crisis and the years 2009 and 2010, when substantial government incentives were implemented to
support investments across a wide variety of industries in which the firm’s customers operate. This data set
represents industrial product context and is set up similarly to other data sets (e.g., [16]). Unfortunately, the
company only allows the use of real data after 6 years of its occurrence, however this does not invalidate the
modeling techniques or the contributions of the article that are timeless (data are available upon request).
3. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 44
The explanatory variables were mainly drawn from existing forecasting and industrial marketing
literature. The variables are divided into two sets: endogenous and exogenous. Two explanatory variables
(proposals and marketing) were identified as endogenous because they are expected to have a bidirectional
relationship with sales volume. The variable ‘proposals’ captures the number of project proposals that the sales
force develops for customers each month. The firm considers this indicator when future sales and purchases of
input supplies are predicted. The variable ‘marketing’ captures monthly investments in advertisements in
specialized media, the sales force’s promotional materials and spending on industry trade shows and mobile
showrooms.
Seven explanatory variables were identified as exogenous. The variable ‘reference rate’ is the main
reference rate for investment capital loans, which are provided by the national central bank. A ‘confidence
index’ was included to capture a subjective measure of economic activity, and a ‘stock market’ index provides
an objective measure of such activity. We also included an ‘exchange rate’ variable (BRL/USD) and two
variables that account for the incentive programs that the government provides to industries: total BNDES
(government bank to foster economic development) loan volume and the BNDES loan program with reduced
interest rates (PRI). Finally, we accounted for foreign direct investments in industrial plant production (FDI).
Table 1. Variables’ Description
Variable Description Source
Endogenous
Sales Volume Sales volume treated, in millions of R$ Firm Records
Proposals New proposals of sales (short, medium and long run) Firm Records
Marketing Total marketing spending, in thousands of R$ Firm Records
Exogenous
Reference Rate SELIC interest rate http://www.ipeadata.gov.br/
Confidence
index
Industrial confidence index ICI-FGV http://portalibre.fgv.br
Stock Market BM&F-Bovespa market index http://www.bmfbovespa.com.br
Exchange Rate Exchange rate (R$/US$). monthly average of bid level http://www.ipeadata.gov.br/
BNDES loans BNDES total loan volume, in million R$ http://www.bndes.gov.br/
PRI
BNDES – loan program with low interest rates (dummy
variable)
http://www.bndes.gov.br/
FDI Foreign direct investment (FDI) http://www.ipeadata.gov.br/
The variables sales volume, marketing, BNDES loan volume and FDI were deflated through the use of
the national index of market prices (IGPM). which is calculated by the Getulio Vargas Foundation on a monthly
basis. We considered the period from November 2008 to July 2010, when the Brazilian economy was more
influenced by the subprime crisis. To reduce the effect of the crisis on several sectors of the Brazilian economy,
including industrial products manufacturers, the government provided incentives for purchasing industrial
products and reduced the interest rate charged for loans (PRI) for this purpose from July 2009 to March 2011.
Figure 1 shows descriptive graphs of the variables considered and allows us to establish some patterns.
For instance, the reference rate is negatively correlated with sales, which makes economic sense. In the period
following the outbreak of the 2008 crisis (Nov/2008-Jul/2010). increases in the reference rate and exchange rate
occurred. The confidence index, the stock market index and the FDI also declined just prior to the decline in
sales. Thus, these economic variables may be useful in forecasting the behavior of sales during the crisis period.
Moreover, regarding the government incentive programs, an increase in sales is associated with increasing
BNDES loan volume. The government’s incentive generated a notable increase in sales of industrial products,
while FDI comes right after increases in sales.
4. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 45
Figure 1. Descriptive Graphs of the Time Series (Sales is on the Left Axis)
5. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 46
Table 2 summarizes the time-series data considered in the analysis, specifically the average of each
variable by year. Sales volume varies over time, with a decline in the crisis period (2008-10) and a recovery
soon after. The average number of proposals was approximately 200 per month, while average spending on
marketing was approximately $35 thousand per month. A sharp increase in proposals occurred in 2012, nearly
doubling the figures in the preceding months, which may reflect the increase in marketing expenses in the
previous year.
Table 2. Descriptive Analysis of Time Series per Year
Variable Year 2004 2005 2006 2007 2008 2009 2010 2011 2012
Sales Mean 12,358 17,694 20,424 19,964 24,487 14,185 24,046 19,291 10,153
SD 3,777 9,083 5,182 7,473 7,534 13,355 12,610 9,132 2,347
Proposals Mean 152 165 186 202 217 177 254 194 362
SD 36 34 51 51 49 43 86 61 143
Marketing Mean 15,210 21,295 39,673 33,477 36,283 35,558 45,676 60,369 27,539
SD 6,088 10,976 27,060 24,033 27,656 31,786 50,571 66,298 25,862
Reference rate Mean 16.3 19.1 15.4 12.1 12.4 10.1 9.9 11.8 9.9
SD 0.4 0.7 1.5 0.8 1.1 1.8 0.9 0.5 0.7
Confidence index Mean 108 99 101 116 110 94 116 107 104
SD 4 5 4 4 15 12 2 5 1
Stock market Mean 22,323 27,543 38,081 53,213 55,329 52,748 67,290 61,348 63,791
SD 1,730 2,807 2,339 7,278 12,083 10,303 2,766 5,647 2,722
Exchange rate Mean 2.9 2.4 2.2 1.9 1.8 2.0 1.8 1.7 1.8
SD 0.1 0.2 0.0 0.1 0.3 0.2 0.0 0.1 0.1
BNDES Loans Mean 153 220 216 303 299 209 549 484 285
SD 29 48 51 84 60 49 131 49 28
FDI Mean 2,244 1,774 2,177 3,842 4,452 2,525 4,386 5,667 4,883
SD 2,376 1,035 769 3,427 2,357 1,280 4,160 1,387 972
Note: 2012 is From January to April
We assessed the stationarity of each time series through the use of correlograms and the augmented
Dickey–Fuller (ADF) unit root test. We were then able to select the appropriate transformations and variables
for use in the forecasting models. The correlogram of the forecasting variable, sales volume, exhibited
exponential decay toward zero in the autocorrelation function (ACF). and on the basis of the ADF test, we did
not find evidence of a unit root at the 1% significance level. Furthermore, sales volume did not present any
indication of seasonality, which reinforces the trend in this variable over time reported in Figure 1. Following
the same arguments, we also assumed that proposals, marketing and BNDES loan volume have no unit root. We
only applied the natural logarithm transformation (log) to these variables to stabilize their variance.
The correlograms of the other five variables (reference rate, confidence index, stock market, exchange
rate and FDI) exhibit a slow decay in the ACF and a value close to 1 for the first lag partial autocorrelation
function (PACF) coefficient. In addition, the ADF tests provided evidence of a unit root, even at the 10%
significance level. Therefore, we applied the log first difference to these variables before we estimated the
models. The log first difference becomes equal to the difference between the log of the variable at times t and t-
1 for t=2,…,T.
6. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 47
III. Model estimation
3.1 Modeling endogeneity
Sales forecasting in manufacturing firms involves several decision-making processes that require accurate
modeling to select the proper actions in the areas of production and sales planning. Prior studies have devoted
particular attention to how forecasting can be improved through carefully examination of management
judgmental adjustment [12]. decision support systems [18] and process to develop forecasting systems [16]. The
majority of past studies have failed to consider that managers make decisions not randomly but based on their
expectations of how their choices will affect future sales [19]. Therefore, management’s decisions are predicated
on the notion that these decisions are endogenous to the sales performance outcome that they expect.
[20] placed the endogeneity as a threat to the validity of the results achieved in marketing research and
they discussed the statistical solutions to this problem. Endogeneity has also implications for the statistical
analysis of sales forecasting. Failing to account for endogeneity in the estimation may cause biased coefficient
estimates [21]. [22] showed that estimations that do not address endogeneity produce parameter estimates that
are likely to be biased and may therefore yield erroneous results and incorrect conclusions regarding the veracity
of theory. This bias results from omitted variables that affect both the influencing factors and sales outcomes.
Estimating unbiased coefficients in the presence of such problems requires statistical approaches that account
for the omitted variables. Previous studies have used vector autoregressive models (VAR) and vector error
correction models (VECM) to account for endogeneity in time-series data [23]. This type of cointegration
analysis addresses the problem of spurious regressions among nonstationary time series. VECM elucidate
potential interrelationships among variables over time, while reducing the risk of endogeneity bias. Other
studies have employed discrete-choice econometric modeling approaches and their corresponding outcome
variables to address endogeneity [24]. [25] suggested incorporating the possibility of self-selection to address
the extent to which an individual’s professional choices are influenced by and influence his or her income.
Transfer functions have long been used to forecast time series concerning economic and monetary
issues [26]. To account for endogeneity, econometricians have applied two-stage least squares (2SLS) to
estimate parameters in systems of linear, simultaneous equations and address endogenous variable bias in
single-equation estimation (e.g., [27]). [28] provided one of the first thorough elaborations of 2SLS estimation,
which is now included in every econometrics textbook (e.g., [21]). The model specification requires one or more
instrumental variables (IVs) that affect the influencing factor and do not directly affect sales performance. For
many cross-sectional data sets, finding IVs that affect the influencing factors but not performance is difficult
[29]. In some cases, one might seek out variables associated with government investment policies that differ
across regions and that might affect the decision, for instance, regarding the number of project proposals. Time
series data on management decisions allow us to identify the instruments of interest under less subjective
assumptions than cross-sectional data. IVs are required to address the simultaneous causality among variables,
and the inferences made using these models are straightforward [30]. Therefore, a 2SLSTF model would
provide a more accurate estimation of time series that contain endogenous variables.
1.2 Forecasting models
We estimate and compare the results of three classes of time-series models: ARMA, transfer function (TF) and
both classic and Bayesian VAR. We applied a log first difference transformation to the variables presenting
evidence of a unit root, as described in the previous section. The ARMA model is typically used as benchmark
to forecast sales volume and is the model that firm managers use when they are analyzing time-series data. In an
univariate ARMA(p,q) model, yt is assumed to be well described by the following equation:
t=1,…,T,
where , is the sample average of y
and is a white noise process with variance , i.e., Here, L denotes the lag operator, i.e., Lj
yt = yt-j. The roots of are assumed to be outside the unit circle. The ARMA model was estimated by
ordinary least squares (OLS) with no backcasting and White heteroskedasticity-consistent standard errors. The
estimation was followed by a variety of diagnostic tests to ensure the adequacy of the estimated model.
The second estimated model is the TF model, which describes the relationship between an output
variable (e.g., sales volume) and one or more explanatory variables. Suppose that yt and xt are second-order
stationary processes, t = 1, …, T; then, the bivariate TF model can be written as:
,
ˆ t
y
t L
y
L
p
pL
L
L
1
1 q
qL
L
L
1
1 y
̂
2
.
,
0
~
2
.
.
n
w
t
z
7. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 48
where b is a nonnegative integer called the transfer function time delay, (L) and (L) are polynomials
in L of degree r and s, respectively, , nt is an ARMA(p, q) process with (L) and L) defined as before
with degree p and q, respectively, and If all roots of the polynomial (L) lie outside the unit circle,
then the transfer function can also be expressed in a linear form v(B). The other explanatory variables are added
to the model with different functions and and a different time delay b.
The transfer function parameters are typically estimated by OLS with the delay parameter b fixed when
the noise component nt is uncorrelated with the explanatory variables xt,. In our data, the explanatory variables,
proposals and marketing, are endogenous because they are simultaneously determined by the output variable,
sales volume, and hence, the OLS estimators are biased and inconsistent. To address this issue, the model was
estimated by 2SLS.
To obtain consistent estimators for the TF model, we included an IV. The IV is an observed variable
that satisfies two assumptions: it is uncorrelated with the error term but is correlated with the endogenous
explanatory variable. The past values of time-series variables are selected as the IVs when stationary time series
are analyzed. For example, proposals at time t are an endogenous explanatory variable in the sales volume
equation at time t, and hence, we can use proposals at time t-1 as an instrument for proposals at time t.
Finally, the VAR model assumes that the group of endogenous variables (sales volume, proposals and
marketing) composes a vector called z. Then, the VAR(p) model with one exogenous variable x can be written
as:
where i are (3x3) coefficient matrices, is a (3x1) coefficient vector that measures the impact of x on
z and t is a trivariate white noise process with covariance matrix . The other exogenous
variables are added to the model with different coefficients and a different time delay b. Parameter estimation
was performed by OLS, and the best VAR model was selected through consideration of the values of Akaike´s
(AIC) and Schwarz´s (BIC) criteria. In our data, we estimated VARs of orders from 1 to 8 to account for short-
and long-run business cycle effects. As the firm variables and economic variables are not cointegrated, the
analysis was performed using the log transformations of stationary variables (sales volume, proposals,
marketing and BNDES loans) and log first differences transformations of the other variables that have a unit
root.
The BVAR model has the same form as the VAR model but differs with respect to the nature of the
prior uncertainty assumed regarding the model’s parameters—the prior density. We used the so-called natural
conjugate (Normal-Wishart) family of prior densities and simulated draws of the relevant random variables
through the use of the Monte Carlo methods presented in [31] and [32]. We selected the following values for the
priori tightness: 0.1 for the overall prior, AR(1). intercept, sum of coefficient prior weight and drift prior and
0.07 for exogenous tightness. Other values were used, and the results were robust. We used the same procedure
employed for the VAR model to select the best BVAR model.
IV. Forecasting accuracy
The model estimation used the 96 observations in the time window from January 2004 to December 2011. We
used 4 additional observations from the year 2012 (Jan-Apr) to assess the out of sample forecasts. The sizes of
our in and out of sample estimations were defined to guarantee the robust estimation of the models with 7
exogenous explanatory variables and two endogenous explanatory variables. We then compared the accuracy of
the forecasts of the in-sample model using the in-sample observations and the out of sample observations.
The sample period includes the economic crisis that became evident months after the Lehman Brothers’
bankruptcy in 2007. We then selected 21 months from November 2008 to July 2010 to analyze forecasting
performance during the crisis period. Forecast errors may be higher during this period than during non-crisis
periods. The volatility of sales volume increases during the crisis (see Figure 1). and hence, we expect to find an
increase in forecasting errors during such a period. We used the correction procedure, described by [21] to
obtain sales volume consistent estimators, as sales volume is log transformed and can under- or overestimate the
t
x
t
t
x
t
b
y
t
t
x
t
r
r
b
s
s
y
t
L
L
x
L
v
L
L
x
L
L
L
y
n
x
L
L
L
L
L
L
L
y
ˆ
ˆ
ˆ
ˆ
)
1
(
)
(
ˆ 2
2
1
2
2
1
0
0
0
.
,
0
~
2
.
.
n
w
t
,
ˆ
ˆ
ˆ
ˆ
2
2
1
t
x
t
b
t
t
x
t
b
t
p
p
μ
x
L
L
μ
x
L
L
L
L
ε
β
μ
z
Φ
ε
β
μ
z
Φ
Φ
Φ
I
z
z
'
t
t
E ε
ε
Σ
8. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 49
expected value of sales owing to the exponentiated predicted values. We also considered the log returns of the
following variables: reference rate, confidence index, stock market, exchange rate and FDI as well as the log of
total BNDES loan volume. The log returns were used to obtain stationarity in the variables and to linearize the
relations [2]. To simplify the explanation of the estimated models, the endogenous variables are defined as:
ARMA model was estimated using the method proposed by Box and Jenkins, in which the ACF and
PACF are used to identify the number of lags to be applied in the model. We estimated an ARMA(2,7) model,
which only includes the parameter for MA with 7 lags, that is:
.
The ARMA(2,7) model was able to capture the autocorrelation structure of sales values, as the
residuals were white noise.
Prior to estimating the TF, VAR and BVAR models, we analyzed the cross-correlograms of sales in
relation to each exogenous variable. We used this procedure to select the number of lags for each variable. Each
exogenous variable enters the model with only one lag, typically the larger cross-correlogram lag. We used the
same dependent variable and lags for the exogenous variables in all 3 models to compare the forecast accuracy
of the models. The lags that were used for the 7 exogenous variables are as follows: lag 6 for reference rate, lag
5 for confidence index, lag 1 for stock market, lag 2 for exchange rate, lag 3 for FDI, lag 1 for BNDES loan
volume and lag 3 for PRI (a dummy variable for the BNDES loan program with reduced interest rates). The
fitted model was:
In the TF model, the endogenous variables, proposals and marketing, needed to be included in the
model with no lags. The 2SLSTF model was then selected to ensure the absence of bias and the consistency of
the coefficient estimators. The residuals and squared residuals were checked, and the model showed adequate
fit.
The VAR model used the same lags that were used for the TF model for the exogenous variables:
, where .
The BVAR model has the same form as the VAR model but with prior uncertainty assumed regarding
the model’s parameters. The best VAR and BVAR models were selected through consideration of the values of
AIC and BIC, and in both cases, we selected the models with p equal to 1, i.e., the VAR(1) and BVAR(1)
models. ACF and PACF are used as tools to assess models’ suitability. The one-step-ahead forecasts results
were evaluated according to three criteria used to compare forecasts: the RMSE, the MAE and the Absolute
Percentage Error (MAPE) [33]. These measures are computed as follows:
, and ,
where are true sales volume and the one-step-ahead forecasting at time t and n is the number of
forecasts. Assuming that the model holds during the post-sample period, we are particularly interested in the
RMSE because this measure should reflect the forecasted standard deviations of the estimated model.
Table 3 presents the RMSE, MAE and MAPE of all the estimated models for the data set for the in
sample (n=96) and out of sample periods (n=4). Table 3 shows the ARMA model’s relative percentage RMSE
to verify the forecast improvement of each model relative to the ARMA model (benchmark). The TF model has
lower values for the three estimated forecasting errors and, hence, shows superior accuracy compared with all
the other estimated models for the in and out of sample analysis. The 2SLSTF model outperforms all other
models in the different samples of the time series. This result shows that accounting for endogeneity improves
forecasting predictions. The 2SLSTF model increases the forecasting accuracy by 29% compared with the
ARMA baseline model using out of sample data. Analyzing the in sample predictions reveals a 11% increase in
accuracy. The 2SLSTF model also performs better in the out of sample compared with VAR and BVAR models
with a reduction of up to 38% in the forecasting error compared with these models.
.
ˆ
)
Marketing
(
Log
,
ˆ
)
Proposals
(
Log
,
ˆ
)
Sales
(
Log
in g )
Lo g (Mark et
3
als)
Lo g (Pro p o s
2
Lo g (Sales)
1
t
t
t
t
t
t
y
y
y
t
t L
y
L
L
7
7
2
2
1 1
1
.
1
1
2
2
1
7
7
7
1
3
03
2
02
1 t
j
jt
j
t
t
t
L
L
L
x
L
v
y
v
y
v
y
t
j
j t
b
j
t
p
p x
L
L
L
L j
ε
β
z
Φ
Φ
Φ
I
7
1
2
2
1
t
t
t
t
y
y
y
3
2
1
z
n
y
y
RMSE
n
t
t
t
1
2
ˆ
n
t
t
t y
y
n
MAE
1
ˆ
1
n
t t
t
t
y
y
y
n
MAPE
1
ˆ
1
t
t y
and
y ˆ
9. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 50
Table 3. RMSE, MAE and MAPE and a Comparison of the Forecasts Between the Estimated Models and the
ARMA Model, Separated by Total in Sample, out of Crisis in Sample, in Crisis in Sample and out of Sample
Periods
RMSE ARMA TF-OLS TF-2SLS VAR1 BVAR1
in sample
total 7977 7326 7079 7578 10008
out crisis 7750 7595 7555 7847 10697
in crisis 8722 6409 5278 6619 7390
out sample total 3740 2848 2649 3593 3669
MAE
in sample
total 6197 5346 5081 5424 7427
out crisis 5930 5791 5647 5762 7955
in crisis 7128 3946 3272 4311 5745
out sample total 2697 2712 2374 3259 2642
MAPE
in sample
total 42,51 27,91 26,29 28,38 36,69
out crisis 31,66 26,17 25,99 28,02 33,54
in crisis 80,21 33,37 27,23 29,58 46,74
out sample total 31,03 28,71 23,56 35,91 24,25
ARMA Relative % RMSE
in sample
total 8 11 5 -25
out crisis 2 3 -1 -38
in crisis 27 39 24 15
out sample total 24 29 4 2
Note: The outperformed result for each line is shown in bold. ARMA Relative % RMSE = [1-(MODEL RMSE /
ARMA RMSE)]*100. Out of sample reports n=4.
The multivariate models presented better forecasting performance when compared with the ARMA
model, which was expected since such models take into account information from other variables in addition to
the past sales. The MAPE results for the VAR model are similar to those for the 2SLSTF model for the
forecasts within the sample; however, for the out of sample forecasts, the results for the 2SLSTF model are 31%
more accurate than those for the VAR model. The BVAR model did not work as expected; we suspect that the
choice of another prior could improve the model forecasts. To further test the accuracy of the 2SLSTF model,
we also estimated all models for different out-of-sample sizes (n=8 and n=12). The 2SLSTF model consistently
outperforms across all different out-of-sample sizes.
The analysis of the sample that includes the crisis period indicates that all models performed poorly
with respect to the error measures compared with the analysis of other samples. This result demonstrates the
difficulty of forecasting during the crisis period. In addition, the models that included economic exogenous
variables, such as TF, VAR and BVAR, performed better than the baseline model. This result shows that
including exogenous variables improves industrial sales forecasts during crisis periods. The 2SLSTF model has
39% greater accuracy than the ARMA model and is superior to the other estimated models.
10. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 51
Sales volatility increases during the crisis, from November 2008 to July 2010, with the highest levels
observed in May and June 2009. This increase may affect the forecasts, increasing the forecast errors of the
ARMA model. To analyze this further, we computed the linear correlation coefficient between volatility and the
ARMA model’s MAPE. The coefficient was equal to 0.39, indicating that moderate correlation exists between
the two estimates and that the forecasts are less accurate during high volatility periods. We also computed the
correlation between volatility and the 2SLSTF model’s MAPE and obtained a coefficient of 0.09. Thus, the use
of exogenous variables improves forecasts during crisis periods, suggesting that economic variables are the first
variables that are affected during such periods.
V. Conclusions
Properly accounting for endogeneity has become a standard component of models in the economic literature.
The application of established VAR and BVAR models is associated with problems related to misestimated
coefficients and increased forecasting errors. Addressing these problems is particularly challenging in the
context of industrial products, as a firm’s management tends to directly influence several relevant variables. We
expect that the simultaneous causal relationships among such variables affect forecast estimates. Therefore,
accounting for endogenous and exogenous variables in forecast estimations and considering the appropriate
model specification would increase the predictive accuracy of forecast models.
In this paper, we applied a two-stage least squares procedure to a transfer function following the
econometric literature (e.g., [21]). Data from the records of an industrial product firm and public sources were
used to test the accuracy of five forecasting models. We selected the variables and lags for each model through
the use of correlograms and the ADF unit root test. To our knowledge, our paper is the first attempt in the
empirical industrial context to address the problem of endogeneity. Our results reveal that the 2SLSTF model
outperformed all other models estimated for industrial sales performance accounting for two endogenous
independent variables: marketing and proposals. In the out of sample analysis, the 2SLSTF model was 38%
more accurate, as assessed by the RMSE, than the baseline benchmark model (ARMA).
We also analyzed the models based on data from the 2008 global financial crisis, as previous research
has called for additional investigation [17]. External events of such magnitude create severe problems for
businesses’ sales and influence forecasting models [5]. In analyzing a subsample from the postcrisis period, we
found that the 2SLSTF model more accurately predicted sales. Compared with the baseline model, the 2SLSTF
model was 39% more accurate. This result reinforces the importance of accounting for endogeneity in
forecasting industrial product sales. Regardless of the type of firm data considered, our results suggest that
accounting for the endogeneity of management variables is important whenever activity in the industrial product
business is modeled.
REFERENCES
[1] Waddell, D. and Sohal, A. S., Forecasting: The Key to Managerial Decision Making, Management
Decision, 321, 1994, 41-49.
[2] Touzani, S. and Van Buskirk, R., Estimating sales and sales market share from sales rank data for
consumer appliances. Physica A, 451, 2016, 266–276.
[3] Kerkkänen, A., Korpela, J. and Huiskonnen, J., Demand Forecasting Errors in Industrial Context:
Measurement and Impacts, International Journal of Production Economics, 118, 2009 43-48.
[4] Trapero, J. R., Pedregal, D. J., Fildes R. and Kourentzes, N., Analysis of Judgmental Adjustments in
the Presence of Promotions, International Journal of Forecasting, 29, 2013, 234–243.
[5] Qian, L. and Soopramanien, D., Using diffusion models to forecast market size in emerging markets
with applications to the Chinese car market, Journal of Business Research, 676, 2014, 1226–1232.
[6] Ilmakunnas, P., Use of Macroeconomic Forecasts in Corporate Forecasting: a Note on Aggregation
Problems, International Journal of Forecasting, 12, 1996, 383-388.
[7] Rippe, R., Wilkinson, M. and Morrison, D., Industrial Market Forecasting with Anticipations Data,
Management Science, 22, 1976, 639-651.
[8] Lackman, C., Forecasting Sales for a B2B Product Category: Case of Auto Component Product,
Journal of Business and Industrial Marketing, 224, 2007, 228-235.
[9] Reynolds, P. L. and Lancaster, G., Predictive strategic marketing management decisions in small firms:
A possible Bayesian solution, Management Decision, 456, 2007, 1038-1057.
[10] Herbig, P., Milewicz, J. and Golden, J., The Do’s and Don’ts of Sales Forecasting, Industrial
Marketing Management, 22, 1993, 49-57.
[11] Byrne, T. M., Moon, M. and Mentzer, J., Motivating the industrial sales force in the sales forecasting
process, Industrial Marketing Management, 40, 2011, 128-138.
11. Forecasting accuracy of industrial sales with endogeneity in firm-level data
International Journal of Business Marketing and Management (IJBMM) Page 52
[12] Franses, P. H. and Legerstee, R., Do Statistical Forecasting Models for SKU-level Data Benefit from
Including Past Expert Knowledge?, International Journal of Forecasting, 29, 2013, 80–87.
[13] Kahn, K. B. and Mentzer, J. T., Forecasting in Consumer and Industrial Markets, Journal of Business
Forecasting, 142, 1995, 21-28.
[14] Rothe, J. T., Effectiveness of Sales Forecasting Methods, Industrial Marketing Management, 7, 1978,
114-118.
[15] Walker, K. B. and Mcclelland, L., Management Forecasts and Statistical Prediction Model Forecasts in
Corporate Budgeting, Journal of Accounting Research, 292, 1991, 371-381.
[16] Danese, P. and Kalchschmidt, M., The role of the forecasting process in improving forecast accuracy
and operational performance, International Journal of Production Economics, 131, 2011, 204–214.
[17] Anderson, H.M. and Vahid, F., Forecasting the Volatility of Australian Stock Returns, Journal of
Business & Economic Statistics, 251, 2007, 76-90.
[18] Wright, D. J., Capon, G., Page, R., Quiroga, J., Taseen, A. A. and Tomasini, F., Evaluation of
Forecasting Methods for Decision Support, International Journal of Forecasting, 2, 1986, 139–153.
[19] Barton, H. H. and Nickerson, J. A., Correcting for Endogeneity in Strategic Management Research,
Strategic Organization, 11, 2003, 51-78.
[20] Jean, R-J. B., Deng, Z., Kim, D. and Yuan, X., Assessing endogeneity issues in international marketing
research, International Marketing Review, 333, 2016, 483-512.
[21] Wooldridge, J., Introductory Econometrics: a Modern Approach (South Western: Mason, 2009).
[22] Shaver, J. M., Accounting for Endogeneity When Assessing Strategy Performance: Does Entry Mode
Choice Affect FDI Survival?, Management Science, 444, 1998, 571-585.
[23] Bonhama. C., Gangnesa, B. and Zhoub. T., Modeling tourism: A fully identified VECM approach,
International Journal of Forecasting, 25, 2009, 531–549.
[24] Heckman, J. J. and Robb Jr., R., Alternative Methods for Evaluating the Impact of Interventions: An
Overview, Journal of Econometrics, 30, 1985, 239-267.
[25] Heckman, J. J., Sample Selection Bias as a Specification Error, Econometrica, 47, 1979, 153-161.
[26] Stokes, H. H. and Neuburger, H., The Effect of Monetary Changes on Interest Rates: a Box-Jenkins
Approach, Review of Economics & Statistics, 614, 1979, 534.
[27] Angrist, J. D. and Imbens, G. W., Two-Stage Least Squares Estimation of Average Causal Effects in
Models with Variable Treatment Intensity, Journal of the American Statistical Association, 90430,
1995, 431-442.
[28] Theil, H., Economic Forecasts and Policy (North-Holland Publishing Co, Amsterdam, 1958)
[29] White, H., Instrumental Variables Estimation with Independent Observations, Econometrica, 50, 1982,
482-499.
[30] Holland, P., Statistics and Causal Inference, Journal of the American Statistical Association, 81, 1986,
945-970.
[31] Sims, C. A. and Zha, T. A., Bayesian Methods for Dynamic Multivariate Models, International
Economic Review, 394, 1998, 949–968.
[32] Waggoner, D. and Zha T. A., Conditional Forecasts in Dynamic Multivariate Models, working paper
98-22, Federal Reserve Bank of Atlanta, Atlanta, December, 1998.
[33] Diebold, F. X. and Mariano, R. S., Comparing Predictive Accuracy, Journal of Business & Economic
Statistics, 13, 1995, 253–263.