Marketing Research

4,283 views
4,079 views

Published on

Presentation made for a lecture that I gave at ITM Mumbai. Marketing Research was an elective subject for the students and this is an overview of the subject

Published in: Business
0 Comments
2 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total views
4,283
On SlideShare
0
From Embeds
0
Number of Embeds
159
Actions
Shares
0
Downloads
320
Comments
0
Likes
2
Embeds 0
No embeds

No notes for slide

Marketing Research

  1. 1. NANDA KISHORE SETHURAMAN FOR ITM EXECUTIVE MBA OCTOBER-2011 Marketing Research
  2. 2. 1 Role & Scope of Marketing Research
  3. 3. Business Intelligence <ul><li>BI is the ability to access data from multiple sources within and outside an organization for the purpose of analysis. </li></ul><ul><li>It links the disparate operation systems to the end users of the data, thus creating an environment with free flow of information. </li></ul><ul><li>It offers a reliable barometer of the business performance. </li></ul>
  4. 4. BUSINESS INTELLIGENCE Operations Intelligence Finance and Accounting Intelligence Marketing Intelligence HR Intelligence Back-End Analysis
  5. 5. Need for Marketing Intelligence <ul><li>MI focuses on the use of information as a source of strategic advantage. </li></ul><ul><li>Need to have a thorough knowledge of customers, their attitudes, tastes and preferences. </li></ul><ul><li>Need to analyze competition for benchmarking and making price, product, market and segment decisions. </li></ul>
  6. 6. Marketing Information System <ul><li>A continuing and interacting structure of people, equipment and procedures designed to gather, sort, analyze, evaluate, and distribute pertinent, timely and accurate information to marketing decision making </li></ul><ul><li>MIS Uses 3 Types of Information </li></ul><ul><ul><li>Recurring market and accounting data from market analysis and accounting activities </li></ul></ul><ul><ul><li>Intelligence relevant to future strategy of business </li></ul></ul><ul><ul><li>Marketing research studies not of a recurring nature </li></ul></ul>
  7. 7. Role of Marketing Research in Decision Making <ul><li>Four Stages of Market Planning Process </li></ul><ul><ul><li>Situation analysis </li></ul></ul><ul><ul><li>Strategy development </li></ul></ul><ul><ul><li>Marketing program development </li></ul></ul><ul><ul><li>Implementation </li></ul></ul>
  8. 8. Situation Analysis <ul><li>Analysis of </li></ul><ul><ul><li>Market environment </li></ul></ul><ul><ul><li>Market characteristics </li></ul></ul><ul><ul><li>Consumer behavior </li></ul></ul><ul><li>Research Approaches </li></ul><ul><ul><li>Organize information obtained from prior studies (secondary) </li></ul></ul><ul><ul><li>Focus groups </li></ul></ul>
  9. 9. Strategy Development <ul><li>Market Research provides information to assist management with three critical decisions </li></ul><ul><ul><li>What business should we be in? </li></ul></ul><ul><ul><li>How will we compete? </li></ul></ul><ul><ul><li>What are the objectives for the business? </li></ul></ul>
  10. 10. Marketing Program Development <ul><li>Programs embrace specific tasks </li></ul><ul><li>Action program usually focuses on a single objective in support of one element of overall business strategy </li></ul>
  11. 11. Implementation <ul><li>Starts with decision to proceed to a new program or strategy </li></ul><ul><li>Commitment to objectives, budgets and timetables </li></ul><ul><li>Specific measurable objectives must be set for all elements of marketing program </li></ul><ul><li>&quot;Did the elements achieve their objectives?&quot; </li></ul><ul><li>“ Should the marketing program be continued, discontinued, revised or expanded?&quot; </li></ul>
  12. 12. Factors Influencing Marketing Research Decisions <ul><li>Relevance </li></ul><ul><li>Type and Nature of Information Sought </li></ul><ul><li>Timing </li></ul><ul><li>Availability of Resources </li></ul><ul><li>Cost-benefit Analysis </li></ul>
  13. 13. Understand the environment and the market Identify threats and opportunities Assess the competitive position Define the business scope and served market segments Establish competitive advantages Set performance objectives. Product and channel decision Communication decisions Pricing Personal selling decisions Performance monitoring Refining strategies and program Situation Analysis Strategy Development Marketing Program Development Implementation
  14. 14. Conquering Latino Homes <ul><li>Hispanics account for nearly 13% of the U.S. population. </li></ul><ul><li>Research shows that Latino households spend $600 billion of $1.3 trillion purchasing power of multicultural population. </li></ul><ul><li>In 1998 only 2.5% of total advertising dollars in the United States was focused on Latinos. </li></ul><ul><li>By 2050, Hispanic population would represent 25% of US population. </li></ul><ul><li>Who can tell me what the problem is ? </li></ul>
  15. 15. Marketing Research in Practice <ul><li>Programmatic Research </li></ul><ul><ul><ul><li>Develops market options through market segmentation, market opportunity analysis, or consumer attitude and product usage studies </li></ul></ul></ul><ul><li>Selective Research </li></ul><ul><ul><ul><li>Tests different decision alternatives such as new product testing, advertising copy testing, pre-test marketing, and test marketing </li></ul></ul></ul><ul><li>Evaluative Research </li></ul><ul><ul><ul><li>Evaluation of performance of programs </li></ul></ul></ul>
  16. 16. Decision Support Systems (DSS) <ul><li>DSS models are developed and adapted to support each firms own decision problems </li></ul><ul><li>Used to retrieve data, transform it into usable information, and disseminate it to users </li></ul><ul><li>Allow managers to interact directly with database </li></ul><ul><li>To retrieve information </li></ul><ul><li>Provides a modeling function to help interpret information retrieved </li></ul>
  17. 17. Marketing Decision Support System <ul><li>Combines marketing data from diverse sources into a single database, enabling product managers, sales planners, market researchers, financial analysts, and production schedulers to share information. </li></ul>
  18. 18. Marketing Decision Support Systems <ul><li>Managers’ needs for decision relevant information: </li></ul><ul><li>Routine comparisons of current performance against past trends on each of the key measures of effectiveness </li></ul><ul><li>Periodic exception reports to assess which sales territories or accounts have not matched previous years’ purchases </li></ul><ul><li>Special analyses to evaluate the sales impact of particular marketing programs, and to predict what would happen if changes were made. </li></ul>
  19. 19. Marketing Decision Support Systems Contd.. <ul><li>Characteristics of MDSS: </li></ul><ul><li>Interactive </li></ul><ul><li>Flexible </li></ul><ul><li>Discovery oriented </li></ul><ul><li>User friendly </li></ul>
  20. 20. Marketing Decision Support Systems <ul><li>Four components of MDSS: </li></ul><ul><li>Database </li></ul><ul><li>Reports and Displays </li></ul><ul><li>Analysis capabilities </li></ul><ul><li>Models </li></ul>
  21. 21. Gaining Insight from a MDSS Manager Modeling Analysis Display Database Environment
  22. 22. Participants in marketing research activities Information Users Information Suppliers: Inside Company Information Suppliers: Outside Company <ul><li>General management </li></ul><ul><li>Planning </li></ul><ul><li>Marketing and sales managers </li></ul><ul><li>Product managers </li></ul><ul><li>Lawyers </li></ul><ul><li>Marketing research department </li></ul><ul><li>Sales analysis group </li></ul><ul><li>Accounting department </li></ul><ul><li>Corporate strategic planning </li></ul><ul><li>Research consultants </li></ul><ul><li>Marketing research suppliers </li></ul><ul><li>Advertising agencies </li></ul>
  23. 23. 2 Marketing Research process & problem definition.
  24. 24. Marketing Research Process <ul><li>MR Process Evolves From Answers to Five Key Questions </li></ul><ul><ul><ul><li>Why should we do research? </li></ul></ul></ul><ul><ul><ul><li>What research should be done? </li></ul></ul></ul><ul><ul><ul><li>Is it worth doing the research? </li></ul></ul></ul><ul><ul><ul><li>How should the research be designed to achieve the research objectives? </li></ul></ul></ul><ul><ul><ul><li>What will we do with the research? </li></ul></ul></ul>
  25. 25. MARKETING PLANNING AND INFORMATION SYSTEM <ul><li>Planning system </li></ul><ul><ul><ul><li>Strategic plans </li></ul></ul></ul><ul><ul><ul><li>Tactical plans </li></ul></ul></ul><ul><li>Information system </li></ul><ul><ul><ul><li>Databases </li></ul></ul></ul><ul><ul><ul><li>DSS </li></ul></ul></ul>1. AGREE ON RESEARCH PROCESS <ul><ul><ul><li>Problems or opportunities </li></ul></ul></ul><ul><ul><ul><li>Decision alternatives </li></ul></ul></ul><ul><ul><ul><li>Research users </li></ul></ul></ul>
  26. 26. 2 . ESTABLISH RESEARCH OBJECTIVES <ul><ul><ul><li>Problems or opportunities </li></ul></ul></ul><ul><ul><ul><li>Decision alternatives </li></ul></ul></ul><ul><ul><ul><li>Research users </li></ul></ul></ul>Estimate the value of information Is benefit > cost Do not conduct marketing research NO Yes
  27. 27. 2. ESTABLISH RESEARCH OBJECTIVES <ul><ul><ul><li>Problems or opportunities </li></ul></ul></ul><ul><ul><ul><li>Decision alternatives </li></ul></ul></ul><ul><ul><ul><li>Research users </li></ul></ul></ul>5. COLLECT THE DATA <ul><li>REPORT THE RESEARCH RESULTS AND PROVIDE STRATEGIC RECOMMENDATIONS </li></ul>6. PREPARE AND ANALYZE THE DATA Yes
  28. 28. The International Marketing Research Process <ul><li>Marketing research process is consistent for both domestic and international markets </li></ul><ul><li>Variety of market environments affect international marketing research process </li></ul>
  29. 29. Major Environmental Forces Influencing International Marketing Research Process <ul><li>Economic Environment </li></ul><ul><li>Social-cultural Environment </li></ul><ul><li>Political and Legal Environment </li></ul><ul><li>Technological, Multimedia and Infrastructural Facilities </li></ul>
  30. 30. The Marketing Research Process <ul><li>Step 1 </li></ul><ul><li>Research Purpose </li></ul><ul><ul><li>Problem or opportunity analysis </li></ul></ul><ul><ul><ul><li>Which problems or opportunities are anticipated </li></ul></ul></ul><ul><ul><ul><li>What is the scope of the problems and the possible reasons? </li></ul></ul></ul><ul><ul><li>Evaluation of decision alternatives </li></ul></ul><ul><ul><ul><li>What are the alternatives being studied? </li></ul></ul></ul><ul><ul><ul><li>What are the criteria for choosing among the alternatives? </li></ul></ul></ul><ul><ul><li>Research users </li></ul></ul><ul><ul><ul><li>Who are the decision makers? </li></ul></ul></ul><ul><ul><ul><li>Are there any covert purposes ? </li></ul></ul></ul>
  31. 31. Kroger Opens Signature Store <ul><li>Kroger Co. is adding five new Signature stores in Houston. More than 1,000 questionnaires were sent to targeted area residents asking what kind of features the respondents (or future customers) would like to see included in a new supermarket in their neighborhood. Based on the surveys, Kroger added several variations: </li></ul><ul><ul><li>A larger selection of wines </li></ul></ul><ul><ul><li>A sit-down coffee bar </li></ul></ul><ul><ul><li>The largest all-natural food section </li></ul></ul><ul><ul><li>U-Scan Express aisles </li></ul></ul>
  32. 32. The Marketing Research Process (Contd.) <ul><li>Step 2 </li></ul><ul><li>Research Objective </li></ul><ul><ul><li>A statement, in as precise terminology as possible, of what information is needed </li></ul></ul><ul><ul><li>Should be framed to ensure information obtained will satisfy research purpose </li></ul></ul><ul><li>Research Question </li></ul><ul><li>Hypothesis Development </li></ul><ul><li>Research Boundaries </li></ul>
  33. 33. The Marketing Research Process (Contd.) <ul><li>Research Question </li></ul><ul><ul><li>Asks what specific information is required to achieve the research purpose </li></ul></ul><ul><li>Sample questions to determine if a specific advertisement should be run: </li></ul><ul><ul><li>Will the advertisement be noticed? </li></ul></ul><ul><ul><li>Will it be interpreted accurately? </li></ul></ul><ul><ul><li>Will it influence attitudes? </li></ul></ul>
  34. 34. <ul><li>Hypothesis Development </li></ul><ul><ul><li>A possible answer to a research question. </li></ul></ul><ul><li>Generating a hypothesis </li></ul><ul><ul><li>Draw on previous research efforts </li></ul></ul><ul><ul><li>Borrow from other disciplines such as: </li></ul></ul><ul><ul><ul><li>Psychology </li></ul></ul></ul><ul><ul><ul><li>Sociology </li></ul></ul></ul><ul><ul><ul><li>Marketing </li></ul></ul></ul><ul><ul><ul><li>Economics </li></ul></ul></ul><ul><ul><li>Manager’s experience with related problems, coupled with knowledge and the use of judgment </li></ul></ul>The Marketing Research Process (Contd.)
  35. 35. Source <ul><li>Theory </li></ul><ul><li>Management experience </li></ul><ul><li>Exploratory research </li></ul>Research Question Hypothesis Research Purpose Research Design Research Objective
  36. 36. <ul><li>Step 3 </li></ul><ul><li>Estimating the Value of Information </li></ul><ul><ul><li>Value depends on: </li></ul></ul><ul><ul><ul><li>Importance of decision </li></ul></ul></ul><ul><ul><ul><li>Uncertainty that surrounds it </li></ul></ul></ul><ul><ul><ul><li>Influence of research information on the decision </li></ul></ul></ul>The Marketing Research Process (Contd.) Marketing Research 8 th Edition Aaker, Kumar, Day
  37. 37. Product A $ 4 million $ 1 million $ 4 million -$ 2.5 million Success Success Failure Failure Introduce Introduce Introduce Introduce Do not Do not Illustrative Decision Models Product B
  38. 38. The International Marketing Research Process <ul><li>Avoid mistakes : </li></ul><ul><ul><li>Profile you target customers and clients </li></ul></ul><ul><ul><li>Interview target segments to assess how well they match your preconceived ideas </li></ul></ul><ul><ul><li>Hire local researchers </li></ul></ul><ul><ul><li>Use a variety of methods to get a well-rounded picture </li></ul></ul><ul><ul><ul><li>Qualitative methods </li></ul></ul></ul><ul><ul><ul><li>Quantitative methods </li></ul></ul></ul><ul><ul><li>Look at the findings and analyze what must be done differently, abroad or internationally, in comparison with current domestic marketing activities </li></ul></ul>
  39. 39. Framing Research Questions in an International Environment <ul><li>Possible questions: </li></ul><ul><ul><li>Do opportunities exist for entry into foreign markets? </li></ul></ul><ul><ul><li>Which foreign markets warrant detailed investigation? </li></ul></ul><ul><ul><li>What are the major economic, political, legal, and other environmental facts in each potential country? </li></ul></ul><ul><ul><li>What mode of entry does the company plan to adopt? </li></ul></ul><ul><ul><li>What is the market potential in these countries? </li></ul></ul><ul><ul><li>Who are the firm’s present and potential customers? </li></ul></ul><ul><ul><li>What is the nature of competition in the foreign market? </li></ul></ul><ul><ul><li>What kind of strategy should the firm adopt? </li></ul></ul>
  40. 40. 3. Research Designs.
  41. 41. Research Design and Implementation <ul><li>Research Design </li></ul><ul><ul><li>The detailed blueprint to guide the implementation of a research study toward the realization of its objectives </li></ul></ul>
  42. 42. Categories of Research <ul><li>Exploratory Research </li></ul><ul><ul><li>Used when seeking insights into the general nature of a problem, the possible decision alternatives, and the relevant variables that need to be considered </li></ul></ul>
  43. 43. Categories of Research (Contd.) <ul><li>Descriptive Research </li></ul><ul><ul><li>Provides an accurate snapshot of some aspect of the market environment, such as: </li></ul></ul><ul><ul><ul><li>The proportion of the adult population that supports the United Fund </li></ul></ul></ul><ul><ul><ul><li>Consumer evaluation of the attributes of our product versus competing products. </li></ul></ul></ul><ul><ul><ul><li>The socioeconomic and demographic characteristics of the readership of a magazine </li></ul></ul></ul><ul><ul><ul><li>The proportion of all possible outlets that are carrying, displaying, or merchandising our products </li></ul></ul></ul>
  44. 44. Categories of Research (Contd.) <ul><li>Causal Research </li></ul><ul><ul><li>Used when it is necessary to show that one variable causes or determines the values of other variables, a causal research approach must be used </li></ul></ul>
  45. 45. Detective Funnel <ul><li>Uses Combination of All Three Research Techniques </li></ul><ul><ul><li>Exploratory techniques generate all possible reasons for a problem </li></ul></ul><ul><ul><li>Descriptive and Causal approaches narrow the possible causes </li></ul></ul>
  46. 46. Problem Exploratory Research Probable Causes Causal Research Descriptive Research Possible causes of the problem Detective Funnel
  47. 47. Data Collection Methods <ul><li>Relationship between Data Collection Method and </li></ul><ul><li>Category of Research </li></ul><ul><li> Category of Research </li></ul><ul><li>Data Collection Method Exploratory Descriptive Causal </li></ul><ul><li>Secondary Sources </li></ul><ul><li>Information System a b </li></ul><ul><li>Databanks of other a b </li></ul><ul><li>organizations </li></ul><ul><li>Syndicated Services a b b </li></ul><ul><li>Primary Sources </li></ul><ul><li>Qualitative Research a b </li></ul><ul><li>Surveys b a b </li></ul><ul><li>Experiments b a </li></ul>
  48. 48. Research Tactics and Implementation <ul><li>Once the research approach has been chosen: </li></ul><ul><li>Develop: </li></ul><ul><ul><li>The specifics of measurements </li></ul></ul><ul><ul><li>Plan for choosing the sample </li></ul></ul><ul><ul><li>Methods of analysis </li></ul></ul><ul><ul><li>Analysis of value versus cost and time involved </li></ul></ul>
  49. 49. Issues in International Research Design <ul><li>Determining Information Requirements </li></ul><ul><li>Consider level and type of decision for which research is conducted </li></ul><ul><li>Two types of decisions </li></ul><ul><ul><li>Strategic </li></ul></ul><ul><ul><li>Tactical </li></ul></ul>
  50. 50. <ul><li>Global Strategic Decision </li></ul><ul><li>Mostly made at corporate headquarters </li></ul><ul><li>Information required is governed by overall company objectives </li></ul><ul><li>Implies long term survival of company </li></ul><ul><li>Deal with macro environment </li></ul>Issues in International Research Design
  51. 51. <ul><li>Tactical Decisions </li></ul><ul><li>Concerned with micro-level implementation issues </li></ul><ul><li>Information obtained from primary data </li></ul><ul><li>Concerned with marketing mix strategy for country/product markets </li></ul><ul><li>Made at functional or subsidiary level </li></ul>Issues in International Research Design
  52. 52. <ul><li>Unit of Analysis </li></ul><ul><li>Researcher must decide at what level the analysis is done </li></ul><ul><ul><li>Global level </li></ul></ul><ul><ul><ul><li>All countries taken simultaneously </li></ul></ul></ul><ul><ul><li>Regional level </li></ul></ul><ul><ul><ul><li>Groups of countries considered homogeneous for macro environmental factors </li></ul></ul></ul><ul><ul><li>Country level </li></ul></ul><ul><ul><ul><li>Each country taken as separate unit </li></ul></ul></ul>Issues in International Research Design
  53. 53. <ul><li>Construct Equivalence </li></ul><ul><li>Deals with how both the researcher and the subjects see, understand, and code a particular phenomenon </li></ul><ul><li>&quot;Are we studying the same phenomenon in countries X and Y?&quot; </li></ul>Construct, Measurement and Sample Equivalence
  54. 54. <ul><li>Measurement Equivalence </li></ul><ul><li>Deals with the methods and procedures used by the researcher to collect and categorize essential data and information </li></ul><ul><li>Are the phenomenon in countries X and Y measured the same way?&quot; </li></ul>Construct, Measurement and Sample Equivalence
  55. 55. <ul><li>Sampling Equivalence </li></ul><ul><li>&quot;Are the samples used in countries X and Y equivalent?&quot; </li></ul>Construct, Measurement and Sample Equivalence
  56. 56. Errors in Research Design <ul><li>Two Components of Errors </li></ul><ul><ul><li>Sampling error </li></ul></ul><ul><ul><li>Non-sampling error </li></ul></ul><ul><li>Sampling Error </li></ul><ul><ul><li>Difference between a measure obtained from a sample of population and the true measure that can be obtained only from the entire population </li></ul></ul><ul><li>Nonsampling Error </li></ul><ul><ul><li>All other errors associated with a research project </li></ul></ul>
  57. 57. <ul><li>Design Errors </li></ul><ul><li>Flaws in research design </li></ul><ul><li>Selection Error </li></ul><ul><li>Population Specification Error </li></ul><ul><li>Sampling Frame Error </li></ul><ul><li>Surrogate Information Error </li></ul><ul><li>Measurement Error </li></ul><ul><li>Experimental Error </li></ul><ul><li>Data Analysis Error </li></ul>Sources of Nonsampling Error
  58. 58. <ul><li>Administering Errors </li></ul><ul><ul><li>Occur during the administration of a survey instrument to the respondents </li></ul></ul><ul><ul><li>Questioning Error </li></ul></ul><ul><ul><li>Recording Error </li></ul></ul><ul><ul><li>Interference Error </li></ul></ul>Sources of Nonsampling Error (Contd.)
  59. 59. <ul><li>Response Error </li></ul><ul><ul><li>Occur when respondent provides inaccurate answers to survey questions </li></ul></ul><ul><li>Non-response Error </li></ul><ul><ul><li>Occurs if </li></ul></ul><ul><ul><ul><li>Some members of sample not contacted </li></ul></ul></ul><ul><ul><ul><li>Some members provide incomplete or no response to survey instrument </li></ul></ul></ul>Sources of Nonsampling Error (Contd.)
  60. 60. <ul><li>Describes a plan for conducting and controlling a research project </li></ul><ul><li>Basis for a written contract between manager and researcher </li></ul><ul><li>Basis for a vehicle for reviewing important decisions </li></ul><ul><li>Used to choose among competing supplies and influence decision to fund study </li></ul>Research Proposal
  61. 61. <ul><li>Executive Summary </li></ul><ul><li>Purpose and Scope </li></ul><ul><li>Objectives </li></ul><ul><li>Research Approach </li></ul><ul><li>Time and Cost Estimates </li></ul><ul><li>Appendices </li></ul>Basic Contents of a Research Proposal
  62. 62. 4. Methods & Data Collection.
  63. 63. <ul><li>Secondary Data </li></ul><ul><li>Primary Data </li></ul>Data Sources
  64. 64. STANDARDIZED SOURCES OF MARKETING DATA <ul><li>STORE AUDITS </li></ul><ul><li>WAREHOUSE WITHDRAWAL SERVICES </li></ul><ul><li>CONSUMER PURCHASE PANELS </li></ul><ul><li>SINGLE SOURCE DATA </li></ul><ul><li>NIELSEN’S TELEVISION INDEX </li></ul><ul><li>STARCH SCORES </li></ul><ul><li>ARBITRON PANEL </li></ul><ul><li>MULTIMEDIA SERVICES </li></ul><ul><li>SALES/PATRONAGE RESULTS ( OUTCOMES ) </li></ul><ul><li>MARKETING ACTIVITY ( INPUTS ) </li></ul><ul><li>COST INFORMATION </li></ul><ul><li>DISTRIBUTOR REPORTS AND FEEDBACK </li></ul><ul><li>CUSTOMER FEEDBACK </li></ul><ul><li>GOVERNMENT </li></ul><ul><li>TRADE ASSOCIATIONS </li></ul><ul><li>PERIODICALS </li></ul><ul><li>NEWSPAPERS </li></ul><ul><li>BOOKS </li></ul><ul><li>ANNUAL REPORTS </li></ul><ul><li>PRIVATE STUDIES </li></ul>Sources of Secondary Data DATA SOURCES SECONDARY DATA SOURCES PRIMARY DATA SOURCES INTERNAL RECORDS EXTERNAL SOURCES PUBLISHEDDATA INTERNET ELECTRONIC PRINTED
  65. 65. <ul><li>Can solve the problem on hand all by its own </li></ul><ul><li>Can lead to new ideas and other sources </li></ul><ul><li>Helps to define the problem more clearly </li></ul><ul><li>Can help in designing the primary data collections process </li></ul><ul><li>Helps in defining the population / sample </li></ul><ul><li>Can serve as a reference base </li></ul>Uses of Secondary Data
  66. 66. <ul><li>Low cost </li></ul><ul><li>Less effort </li></ul><ul><li>Less time </li></ul><ul><li>At times, more accurate </li></ul><ul><li>At times, only way to obtain data </li></ul><ul><li>Collected for some other purpose </li></ul><ul><li>No control over data collection </li></ul><ul><li>May not be accurate </li></ul><ul><li>May not be in correct form </li></ul><ul><li>May be outdated </li></ul><ul><li>May not meet data requirements </li></ul><ul><li>Assumptions have to be made </li></ul>Benefits and Limitations of Secondary Data Benefits Limitations
  67. 67. <ul><li>Internal Records </li></ul><ul><li>Accounting Data </li></ul><ul><li>Sales Reports </li></ul><ul><li>Inventory Management </li></ul><ul><li>Customer Database </li></ul>Internal Sources of Secondary Data
  68. 68. <ul><li>Published data sources (e.G., Census, publications of various trade associations) </li></ul><ul><li>Trade directories </li></ul><ul><li>Computer retrievable databases (&quot;online&quot; databases) </li></ul>External Sources of Secondary Data
  69. 69. Computer Retrievable Database Based on the Method of Storage and Retrieval of Information Based on the Type of Information Source Reference On-line Databases CD-ROM Databases Floppy Disc Databases Indirect through Networks Direct from Producer Direct from Vendors Internet
  70. 70. <ul><li>Scope of information available </li></ul><ul><li>Speed of information access and retrieval </li></ul><ul><li>Commercially available search procedures provide considerable flexibility and efficiency </li></ul><ul><li>Rely solely on the accuracy of the abstract author </li></ul><ul><li>Depend on the journal and article selection policy of the database producer </li></ul><ul><li>Might miss important information, or retrieve a lot of irrelevant data if searching by “keyword” </li></ul>Computer-Retrievable Methods Limitations Advantages
  71. 71. <ul><li>Factors to Be Considered: </li></ul><ul><li>Who has collected the data (did they have adequate resources)? </li></ul><ul><li>Why was the data collected (how the interests of agency match with ours)? </li></ul><ul><li>How the data was collected (to determine the quality of data on-hand)? </li></ul><ul><li>What data was collected (geographic and demographic limitations)? </li></ul><ul><li>When the data was collected (how old/obsolete is the data)? </li></ul>Appraising Secondary Sources
  72. 72. <ul><li>Monitoring the Environment </li></ul><ul><li>Demand Estimation </li></ul>Applications of Secondary Data
  73. 73. <ul><li>Census data </li></ul><ul><li>Standard Industrial Classification (SIC) or North American Industrial Classification (NAIC) </li></ul><ul><li>Trade association data </li></ul><ul><li>Experts and authorities </li></ul><ul><li>Press releases </li></ul><ul><li>Legislation and laws </li></ul><ul><li>Industry news </li></ul><ul><li>Business and practitioner literature, such as magazines </li></ul>Applications of Secondary Data (Contd.) Demand Estimation Monitoring the Environment
  74. 74. <ul><li>ORG Reports </li></ul><ul><li>CLUSTER PLUS </li></ul><ul><li>Competitor’s annual reports </li></ul><ul><li>Press releases </li></ul>Applications of Secondary Data (Contd.) Segmentation and Targeting Developing a Business Intelligence System
  75. 75. <ul><li>Factors </li></ul><ul><li>Multitude of information users having common information needs </li></ul><ul><li>When cost of satisfying individual user's need is prohibitive </li></ul><ul><li>The increasing use of scanner systems at the check out points </li></ul>Growth of Standardized Sources
  76. 76. <ul><li>Biggest research company in the world </li></ul><ul><li>Their auditing services cover four groups </li></ul><ul><ul><li>Grocery products </li></ul></ul><ul><ul><li>Drugs </li></ul></ul><ul><ul><li>Mass merchandisers </li></ul></ul><ul><ul><li>Alcoholic beverages </li></ul></ul>Nielsen Retail Index
  77. 77. <ul><li>To Cover the gap between Warehouse Withdrawal Audits and Actual Purchases, following Methods can be used </li></ul><ul><li>Home Audit Approach </li></ul><ul><ul><li>Panel member agrees to permit an auditor to check the household stocks of certain product categories at regular intervals </li></ul></ul><ul><li>Mail Diary Method </li></ul><ul><ul><li>Panel member records the details of each purchase and returns in the diary by mail at regular intervals </li></ul></ul>Consumer Purchase Panels
  78. 78. <ul><li>Can Provide Information On: </li></ul><ul><ul><li>Aggregate Sales Activity </li></ul></ul><ul><ul><li>Brand Shares </li></ul></ul><ul><ul><li>Shifts in Buyer Characteristics </li></ul></ul><ul><ul><li>Shifts in Retail Outlets </li></ul></ul>Advantages of Consumer Panels
  79. 79. <ul><li>Possibility of Selection Bias </li></ul><ul><li>Mortality Effect </li></ul><ul><li>Testing Effects </li></ul>Limitations of Consumer Panels
  80. 80. <ul><li>A new technology that may replace the bar codes. Utilizing a tiny silicon chip to store information; a small transmitter would then send this information to a scanner. RFID offers more benefits than a UPC, such as: </li></ul><ul><ul><li>The ability to store more information </li></ul></ul><ul><ul><li>The ability to change the information on the tag </li></ul></ul><ul><ul><li>The ability to transmit all the information on the chip to a scanner without clear line of sight </li></ul></ul>RFID
  81. 81. <ul><li>TAM for TV audiences </li></ul><ul><li>RAM for FM Radio Channels </li></ul><ul><li>INS & IRS for newspapers </li></ul><ul><li>ORG report for FMCG, Consumer Durables etc </li></ul>Media Related Standardized Sources
  82. 82. Measurement Systems SMART PEOPLE METER Mechanics No wire connections Wired directly to TV and VCR tuners Research Methods Data retrieved by reading UTCP codes Telephone connections used to return data Method of Data Collection User logs in/out before and after watching TV User punches numerical code into data-entry device Reputation as: Media measurement business serving the ratio industry Foremost in TV ratings
  83. 83. <ul><li>A typical marketing manager receives some or all of following data: </li></ul><ul><ul><li>Factory shipments or order </li></ul></ul><ul><ul><li>Syndicated aggregate (industry) data services </li></ul></ul><ul><ul><li>Sales reports from sales personnel </li></ul></ul><ul><ul><li>Consumer panel data </li></ul></ul><ul><ul><li>Scanner data </li></ul></ul><ul><ul><li>Demographic data </li></ul></ul><ul><ul><li>Internal cost and budget data </li></ul></ul><ul><li>Purpose of MDSS is to combine marketing data from diverse sources into single database </li></ul>Marketing Decision Support Systems
  84. 84. <ul><li>Measuring product sales and market share </li></ul><ul><li>Measuring advertisement exposure and effectiveness </li></ul><ul><li>Measuring promotion effectiveness </li></ul><ul><li>Estimation And evaluation of models </li></ul>Applications of Standardized Sources of Data
  85. 85. 5 Survey method of data collection. & Methods of Qualitative research.
  86. 86. Marketing Research Data Matrix Qualitative Quantitative Primary Secondary
  87. 87. <ul><li>Qualitative Methods </li></ul><ul><ul><li>Recommended to capture the basic feel of a problem prior to conducting more analytical study </li></ul></ul><ul><li>Observational Methods </li></ul><ul><ul><li>These methods are limited to providing information on current behavior </li></ul></ul>Information Collection : Qualitative and Observational Methods
  88. 88. <ul><li>Exploratory </li></ul><ul><ul><li>Conducted primarily to explicitly define the problem and formulate hypotheses </li></ul></ul><ul><li>Orientation </li></ul><ul><ul><li>To learn more about target consumer (e.G. Culture, language) </li></ul></ul><ul><li>Clinical </li></ul><ul><ul><li>To gain insights into topics that are difficult in a structured research </li></ul></ul>Qualitative Research Methods
  89. 89. <ul><li>Major constraints: </li></ul><ul><ul><li>Volume of data </li></ul></ul><ul><ul><li>Complexity of analysis </li></ul></ul><ul><ul><li>Detail of clarification record </li></ul></ul><ul><ul><li>Time-consuming nature of the clerical efforts required </li></ul></ul><ul><ul><li>Relatively expensive </li></ul></ul>Qualitative Research Methods
  90. 90. <ul><li>Nondirective interviews (respondent enjoys maximum freedom) </li></ul><ul><li>Semi-structured or focused individual interviews </li></ul><ul><ul><li>Covers a specific list of topics or sub-areas </li></ul></ul><ul><li>Individual in-depth interviews (3 techniques): </li></ul><ul><ul><li>Laddering </li></ul></ul><ul><ul><li>Hidden-issue </li></ul></ul><ul><ul><li>Symbolic Analysis </li></ul></ul>Individual In-depth Interviews
  91. 91. <ul><li>Offers participants more stimulation than an interview; makes new ideas and meaningful comments more likely </li></ul><ul><li>Issues to be addressed : </li></ul><ul><ul><li>Outlining the intended direction of the group </li></ul></ul><ul><ul><li>Explaining how participants were recruited </li></ul></ul><ul><ul><li>Reeducating observers on the concepts of random selection, statistical reliability, and projectability of research results </li></ul></ul>Focus Group Discussions
  92. 92. <ul><li>Exploratory Focus Groups </li></ul><ul><ul><li>Used in the exploratory phase of the market research process </li></ul></ul><ul><ul><li>Used for generating the hypotheses </li></ul></ul><ul><li>Clinical Focus Groups </li></ul><ul><ul><li>Based on the premise that an individual's true feelings and motivations are subconscious in nature </li></ul></ul><ul><li>Experiencing Focus Groups </li></ul><ul><ul><li>Allows the researcher to experience the emotional framework in which the product is being used </li></ul></ul>Types of Focus Groups
  93. 93. <ul><li>Casual Observation </li></ul><ul><li>Systematic Observation </li></ul><ul><li>Direct Observation </li></ul><ul><li>Contrived Observation </li></ul><ul><li>Content Analysis </li></ul><ul><li>Physical Trace Measures </li></ul><ul><li>Humanistic Inquiry </li></ul><ul><li>Behavior Recording Devices </li></ul>Observational Methods
  94. 94. <ul><li>Cannot be used to observe motives, attitudes or intentions </li></ul><ul><li>More costly and time consuming </li></ul>Limitations of Observational Methods
  95. 95. <ul><li>Used to Capture a Wide Variety of Information: </li></ul><ul><li>Attitude </li></ul><ul><li>Decisions </li></ul><ul><ul><li>Focus on process and not the results </li></ul></ul><ul><li>Measuring the relationship between actions & needs, desires, preferences, motives and goals </li></ul>Information From Surveys
  96. 96. <ul><li>The Results Will Be Meaningful If: </li></ul><ul><li>Population has been defined correctly </li></ul><ul><li>Sample is representative of the population </li></ul><ul><li>Respondents selected are able and willing to cooperate </li></ul><ul><li>Questions are understood by the respondents </li></ul><ul><li>Respondents have the knowledge, opinions, attitudes, or facts required </li></ul><ul><li>Interviewer correctly understands and records the response </li></ul>Sources of Survey Error
  97. 97. POPULATION RESPONDENT INTERVIEWER Sample Question Answer Sampling error Nonresponse due to refusals or not-at-home Ambiguity of question Interviewer error Ambiguity of answer <ul><li>Inaccuracy in response </li></ul><ul><li>Inability to formulate a response </li></ul><ul><li>Unwillingness to respond </li></ul>Sources of Survey Error
  98. 98. <ul><li>Refusals Could Occur Due to: </li></ul><ul><li>Nature of questions and place </li></ul><ul><li>Subject of no interest to the respondent </li></ul><ul><li>Fear </li></ul><ul><li>Invasion of privacy </li></ul><ul><li>Hostility towards sponsor </li></ul><ul><li>Personal bias </li></ul><ul><li>Characteristics of the data collection procedure (e.G., Presidential polls) </li></ul>Non-response Errors Due to Refusals
  99. 99. <ul><li>Phenotypic Source </li></ul><ul><ul><li>Characteristics of the data collection procedure </li></ul></ul><ul><ul><ul><li>Question asked </li></ul></ul></ul><ul><ul><ul><li>How question is asked </li></ul></ul></ul><ul><ul><ul><li>Length of interview </li></ul></ul></ul><ul><li>Genotypic Source </li></ul><ul><ul><li>Indigenous characteristics of the respondents </li></ul></ul><ul><ul><ul><li>Age </li></ul></ul></ul><ul><ul><ul><li>Sex </li></ul></ul></ul><ul><ul><ul><li>Occupation </li></ul></ul></ul>Non-response Errors Due to Refusals
  100. 100. <ul><li>Inability to respond </li></ul><ul><li>Telescoping </li></ul><ul><li>Averaging </li></ul><ul><li>Omission </li></ul><ul><li>Cannot formulate an adequate answer </li></ul><ul><li>Some of these problems can be solved by: </li></ul><ul><li>Aided-recall techniques </li></ul>Inaccuracy in Response
  101. 101. <ul><li>This Could Arise Due to the Following Reasons : </li></ul><ul><li>Concern about invasion of privacy </li></ul><ul><li>Time pressure and fatigue </li></ul><ul><li>Prestige seeking and social desirability response bias </li></ul><ul><li>Courtesy bias </li></ul><ul><li>Uninformed response bias </li></ul><ul><li>Response style </li></ul>Unwillingness to Respond Accurately
  102. 102. <ul><li>This Depends On: </li></ul><ul><li>Respondent’s Impression of the Interviewer </li></ul><ul><li>Questioning, Probing, and Recording </li></ul><ul><li>Fraud and Deceit </li></ul><ul><li>Improving Interviewer Quality </li></ul>Interviewer Error
  103. 103. <ul><li>Personal Interview </li></ul><ul><li>Telephone Interview </li></ul><ul><li>Mail Survey </li></ul><ul><li>Fax Survey </li></ul><ul><li>E-mail Survey </li></ul><ul><li>Web-based Survey </li></ul>Methods of Data Collection
  104. 104. <ul><li>Sampling </li></ul><ul><li>Type of Population </li></ul><ul><li>Question Form </li></ul><ul><li>Question Content </li></ul><ul><li>Response Rate </li></ul><ul><li>Costs </li></ul><ul><li>Available Facilities </li></ul><ul><li>Length of Data Collection </li></ul>Factors Affecting the Choice of a Survey Method
  105. 105. <ul><li>Misrepresentation of Data Collection Process Stems From: </li></ul><ul><li>Representation of a marketing activity other than research as research </li></ul><ul><li>Abuse of respondents rights during the data collection process, under the rationale of providing better quality research. E.G., </li></ul><ul><ul><ul><li>Use of survey for selling purposes </li></ul></ul></ul><ul><ul><ul><li>Use of survey to obtain names and addresses of prospects for direct marketing </li></ul></ul></ul>Ethical Issues in Data Collection
  106. 106. <ul><li>The rights of the respondents can be violated by: </li></ul><ul><li>Disguising the purpose of a particular measurement </li></ul><ul><li>Deceiving the prospective respondent as to the true duration of the interview </li></ul><ul><li>Misrepresenting the compensation in order to gain cooperation </li></ul>Ethical Issues in Data Collection
  107. 107. <ul><li>The rights of the respondents can be violated by: </li></ul><ul><li>Not mentioning to the respondent that a follow up interview will be made </li></ul><ul><li>Using projective tests and unobtrusive measures to circumvent the need for a respondents consent </li></ul><ul><li>Using hidden tape recorders </li></ul><ul><li>Not debriefing the respondent </li></ul><ul><li>Conducting simulated product tests in which identical product is tried by respondent except for variations in color </li></ul>Ethical Issues in Data Collection
  108. 108. <ul><li>Guidelines: </li></ul><ul><ul><li>Reviewing data </li></ul></ul><ul><ul><li>Getting started </li></ul></ul><ul><ul><li>Setting the feedback objective </li></ul></ul><ul><ul><li>Customer presentation </li></ul></ul><ul><ul><li>Sharing responsibility </li></ul></ul><ul><ul><li>Handling issues you cannot fix </li></ul></ul><ul><ul><li>Working the issue resolution with your account </li></ul></ul>Collecting Data
  109. 109. <ul><li>Personal Interview </li></ul><ul><li>Telephone Interview </li></ul><ul><li>Mail Survey </li></ul>Basic Survey Methods
  110. 110. <ul><li>There Are Four Entities Involved: </li></ul><ul><li>Researcher </li></ul><ul><li>Interviewer </li></ul><ul><li>Interviewee </li></ul><ul><li>The Interview Environment </li></ul>Personal Interviews
  111. 111. <ul><li>Methods: </li></ul><ul><li>Door to Door Interviewing </li></ul><ul><li>Executive Interviewing </li></ul><ul><li>Mall Intercept Surveys </li></ul><ul><li>Self Administered Interviews </li></ul><ul><li>Purchase Intercept Technique (PIT) </li></ul><ul><li>Omnibus Surveys </li></ul>Personal Interviews (Contd.)
  112. 112. <ul><li>Advantages: </li></ul><ul><li>Can arouse and keep interest </li></ul><ul><li>Can build rapport </li></ul><ul><li>Ask complex questions with the help of visual and other aids </li></ul><ul><li>Clarify misunderstandings </li></ul><ul><li>High degree of flexibility </li></ul><ul><li>Probe for more complete answers </li></ul><ul><li>Accurate for neutral questions </li></ul><ul><li>Do not need an explicit or current list of households or individuals </li></ul>Personal Interviews (Contd.) <ul><li>Disadvantages: </li></ul><ul><li>Bias of Interviewer </li></ul><ul><li>Response Bias </li></ul><ul><ul><li>Embarrassing/personal questions </li></ul></ul><ul><li>Time Requirements </li></ul><ul><li>Cost Per Completed Interview Is High </li></ul>
  113. 113. <ul><li>The Important Aspects of Telephone Interviewing : </li></ul><ul><li>Selecting telephone numbers </li></ul><ul><ul><li>Pre-specified list </li></ul></ul><ul><ul><li>A directory </li></ul></ul><ul><ul><li>Random dialing procedure </li></ul></ul><ul><ul><ul><li>Random digit dialing </li></ul></ul></ul><ul><ul><ul><li>Systematic random digit dialing (SRDD) </li></ul></ul></ul><ul><li>Call outcomes </li></ul><ul><li>The introduction </li></ul><ul><li>When to call </li></ul><ul><li>Call reports </li></ul>Telephone Interviewing
  114. 114. <ul><li>Advantages: </li></ul><ul><li>Central location, under supervision, at own hours </li></ul><ul><li>More interviews can be conducted in a given time </li></ul><ul><ul><li>Travelling time is saved </li></ul></ul><ul><li>More hours of the day are productive </li></ul><ul><li>Repeated call backs at lower cost </li></ul><ul><li>Absence of administrative costs </li></ul><ul><li>Lower cost per completed interview </li></ul><ul><li>Intrusiveness of the phone and ease of call backs </li></ul><ul><ul><li>Less sample bias </li></ul></ul>Telephone Interviewing (Contd.) <ul><li>Limitations: </li></ul><ul><li>Inability to employ visual aids or complex tasks </li></ul><ul><li>Can't be longer than 5-10 min. or they get boring </li></ul><ul><li>Amount of data that can be collected is relatively less </li></ul><ul><li>A capable interviewer essential </li></ul><ul><li>Sample bias </li></ul><ul><ul><li>As all people do not have phones, or are not listed </li></ul></ul>
  115. 115. <ul><li>Requires a broad identification of the individuals to be sampled before data collection begins </li></ul><ul><li>Some Decisions That Need to Be Taken Are: </li></ul><ul><li>Type of Return Envelope </li></ul><ul><li>Postage </li></ul><ul><li>Method of Addressing </li></ul><ul><li>Cover Letter </li></ul><ul><li>The Questionnaire Length, Layout, Color, Format Etc </li></ul><ul><li>Method of Notification </li></ul><ul><li>Incentive to Be Given </li></ul>Mail Surveys
  116. 116. <ul><li>Advantages: </li></ul><ul><li>Lower cost </li></ul><ul><li>Better results, including a shorter response time </li></ul><ul><li>Reliable answers as no inhibiting intermediary </li></ul><ul><li>Survey answered at respondents discretion </li></ul>Mail Surveys (Contd.) <ul><li>Disadvantages: </li></ul><ul><li>The identity of the respondent is inadequately controlled </li></ul><ul><li>No control over whom the respondent consults before answering the questions </li></ul><ul><li>The speed of the response can't be monitored </li></ul><ul><li>No control on the order in which the questions are exposed or answered </li></ul><ul><li>The respondent may not clearly understand the question and no opportunity to clarify </li></ul><ul><li>No long questionnaires </li></ul><ul><li>Subject to availability of a mailing list </li></ul><ul><li>Response rate is generally poor </li></ul><ul><li>Number of problems such as obsolescence, omissions, duplications, etc </li></ul>
  117. 117. <ul><li>Perceived amount of work required, and the length of the questionnaire </li></ul><ul><li>Intrinsic interest in the topic </li></ul><ul><li>Characteristics of the sample </li></ul><ul><li>Credibility of the sponsoring organization </li></ul><ul><li>Level of induced motivation </li></ul><ul><li>Coping with non-response: </li></ul><ul><li>Include monetary incentive </li></ul><ul><li>Send a follow-up letter </li></ul><ul><li>Include return envelope </li></ul><ul><li>Alternatives: </li></ul><ul><li>Mail Panels </li></ul><ul><li>Fax Surveys </li></ul>Factors Affecting the Response Rate
  118. 118. <ul><li>Advantages </li></ul><ul><li>The best way to implement some sample designs </li></ul><ul><li>Most effective way of enlisting cooperation. </li></ul><ul><li>Advantages of interview questions-probing for adequate answers, accurately following complex instructions or sequences are realized. </li></ul><ul><li>Multi-method data collection are feasible </li></ul><ul><li>Rapport and confidence building are possible. </li></ul><ul><li>Probably longer interviews can be done in person. </li></ul>Comprehensive benefits of Various Methods Survey Method: Personal Interviewing <ul><li>Limitations </li></ul><ul><li>It is likely to be more costly than alternatives. </li></ul><ul><li>A trained staff of interviewers that is geographically near the sample is needed. </li></ul><ul><li>The total data collection period is likely to be longer than for most procedures. </li></ul><ul><li>Some samples may be more accessible by some other mode. </li></ul>
  119. 119. Comprehensive benefits of Various Methods Survey Method: Telephone Interviewing <ul><li>Advantages </li></ul><ul><li>Lower costs than personal interviews. </li></ul><ul><li>Random Digit-Dialing (RDD) sampling of general population. </li></ul><ul><li>Better access to certain populations </li></ul><ul><li>Shorter data collection periods. </li></ul><ul><li>The advantages of interviewer administration (In contrast to mail surveys). </li></ul><ul><li>Interviewer staffing and management easier than personal interviews-smaller staff needed, not necessary to be near sample, supervision and quality control potentially better. </li></ul><ul><li>Likely better response rate from a list sample than from mail </li></ul><ul><li>Limitations </li></ul><ul><li>Sampling limitations, especially as a result of omitting those without telephone </li></ul><ul><li>Nonresponse associated with RDD sampling is higher than with interviews </li></ul><ul><li>Questionnaires or measurement constraints </li></ul><ul><li>Possibly less appropriate for personal or sensitive questions if no prior contact </li></ul>
  120. 120. Comprehensive benefits of Various Methods Survey Method: Self Administration <ul><li>Advantages </li></ul><ul><li>Ease of presenting questions requiring visual aids. </li></ul><ul><li>Asking questions with long or complex response categories is facilitated. </li></ul><ul><li>Asking batteries of similar questions is possible. </li></ul><ul><li>Limitations </li></ul><ul><li>Questionnaire design needs special attention </li></ul><ul><li>Open questions are usually not useful. </li></ul><ul><li>Respondents require good reading and writing skills. </li></ul><ul><li>The interviewer is not present to exercise quality control with respect to answering all questions, meeting questions objectives, or the quality of answers provided. </li></ul>
  121. 121. Comprehensive benefits of Various Methods Survey Method: Mail Procedures <ul><li>Advantages </li></ul><ul><li>Relatively low cost </li></ul><ul><li>Can be accomplished with minimal staff and facilities. </li></ul><ul><li>Provides access to widely dispersed samples. </li></ul><ul><li>Respondents have time to give thoughtful answers, look up records, or consult others. </li></ul><ul><li>Limitations </li></ul><ul><li>Ineffective as a way of enlisting cooperation. </li></ul><ul><li>Various disadvantages of not having interviewer involved in data collection. </li></ul><ul><li>Need for accurate mailing addresses of the sample. </li></ul>
  122. 122. Comprehensive benefits of Various Methods Survey Method: Drop-off questionnaire <ul><li>Advantages </li></ul><ul><li>The interviewer can explain the study, answer questions, and designate a respondent. </li></ul><ul><li>Response rates tend to be like those of personal interview studies. </li></ul><ul><li>There is more opportunity to give thoughtful answers and consult records. </li></ul><ul><li>Limitations </li></ul><ul><li>Costs about as much as personal interviews. </li></ul><ul><li>A field staff is required. </li></ul>
  123. 123. 6 Measurement, scaling & sampling.
  124. 124. <ul><li>Mental states used by individuals to structure the way they perceive their environment and guide the way they respond to it </li></ul>What Are Attitudes?
  125. 125. <ul><li>Majority of questions in marketing research are designed to measure attitudes </li></ul><ul><li>Attitudes include </li></ul><ul><ul><li>Information possessed </li></ul></ul><ul><ul><li>Feelings of like and/or dislike </li></ul></ul><ul><ul><li>Intentions to behave </li></ul></ul><ul><li>Management wants to understand and influence behavior </li></ul>Attitude Measurement
  126. 126. <ul><li>Attitudes lead to behavior </li></ul><ul><li>More feasible to ask questions on attitudes than to observe and interpret behavior </li></ul><ul><li>Large capacity for diagnosis and explanation </li></ul><ul><li>Learn which features of a new product concept are acceptable or unacceptable </li></ul><ul><li>Measure the perceived strengths and weaknesses of competitive alternatives </li></ul>Reasons for Measuring Attitudes
  127. 127. <ul><li>Cognitive or Knowledge Component </li></ul><ul><ul><li>Represents a person’s information about an object </li></ul></ul><ul><ul><li>Awareness of existence of the object </li></ul></ul><ul><ul><li>Beliefs about the characteristics or attributes of the object </li></ul></ul><ul><ul><li>Judgments about the relative importance of each of the attributes </li></ul></ul><ul><li>Affective or Liking Component </li></ul><ul><ul><li>Summarizes a person’s overall feelings toward an object, situation, or person </li></ul></ul><ul><ul><li>On a scale of like-dislike or favorable-unfavorable </li></ul></ul><ul><ul><li>When there are several alternatives, liking is expressed in terms of preference </li></ul></ul><ul><ul><li>Measured by asking which alternative is “most preferred” or “first choice,” which is the “second choice,” and so on </li></ul></ul><ul><li>Intention or Action Component </li></ul><ul><ul><li>Refers to a person’s expectations of future behavior toward an object </li></ul></ul><ul><ul><li>Intentions are usually limited to a distinct time period that depends on buying habits and planning horizons </li></ul></ul><ul><li>Advantage </li></ul><ul><ul><li>Incorporates information about a respondent’s ability or willingness to pay for the object, or other taken action </li></ul></ul>Components of Attitude
  128. 128. <ul><li>Measurement </li></ul><ul><li>Standardized process of assigning numbers or other symbols to certain characteristics of objects of interests according to pre-specified rules </li></ul><ul><li>Characteristics for Standardization </li></ul><ul><li>One-to-one correspondence between the symbol and the characteristic in the object that is being measured </li></ul><ul><li>Rules for assignment should be invariant over time and the objects being measured </li></ul><ul><li>Scaling </li></ul><ul><li>Process of creating a continuum on which objects are located according to the amount of the measured characteristic that the object possesses </li></ul>Measurement and Scaling
  129. 129. <ul><li>Nominal Scale </li></ul><ul><li>Objects are assigned to mutually exclusive, labeled categories </li></ul><ul><li>No necessary relationships among categories </li></ul><ul><li>No ordering or spacing are implied </li></ul><ul><li>Only possible arithmetic operation is a count of each category </li></ul><ul><li>Ordinal Scale </li></ul><ul><li>Rank objects or arrange them in order by some common variable </li></ul><ul><li>Does each object have more or less of a variable than some other object? </li></ul><ul><li>Does not provide information on how much difference there is between objects </li></ul><ul><li>Arithmetic operations are limited to statistics such as median or mode </li></ul>Measurement Scales <ul><li>Interval Scale </li></ul><ul><li>Numbers are assigned to objects that represent categories, rank orders, as well as how much the object is preferred on the attribute being measured </li></ul><ul><li>Differences can be compared </li></ul><ul><li>Entire range of statistical operations can be employed </li></ul><ul><li>Ratio Scale </li></ul><ul><li>Special kind of interval scale with meaningful zero point </li></ul><ul><li>Possible to say how many times greater or smaller one object is than the other </li></ul><ul><li>Magnitude scaling of attitudes has been calibrated through numeric estimation </li></ul>
  130. 130. Attitude Scales Single-Item Scales Continuous Scales Multi-Item Scales Stapel Scales Thurstone Scales Likert Scales Associative Scales Semantic Differential Scale Paired Comparison Scales Q-sort Scales Comparative Scales Itemized Category Scales Pictorial Scales Constant Sum Scales Rank Order Scales Classification of Attitude Scales
  131. 131. <ul><li>Problems in choosing </li></ul><ul><ul><li>There are many different techniques, each with its own strengths and weaknesses </li></ul></ul><ul><ul><li>Virtually any technique can be adapted to the measurement of any one of the attitude components </li></ul></ul><ul><li>Researchers choice shaped by: </li></ul><ul><ul><li>The specific information required </li></ul></ul><ul><ul><li>Adabtability of the scale to the data collection method and budget constraints </li></ul></ul><ul><ul><li>Compatibility of the scale with the structure of the respondent’s attitude </li></ul></ul>Choosing An Attitudinal Scale
  132. 132. <ul><li>Validity </li></ul><ul><ul><li>An attitude measure has validity if it measures what it is supposed to measure </li></ul></ul><ul><li>Face Validity </li></ul><ul><ul><li>The extent to which the content of a measurement scale appears to tap all relevant facets of the construct </li></ul></ul><ul><li>Criterion Validity </li></ul><ul><ul><li>Based on empirical evidence that the attitude measure correlates with other “criterion” variables </li></ul></ul><ul><li>Concurrent validity </li></ul><ul><ul><li>Two variables are measured at the same time </li></ul></ul><ul><li>Predictive validity </li></ul><ul><ul><li>The attitude measure can predict some future event </li></ul></ul><ul><li>Convergent validity </li></ul><ul><ul><li>A form of construct validity that represents the association between the measured construct and measures of other constructs with which the construct is related on theoretical grounds </li></ul></ul>Accuracy of Attitude Measurements <ul><ul><li>Discriminant validity </li></ul></ul><ul><ul><li>A form of construct validity that represents the extent to which the measured construct is not associated with which the construct is related on theoretical grounds </li></ul></ul><ul><ul><li>Construct Validity </li></ul></ul><ul><ul><li>A scale evaluation criterion that relates to the underlying question &quot;what is the nature of the underlying variable or construct measured by the scale?“ </li></ul></ul><ul><ul><li>Reliability </li></ul></ul><ul><ul><li>The consistency with which the measure produces the same results with the same or comparable population </li></ul></ul><ul><ul><li>Sensitivity </li></ul></ul><ul><ul><li>Extent to which ratings provided by a scale are able to discriminate between the respondents who differ with respect to the construct being measured </li></ul></ul><ul><ul><li>Generalizability </li></ul></ul><ul><ul><li>Refers to the ease of scale administration and interpretation in different research settings and situations </li></ul></ul><ul><ul><li>Relevancy </li></ul></ul><ul><ul><li>Relevance = reliability * validity </li></ul></ul>
  133. 133. 7 Design of survey questionnaires.
  134. 134. Designing the Questionnaire <ul><li>Questionnaire building </li></ul><ul><li>is an art! </li></ul>A questionnaire is always custom-built!
  135. 135. <ul><li>PLANNING WHAT TO MEASURE </li></ul><ul><li>Revisit the research objectives </li></ul><ul><li>Decide on the Research issue of your questionnaire </li></ul><ul><li>Get additional information on the research issue from data sources and secondary exploratory research </li></ul><ul><li>Decide what to be asked under the research issue </li></ul><ul><li>FORMATTING THE QUESTIONNAIRE </li></ul><ul><li>In each issue determine the content of each question </li></ul><ul><li>Decide on the format of each question </li></ul><ul><li>QUESTION WORDING </li></ul><ul><li>Determine how the question is worded </li></ul><ul><li>Evaluate each question on the basis of comprehensibility, knowledge and ability, willingness/inclination of a typical respondent to answer the question </li></ul>Process of Questionnaire Design
  136. 136. <ul><li>SEQUENCING AND LAYOUT DESIGNS </li></ul><ul><li>Layout the questions in proper sequence </li></ul><ul><li>Group all the questions in each subtopic to get a single questionnaire </li></ul><ul><li>PRETESTING AND CORRECTING PROBLEMS </li></ul><ul><li>Read through the whole questionnaire to check whether it makes sense and it measures what it is supposed to measure </li></ul><ul><li>Check the questionnaire for error </li></ul><ul><li>Pretest the questionnaire </li></ul><ul><li>Correct the problems </li></ul>Process of Questionnaire Design
  137. 137. <ul><li>Logical Steps to Develop a Good Questionnaire </li></ul><ul><li>Plan what to measure </li></ul><ul><li>Formulate questions to obtain the needed information </li></ul><ul><li>Decide on the order and wording of questions and the layout of the questionnaire </li></ul><ul><li>Using a sample, test the questionnaire for omissions and ambiguity </li></ul><ul><li>Correct the problems (pretest again, if necessary) </li></ul><ul><li>Planning What to Measure </li></ul><ul><li>Specify research objectives and information to be collected </li></ul><ul><li>Relevance of the study </li></ul><ul><li>Translating Research Objectives Into Information Requirements </li></ul>Designing the Questionnaire
  138. 138. <ul><li>Formatting the Question </li></ul><ul><li>Decision to be made regarding the degree of freedom to be given to the respondents in answering the questions </li></ul><ul><li>Alternatives </li></ul><ul><ul><li>Open ended with no classification </li></ul></ul><ul><ul><li>Open ended where the interviewer uses precoded classifications to record the response </li></ul></ul><ul><ul><li>Close ended or structured format in which a question or a supplementary card presents the responses to be considered </li></ul></ul>Designing the Questionnaire (Contd.)
  139. 139. <ul><li>Open Ended Questions Are Good for the Following Circumstances </li></ul><ul><li>Introduction to a survey or to a topic </li></ul><ul><li>When it is important to measure the saliency of an issue to a respondent </li></ul><ul><li>When there are too many responses to be listed, or they can't be foreseen </li></ul><ul><li>When verbatim responses are desired to give the flavor of people's answers or to cite examples </li></ul><ul><li>When the behavior to be measured is sensitive or disapproved </li></ul>Open Ended Questions
  140. 140. <ul><li>Disadvantages </li></ul><ul><li>Variability in the clarity and depth of the responses </li></ul><ul><li>Articulateness of the respondent in personal interview </li></ul><ul><li>Willingness to compose a written answer for a mail survey </li></ul><ul><li>Interviewer's ability to record the verbatim answers quickly </li></ul>Open Ended Questions <ul><li>Advantages </li></ul><ul><li>Wide range of responses </li></ul><ul><li>Responses obtained without any influence </li></ul><ul><li>Free choices </li></ul>
  141. 141. <ul><li>There Are Two Basic Formats for Closed Ended or Structured Questions </li></ul><ul><li>Choice from a list of responses </li></ul><ul><li>Appropriate single-choice rating on a scale </li></ul>Closed-response Questions
  142. 142. Closed-response Questions (Contd.) <ul><li>Advantages </li></ul><ul><li>Easier to answer </li></ul><ul><li>Require less effort by the interviewer </li></ul><ul><li>Tabulation and analysis is easier </li></ul><ul><li>Less potential error in the way the question is asked and the way it is recorded </li></ul><ul><li>The responses are directly comparable from respondent to respondent </li></ul><ul><li>Limitations </li></ul><ul><li>Disagreement among researchers on the type of responses that should be listed </li></ul><ul><li>The answer to a closed response question will be received no matter how relevant or irrelevant the question is in that context </li></ul><ul><li>May not produce meaningful results </li></ul><ul><li>Dichotomous questions are prone to a large amount of measurement error because the alternatives are polarized </li></ul><ul><li>Good questions are hard to develop </li></ul><ul><li>Provides fewer opportunities of self expression </li></ul><ul><li>The list of alternative responses provides answers that might have not been considered by the respondent who are reluctant to admit ignorance, and thereby selecting a &quot;reasonable&quot; response </li></ul>
  143. 143. <ul><li>Generally five to seven categories </li></ul><ul><li>Ideally the multiple choices should be mutually exclusive </li></ul>Number of Response Categories
  144. 144. <ul><li>Responses are likely to be affected by the order in which they are presented. </li></ul><ul><li>What factor influences your fast-food restaurant choice most ? </li></ul><ul><li> Convenient location </li></ul><ul><li> Quality of food </li></ul><ul><li> Menu selection </li></ul><ul><li> Fast service </li></ul><ul><li> Reasonable prices </li></ul><ul><li> Brand name </li></ul><ul><li>Cleanliness </li></ul><ul><li>To prevent order bias, place the average or expected response at various positions in the sequence of categories </li></ul>Order of Response Categories
  145. 145. <ul><li>Respondents who do not know the answer might take categories as cues. </li></ul><ul><li>How many long-distance calls do make in a week? </li></ul><ul><li> less than 5  less than 10 </li></ul><ul><li> 5-10 or  10-20 </li></ul><ul><li> More than 10.  More than 20. </li></ul>Range of Response Categories
  146. 146. <ul><li>Concerns the handling of “don’t know” and neutral responses </li></ul><ul><li>May be advisable to provide the interviewer with an additional “no answer” category to identify these people correctly </li></ul>Handling Uncertainty and Ignorance
  147. 147. <ul><li>Probe: </li></ul><ul><li>Using an open-response question to follow up a closed-response question </li></ul><ul><li>Two general purposes for the use of probes : </li></ul><ul><li>Pinpoint questions that were particularly difficult for respondents </li></ul><ul><li>Aid researcher interpretation of respondent answers </li></ul>Using Both Open- And Closed-Response Questions
  148. 148. <ul><li>The following details need special attention: </li></ul><ul><li>Is the vocabulary simple, direct, and familiar to all respondents? </li></ul><ul><li>Do any words have vague or ambiguous meanings? </li></ul><ul><li>Are any questions &quot; double-barreled”? </li></ul><ul><li>Are any questions leading or loaded? </li></ul><ul><li>Are the instructions potentially confusing? </li></ul><ul><li>Is the question applicable to all respondents? </li></ul><ul><li>Are the questions of appropriate length? </li></ul>Question Wording
  149. 149. <ul><li>Avoid ambiguous words </li></ul><ul><li>How many times per month do you visit a fast-food restaurant? </li></ul><ul><li> Never </li></ul><ul><li> Occasionally </li></ul><ul><li> Sometimes </li></ul><ul><li> Often </li></ul>Question Wording
  150. 150. <ul><li>Are any questions loaded? </li></ul><ul><li>1) Don’t you think, because its so greasy, fast-food is one of the worst types of food? </li></ul><ul><li>2) Do you prefer a burger that is grilled on a hot stainless-steel grill or cooked by passing the raw meat through an open gas flame? </li></ul>Question Wording
  151. 151. <ul><li>Are any questions &quot;double-barreled”? </li></ul><ul><li>Are you satisfied with the price and the service of Café Coffee Day? </li></ul>Question Wording
  152. 152. Question Wording <ul><li>Is the question applicable to all respondents? </li></ul><ul><li>Why do you like fast-food? </li></ul><ul><li>Assumes that respondent likes fast-food. </li></ul>
  153. 153. <ul><li>Consumption of Kellogg’s Frosted Flakes </li></ul><ul><li>The casual approach </li></ul><ul><ul><li>“ Have you eaten ‘Frosted Flakes’ within the last week? </li></ul></ul><ul><li>The numbered card </li></ul><ul><ul><li>“ Would you please read off the number on this card that corresponds to what you had eaten for breakfast in the last week?” </li></ul></ul><ul><ul><li>(Hand card to respondent) </li></ul></ul><ul><ul><li>Pancakes </li></ul></ul><ul><ul><li>Frosted Flakes </li></ul></ul><ul><ul><li>Other (what)? </li></ul></ul>Asking Sensitive Questions
  154. 154. <ul><li>The everybody approach </li></ul><ul><ul><li>“ As you know, many people have been eating Frosted Flakes for breakfast. Do you eat Frosted Flakes?” </li></ul></ul><ul><li>The “other people” approach </li></ul><ul><ul><li>“ Do you know of any adult who eats Frosted Flakes?” </li></ul></ul><ul><ul><li>“ How about yourself?” </li></ul></ul>Asking Sensitive Questions
  155. 155. <ul><li>The sealed ballot technique </li></ul><ul><ul><li>In this version you explain that the survey respects people’s right to anonymity with respect to their eating habits, and that they themselves are to fill out the answer to the question, seal it in an envelope, and drop it in a box conspicuously labeled “sealed ballet box” that is carried by the interviewer </li></ul></ul><ul><li>The Kinsey approach </li></ul><ul><ul><li>Stare firmly into respondent’s eyes and ask in simple clear-cut language as that to which the respondent is accustomed, and with an air of assuming that everyone had done everything, “Do you eat Frosted Flakes for breakfast?” </li></ul></ul>Asking Sensitive Questions
  156. 156. <ul><li>Randomized Response Technique </li></ul><ul><ul><li>The respondent is asked to answer one or two randomly selected questions without revealing which question has been answered </li></ul></ul><ul><li>Questions: </li></ul><ul><ul><li>Sensitive </li></ul></ul><ul><ul><li>Innocuous </li></ul></ul><ul><li>Since the interviewer records a “yes” or “no” answer without knowing which question has been answered, the respondent feels free to answer honestly </li></ul>Asking Sensitive Questions
  157. 157. <ul><li>Open with an easy and non threatening question </li></ul><ul><li>The questionnaire should flow smoothly and logically from one topic to the next </li></ul><ul><li>Proceed from broad general questions to the more specific </li></ul>Sequence And Layout Decisions
  158. 158. Organization of a Typical Questionnaire Location Type Function Example Starting Questions Broad, General Questions To break the ice and establish rapport with the respondents Do you own a personal computer? Next few Questions Simple and Direct Questions To reassure the respondent that the survey is simple and easy to answer. What brands of personal computers did you consider while you were buying the PC? Questions up to a third of the questionnaire Focused Questions Relate more to the research objectives and convey to the respondent the area of research What attributes did you consider when you purchased your personal computer? Major portion of the questionnaire Focused Questions: Some may be difficult and complicated To obtain most of the information required for the research Rank the following attributes of a personal computer based on their importance to you. Last few questions Personal questions that may be perceived by the respondent as sensitive To get classification and demographic information about the respondent. What is the highest level of education you have attained?
  159. 159. <ul><li>Sensitive questions should not be placed in the beginning of the questionnaire </li></ul><ul><li>Use good quality of paper </li></ul><ul><li>Physical layout should be appealing and interesting </li></ul><ul><li>Order bias </li></ul>Sequence And Layout Decisions
  160. 160. Order Bias: Does The Question Create The Answer? Percentage of Respondents “Very Much Interested” in Buying New Product Questions Preceding Buying Interest Question 1. No question asked 2.8 2. Asked only about advantages 16.7 3. Asked only about disadvantages 0.0 4. Asked about both advantages and disadvantages 5.7
  161. 161. <ul><li>Pretest Design </li></ul><ul><li>Pretesting Specific Questions For </li></ul><ul><ul><ul><li>Variation </li></ul></ul></ul><ul><ul><ul><li>Meaning </li></ul></ul></ul><ul><ul><ul><li>Task difficulty </li></ul></ul></ul><ul><ul><ul><li>Respondent interest and attention </li></ul></ul></ul><ul><li>Pretesting the Questionnaire </li></ul><ul><ul><ul><li>Flow of the questionnaire </li></ul></ul></ul><ul><ul><ul><li>Skip patterns </li></ul></ul></ul><ul><ul><ul><li>Length </li></ul></ul></ul><ul><ul><ul><li>Respondent Interest and Attention </li></ul></ul></ul>Pretesting and Correcting Problems
  162. 162. Quantitative Vs Qualitative Research <ul><li>A research strategy that emphasizes quantification in collection and analysis of data </li></ul><ul><li>Entails a deductive approach to the relationship between theory and research in which the accent is placed on the testing of the theories </li></ul><ul><li>It has incorporated the practices and norms of the natural scientific model and positivism in particular </li></ul><ul><li>It embodies a view of social reality as an external objective reality </li></ul><ul><li>In summary – The collection of numerical data and as exhibiting view of relationship between theory and research as deductive </li></ul><ul><li>Strategy that emphasizes words rather than quantificatino in collection & analysis of data </li></ul><ul><li>Predominantly emphasizes an inductive approach to relationship between theory and research in which emphasis is placed on generation of theories </li></ul><ul><li>No scientific model has been accepted as practices and norms </li></ul><ul><li>Social reality as a constantly shifting emergent property of individual’s creation </li></ul>
  163. 163. Quantitative research methods & Data Analysis
  164. 164. <ul><li>A set of methods and techniques used to obtain information and insights from data </li></ul><ul><li>Helps avoid erroneous judgements and conclusions </li></ul><ul><li>Can constructively influence the research objectives and the research design </li></ul>Data Analysis
  165. 165. <ul><li>Data editing </li></ul><ul><li>Coding </li></ul><ul><li>Statistically adjusting the data </li></ul>Preparing the Data for Analysis
  166. 166. Data Editing <ul><li>Data Editing </li></ul><ul><li>Identifies omissions, ambiguities, and errors in responses </li></ul><ul><li>Conducted in the field by interviewer and field supervisor and by the analyst prior to data analysis </li></ul>
  167. 167. Data Editing <ul><li>Problems identified with data editing </li></ul><ul><li>Interviewer Error </li></ul><ul><li>Omissions </li></ul><ul><li>Ambiguity </li></ul><ul><li>Inconsistencies </li></ul><ul><li>Lack of Cooperation </li></ul><ul><li>Ineligible Respondent </li></ul>
  168. 168. Coding <ul><li>Coding </li></ul><ul><li>Coding closed-ended questions involves specifying how the responses are to be entered </li></ul><ul><li>Open-ended questions are difficult to code </li></ul><ul><ul><li>Lengthy list of possible responses is generated </li></ul></ul>
  169. 169. <ul><li>Statistically Adjusting the Data + Weighting </li></ul><ul><li>Each response is assigned a number according to a pre-specified rule </li></ul><ul><li>Makes sample data more representative of target population on specific characteristics </li></ul><ul><li>Modifies number of cases in the sample that possess certain characteristics </li></ul><ul><li>Adjusts the sample so that greater importance is attached to respondents with certain characteristics </li></ul>Preparing the Data for Analysis (Contd.)
  170. 170. <ul><li>Statistically Adjusting the Data + Variable Re-specification </li></ul><ul><li>Existing data is modified to create new variables </li></ul><ul><li>Large number of variables collapsed into fewer variables </li></ul><ul><li>Creates variables that are consistent with study objectives </li></ul><ul><li>Dummy variables are used (binary, dichotomous, instrumental, quantitative variables) </li></ul><ul><li>Use (d-1) dummy variables to specify (d) levels of qualitative variable </li></ul>Preparing the Data for Analysis (Contd.)
  171. 171. <ul><li>Statistically Adjusting the Data + Scale Transformation </li></ul><ul><li>Scale values are manipulated to ensure comparability with other scales </li></ul><ul><li>Standardization allows the researcher to compare variables that have been measured using different types of scales </li></ul><ul><li>Variables are forced to have a mean of zero and a standard deviation of one </li></ul><ul><li>Can be done only on interval or ratio scaled data </li></ul>Preparing the Data for Analysis (Contd.)
  172. 172. <ul><li>Consists of counting the number of cases that fall into various categories </li></ul><ul><li>Use of Simple Tabulation </li></ul><ul><li>Determine empirical distribution (frequency distribution) of the variable in question </li></ul><ul><li>Calculate summary statistics, particularly the mean or percentages </li></ul><ul><li>Aid in &quot;data cleaning&quot; aspects </li></ul>Simple Tabulation
  173. 173. <ul><li>Reports the number of responses that each question received </li></ul><ul><li>Organizes data into classes or groups of values </li></ul><ul><li>Shows number of observations that fall into each class </li></ul><ul><li>Can be illustrated simply as a number or as a percentage or histogram </li></ul><ul><li>Response categories may be combined for many questions </li></ul><ul><li>Should result in categories with worthwhile number of respondents </li></ul>Frequency Distribution
  174. 174. <ul><li>Statistics normally associated with a frequency distribution to help summarize information in the frequency table </li></ul><ul><li>Measures of central tendency mean, median and mode </li></ul><ul><li>Measures of dispersion (range, standard deviation, and coefficient of variation) </li></ul><ul><li>Measures of shape (skewness and kurtosis) </li></ul>Descriptive Statistics
  175. 175. <ul><li>Differences between means or percentages of two subgroup responses can provide insights </li></ul><ul><li>Difference between means is concerned with the association between two questions </li></ul><ul><li>Question upon which means are based are intervally scaled </li></ul>Analysis for Various Population Subgroups
  176. 176. <ul><li>Statistical analysis technique to study the relationships among and between variables </li></ul><ul><li>Sample is divided to learn how the dependent variable varies from subgroup to subgroup </li></ul><ul><li>Frequency distribution for each subgroup is compared to the frequency distribution for the total sample </li></ul><ul><li>The two variables that are analyzed must be nominally scaled </li></ul>Cross Tabulations
  177. 177. <ul><li>Type of Data </li></ul><ul><ul><li>Classification of data involves nominal, ordinal, interval and ratio scales of measurement </li></ul></ul><ul><ul><li>Nominal scaling is restricted to the mode as the only measure of central tendency </li></ul></ul><ul><ul><li>Both median and mode can be used for ordinal scale </li></ul></ul><ul><ul><li>Non-parametric tests can only be run on ordinal data </li></ul></ul><ul><ul><li>Mean, median and mode can all be used to measure central tendency for interval and ratio scaled data </li></ul></ul>Factors Influencing the Choice of Statistical Technique
  178. 178. <ul><li>Research Design </li></ul><ul><ul><li>Dependency of observations </li></ul></ul><ul><ul><li>Number of observations per object </li></ul></ul><ul><ul><li>Number of groups being analyzed </li></ul></ul><ul><ul><li>Control exercised over variable of interest </li></ul></ul><ul><li>Assumptions Underlying the Test Statistic </li></ul><ul><ul><li>If assumptions on which a statistical test is based are violated, the test will provide meaningless results </li></ul></ul>Factors Influencing the Choice of Statistical Technique (Contd.)
  179. 179. <ul><li>Univariate Techniques </li></ul><ul><ul><li>Appropriate when there is a single measurement of each of the 'n' sample objects or there are several measurements of each of the `n' observations but each variable is analyzed in isolation </li></ul></ul><ul><ul><li>Nonmetric - measured on nominal or ordinal scale </li></ul></ul><ul><ul><li>Metric-measured on interval or ratio scale </li></ul></ul><ul><ul><li>Determine whether single or multiple samples are involved </li></ul></ul><ul><ul><li>For multiple samples, choice of statistical test depends on whether the samples are independent or dependent </li></ul></ul><ul><li>Multivariate Techniques </li></ul><ul><ul><li>A collection of procedures for analyzing association between two or more sets of measurements that have been made on each object in one or more samples of objects </li></ul></ul><ul><ul><li>Dependence or interdependence techniques </li></ul></ul>Overview of Statistical Techniques
  180. 180. <ul><li>Multivariate Techniques (Contd.) </li></ul><ul><li>Dependence Techniques </li></ul><ul><li>One or more variables can be identified as dependent variables and the remaining as independent variables </li></ul><ul><li>Choice of dependence technique depends on the number of dependent variables involved in analysis </li></ul><ul><li>Interdependence Techniques </li></ul><ul><li>Whole set of interdependent relationships is examined </li></ul><ul><li>Further classified as having focus on variable or objects </li></ul>Overview of Statistical Techniques
  181. 181. <ul><li>Why use Multivariate Analysis? </li></ul><ul><li>To group variables or people or objects </li></ul><ul><li>To improve the ability to predict variables (such as usage) </li></ul><ul><li>To understand relationships between variables (such as advertising and sales) </li></ul>Overview of Statistical Techniques
  182. 182. <ul><li>Assumption (hypothesis) made about a population parameter (not sample parameter) </li></ul><ul><li>Purpose of Hypothesis Testing </li></ul><ul><ul><ul><li>To make a judgement about the difference between two sample statistics or between sample statistic and a hypothesized population parameter </li></ul></ul></ul><ul><li>Evidence has to be evaluated statistically before arriving at a conclusion regarding the hypothesis. </li></ul>Hypothesis Testing: Basic Concepts
  183. 183. Hypothesis Testing <ul><li>The null hypothesis (H o ) is tested against the alternative hypothesis (H a ). </li></ul><ul><li>At least the null hypothesis is stated. </li></ul><ul><li>Decide upon the criteria to be used in making the decision whether to “reject” or &quot;not reject&quot; the null hypothesis. </li></ul><ul><li>The null hypothesis (H o ) is tested against the alternative hypothesis (H a ). </li></ul><ul><li>At least the null hypothesis is stated. </li></ul><ul><li>Decide upon the criteria to be used in making the decision whether to “reject” or &quot;not reject&quot; the null hypothesis. </li></ul>
  184. 184. The Logic of Hypothesis Testing <ul><li>Evidence has to be evaluated statistically before arriving at a conclusion regarding the hypothesis </li></ul><ul><li>Depends on whether information generated from the sample is with fewer or larger observations </li></ul>
  185. 185. Problem Definition Clearly state the null and alternative hypotheses. Choose the relevant test and the appropriate probability distribution Choose the critical value Compare test statistic and critical value Reject null Does the test statistic fall in the critical region? Determine the significance level Compute relevant test statistic Determine the degrees of freedom Decide if one-or two-tailed test Do not reject null
  186. 186. Basic Concepts of Hypothesis Testing (Contd.) <ul><li>The Three Criteria Used Are </li></ul><ul><li>Significance Level </li></ul><ul><li>Degrees of Freedom </li></ul><ul><li>One or Two Tailed Test </li></ul>
  187. 187. Data tabulation techniques <ul><li>Cross Tabulation & Chi-square Test </li></ul><ul><li>ANOVA – Analysis of Variance </li></ul><ul><li>Correlation Analysis </li></ul><ul><li>Regression Analysis </li></ul><ul><li>Factor Analysis </li></ul><ul><li>Cluster Analysis </li></ul><ul><li>L Scaling </li></ul><ul><li>Conjoint Analysis </li></ul><ul><li>Perceptual Maps </li></ul>
  188. 188. Data Interpretation
  189. 189. Common myths <ul><li>Complex analysis and big words impress people. </li></ul><ul><ul><li>Most people appreciate practical and understandable analyses. </li></ul></ul><ul><li>Analysis comes at the end after all the data are collected. </li></ul><ul><ul><li>We think about analysis upfront so that we HAVE the data we WANT to analyze. </li></ul></ul><ul><li>Quantitative analysis is the most accurate type of data analysis. </li></ul><ul><ul><li>Some think numbers are more accurate than words but it is the quality of the analysis process that matters. </li></ul></ul>
  190. 190. Common myths cont… <ul><li>Data have their own meaning. </li></ul><ul><ul><li>Data must be interpreted. Numbers do not speak for themselves. </li></ul></ul><ul><li>Stating limitations to the analysis weakens the evaluation. </li></ul><ul><ul><li>All analyses have weaknesses; it is more honest and responsible to acknowledge them. </li></ul></ul><ul><li>Computer analysis is always easier and better. </li></ul><ul><ul><li>It depends upon the size of the data set and personal competencies. For small sets of information, hand tabulation may be more efficient </li></ul></ul>
  191. 191. <ul><li>It involves: </li></ul><ul><li>organizing the data </li></ul><ul><li>doing the calculations </li></ul><ul><li>interpreting the information </li></ul><ul><ul><ul><li>lessons learned </li></ul></ul></ul><ul><li>explaining limitations </li></ul>Quantitative data analysis is making sense of the numbers to permit meaningful interpretation
  192. 192. <ul><li>Organize all forms/questionnaires in one place </li></ul><ul><li>Check for completeness and accuracy </li></ul><ul><li>Remove those that are incomplete or do not make sense; keep a record of your decisions </li></ul><ul><li>Assign a unique identifier to each form/questionnaire </li></ul>1. Organizing the data
  193. 193. <ul><li>By hand </li></ul><ul><li>By computer </li></ul><ul><ul><li>Excel (spreadsheet) </li></ul></ul><ul><ul><li>Microsoft Access (database mngt) </li></ul></ul><ul><ul><li>Quantitative analysis: SPSS (statistical software) </li></ul></ul>Enter your data
  194. 194. 2. Do the calculations <ul><ul><li>Count (frequencies) </li></ul></ul><ul><ul><li>Percentage </li></ul></ul><ul><ul><li>Mean </li></ul></ul><ul><ul><li>Mode </li></ul></ul><ul><ul><li>Median </li></ul></ul><ul><ul><li>Range </li></ul></ul><ul><ul><li>Standard deviation </li></ul></ul><ul><ul><li>Variance </li></ul></ul><ul><ul><li>Ranking </li></ul></ul><ul><ul><li>Cross tabulation </li></ul></ul>http://learningstore.uwex.edu/pdf/G3658-6.pdf
  195. 195. Which calculation do I use? It depends upon what you want to know Do you want to know how many individuals checked each answer? Frequency Do you want the proportion of people who answered in a certain way? Percentage Do you want the average number or average score? Mean Do you want the middle value in a range of values or scores? Median Do you want to show the range in answers or scores? Range Do you want to compare one group to another? Cross tab Do you want to report changes from pre to post? Change score Do you want to show the degree to which a response varies from the mean? Standard deviation
  196. 196. 3. Interpreting the information <ul><li>Numbers do not speak for themselves. </li></ul><ul><li>For example, what does it mean that 55 youth reported a change in behavior. Or, 25% of participants rated the program a 5 and 75% rated it a 4. What do these numbers mean? </li></ul><ul><li>Interpretation is the process of attaching meaning to the data. </li></ul><ul><li>Interpretation demands fair and careful judgments. Often the same data can be interpreted in different ways. So, it is helpful to involve others or take time to hear how different people interpret the same information. </li></ul><ul><li>Think of ways you might do this…for example, hold a meeting with key stakeholders to discuss the data; ask individual participants what they think </li></ul>
  197. 197. Part of interpreting information is identifying the lessons learned <ul><li>What did you learn? – about the program, about the participants, about the evaluation. </li></ul><ul><ul><li>Are there any ‘ah-has’? What is new? What was expected? </li></ul></ul><ul><ul><li>Were there findings that surprised you? </li></ul></ul><ul><ul><li>Are there things you don’t understand very well – where further study is needed? </li></ul></ul><ul><li>We often include recommendations or an action plan. This helps ensure that the results are used. </li></ul>
  198. 198. <ul><li>Written reports: </li></ul><ul><li>Be explicit about your limitations </li></ul><ul><li>Oral reports: </li></ul><ul><li>Be prepared to discuss limitations </li></ul><ul><li>Be honest about limitations </li></ul><ul><li>Know the claims you cannot make </li></ul><ul><ul><li>Do not claim causation without a true experimental design </li></ul></ul><ul><ul><li>Do not generalize to the population without random sample and quality administration (e.g., <60% response rate on a survey) </li></ul></ul>4. Discuss limitations
  199. 199. Common errors in analyzing quantitative data <ul><li>Incorrect denominator when calculating the percentage </li></ul><ul><li>Do not average percentages </li></ul><ul><li>Using a single average that distorts or misrepresents the range of information </li></ul>
  200. 200. Practical Applications
  201. 201. <ul><li>New Product Research Process </li></ul><ul><li>Generation of new product concepts </li></ul><ul><li>Evaluation and development of those concepts </li></ul><ul><li>Evaluation and development of the actual products </li></ul><ul><li>Testing in the context of the marketing program </li></ul><ul><li>Need Identification </li></ul><ul><ul><li>Perceptual maps </li></ul></ul><ul><ul><li>Social and environmental trends </li></ul></ul><ul><ul><li>Benefit structure analysis </li></ul></ul><ul><ul><li>Product users </li></ul></ul><ul><ul><li>Focus-group interviews </li></ul></ul><ul><ul><li>Lead user analysis </li></ul></ul><ul><li>Concept Identification </li></ul>New Product Research
  202. 202. <ul><li>Test Marketing </li></ul><ul><ul><li>Designing the sell-in market test </li></ul></ul><ul><ul><li>Selecting the test cities </li></ul></ul><ul><ul><li>Implementing and controlling the test </li></ul></ul><ul><ul><li>Timing </li></ul></ul><ul><ul><li>Measurement </li></ul></ul><ul><ul><li>Costs of a test market </li></ul></ul><ul><li>Controlled Distribution Scanner Markets (CDSM) </li></ul><ul><li>Projecting Trial, Repeat and Usage Rate Using Panel Data </li></ul>New Product Research (Contd.)
  203. 203. <ul><ul><li>Gabor and Grainger method </li></ul></ul><ul><ul><li>Multi-brand choice method </li></ul></ul><ul><li>Research for Profit-oriented Pricing </li></ul><ul><li>Research for Share-oriented Pricing </li></ul>Pricing Research
  204. 204. <ul><li>Warehouse and Retail Location Research </li></ul><ul><li>Center-of-gravity Simulation </li></ul><ul><li>Computerized Simulation Models </li></ul><ul><li>Catchment Area Analysis </li></ul><ul><li>Outlet Location Research </li></ul>Distribution Research
  205. 205. <ul><li>Number and Location of Sales Representatives </li></ul><ul><li>Sales effort approach </li></ul><ul><li>Statistical analysis of sales data </li></ul><ul><li>Field experiments </li></ul><ul><li>Computerized models of sales force size and allocation by market and by product line </li></ul>Distribution Research (Contd.)
  206. 206. <ul><li>Criteria </li></ul><ul><li>Recognition </li></ul><ul><li>Recall </li></ul><ul><li>Persuasion </li></ul><ul><ul><li>Forced exposure, brand preference change </li></ul></ul><ul><ul><li>On-air tests -- brand preference change </li></ul></ul><ul><li>Customized Measures of Communication / Attitude </li></ul><ul><li>Purchase Behavior </li></ul><ul><li>Coupon stimulated purchasing </li></ul><ul><li>Split-cable tests </li></ul><ul><li>Tracking Studies </li></ul><ul><li>Diagnostic Testing </li></ul>Advertising Research <ul><li>Copy Test Validity </li></ul><ul><li>Qualitative Research </li></ul><ul><li>Audience Impressions of the Ad </li></ul><ul><li>Adjective Checklist </li></ul><ul><li>Eye Movement </li></ul><ul><li>Physiological Measurement </li></ul><ul><li>Budget Decision </li></ul><ul><li>Media Research </li></ul><ul><ul><li>Measuring print vehicle audiences </li></ul></ul><ul><ul><li>Measuring broadcast vehicles audiences </li></ul></ul>
  207. 207. <ul><li>Promotional Tools </li></ul><ul><li>Price Discounts </li></ul><ul><li>Features </li></ul><ul><li>Displays </li></ul><ul><li>Coupons / Rebates </li></ul><ul><li>Sweepstakes </li></ul><ul><li>Promotional Strategy </li></ul><ul><li>Hi-lo </li></ul><ul><li>Every Day Low Price (EDLP) </li></ul>Sales Promotion Research
  208. 208. Other areas where Research is used <ul><li>Assessing Competitive Advantage </li></ul><ul><li>Brand Equity </li></ul><ul><li>Measuring Brand Equity </li></ul><ul><li>Customer Satisfaction </li></ul><ul><li>Quality Management </li></ul><ul><li>Benchmarking </li></ul><ul><li>Market Intelligence </li></ul>

×