Your SlideShare is downloading. ×



Published on

Priyanka Mam's Doc

Priyanka Mam's Doc

Published in: Technology, Economy & Finance
  • Be the first to comment

  • Be the first to like this

No Downloads
Total Views
On Slideshare
From Embeds
Number of Embeds
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

No notes for slide


  • 1. Introduction:What is Econometrics? Econometrics is based upon the development of statistical methods for estimating economic relationships, testing economic theories, and evaluating and implementing government and business policy. Economic Measurement i.e. measument of things such as economic system, market etc. Micro Economics-Other things remaining the same, a decrease in price are expected to increase the quantity demanded.But does not provide any numerical measure of the relationshipbetween the two.Does not provide a numerical measure; tell us how much quantity goesup or down.Economic Statistical collects data (raw) on GNP, unemployment, interestrate, and so on.So the econometricians use these data’s and build models bases onmathematics.Econometric methods are relevant in virtually every branch of appliedeconomics.They come into play either when we have an economic theory to testor when we have a relationship in mind that has some importance forbusiness decisions or policy analysis. An empirical analysis uses data to test a theory or to estimate arelationship.How does one go about structuring an empirical economic analysis?The question might deal with testing a certain aspect of an economictheory, or it might pertain to testing the effects of a government policy.
  • 2. In principle, econometric methods can be used to answer a wide rangeof questions. 1. Statement of Hypothesis:Keynesian Theory:Marginal Propensity to Consume: The rate of change in consumption fora unit ($) change in income is greater than ZERO but less than ONE. y = f(x) where y = consumption and x= wage. This relationship is based on economic analysis. 2. Mathematical Model:Although Keynes postulated a positive relationship between theconsumption and income he did not specify the precise form offunctional relationship. Consumption Function: XThe model is simply a set of mathematical equation.Y 1 X
  • 3. Where As X increase by one unit Y has to increase by less than one unit. Linear in nature & positive relationship. Single Equation Model. Deterministic Model, since we deal with a relationship of a certain type. EXACT 3. Econometric ModelBase on the Mathematical Model we build an economic model i.e.Economic models are not exact. Samples. + +uWhere u; is the error or the disturbance term.Income is the cause consumptions the effect.But does consumption solely depend on the income?Interest rates, inflation rates etc. And captures all the other terms,which the income is not able to capture in determining consumption.We can add other factors like interest rate, inflation and so on to themodel but we cannot eliminate the entirely.Thus dealing with the error term or the disturbance term is the essence ofany econometric analysis
  • 4. Consumption u Income4. Obtain Data5. Estimation of the Economic Model.Estimate parameters of the consumption functioni.e,Once we regress Y on X we will have:On average with every unit increase in income consumption increaseby 0.71 cents. Or MPC = 0.71.6. Hypothesis TestingIs the above model correct and statistically significant?Or is it just a chance occurrence or peculiarity of the data? i.e. wehave to test whether is statistically less than 1.In other words we have to test our hypothesis.
  • 5. Such conformation or rejection of economic theories on the basis onsample evidence is based on a branch of statistical theory know asstatistical inference or hypothesis testing.7. Forecasting and Prediction.Once we know that our chosen model is accurate we can use thismodel to forecast or predict future values.8. Use of Model for Control and Policy.Government often uses these models for policy-making purposes.Eg. If the government believes that if consumption expenditure in1992 is approximately 4900 billion will keep the unemployment rateat 4.2% then using the above economic model it can control Xvariable to generate the desired target variable.4900 = -184.0779+0.7064X or X = 7194.Types of Data:Cross Sectional Data: Data on one or more variable collected at samepoint in time.However sometimes the data on all units do not correspond toprecisely the same time period, thus in pure cross sectional data weignore the minor time difference.The most important feature of cross sectional data is that thesedata’s have been collected via random sampling.Eg: obtaininginformation on wage, education, experience and other characteristicsby randomly drawing 500 people from the working population, thenwe have a random sample from the population of all working people.Eg: We want to know the current obesity in Kathmandu; we drawa sample of 1000 people randomly from the population andmeasure their height and weight.
  • 6. The fact that the ordering of the data does not matter for econometricanalysis is a key feature of cross-sectional data sets obtained fromrandom sampling.Time Series Data: Data’s collected on a variable or variables on aregular time intervalsi.e, daily, weekly, monthly or annuallyEg: Data on a stock price collected every day, monthly automobilesales, GDP, money supply ect.Key feature of Time series data unlike cross sectional data is the factthat economic observations can rarely, if ever, be assumed to beindependent across time. Most economic and other time series are related, often stronglyrelated, to their recent histories.Many weekly, monthly, and quarterly economic time series display astrong seasonal pattern, which can be an important factor in a timeseries analysis.For example, monthly data on housing starts differs across themonths simply due to changing weather conditions.Pooled Cross Sections:Some data sets have both cross-sectional and time series features.For example, suppose that two cross-sectional household surveys aretaken in the United States, one in 1985 and one in 1990.In 1985, a random sample of households is surveyed for variablessuch as income, savings, family size, and so on.In 1990, a new random sample of households is taken using the samesurvey questions. In order to increase our sample size, we can forma pooled cross section by combining the two years.
  • 7. Because random samples are taken in each year, it would be a fluke if the same household appeared in the sample during both years. Pooling cross sections from different years is often an effective way of analyzing the effects of a new government policy. The idea is to collect data from the years before and after a key policy change. Sources of Data: Primary: SurveySecondary: Internet, government and private agencies.Causality and the notion of Cetris Paribus in Econometric Analysis:For example, in analyzing consumer demand, we are interested inknowing the effect of changing the price of a good on its quantitydemanded, while holding all other factors—such as income, prices ofother goods, and individual tastes—fixed.If other factors are not held fixed, then we cannot know the causaleffect of a price change on quantity demanded.The notion of ceteris paribus—which means “other (relevant) factorsbeing equal”—plays an important role in causal analysis.