Introduction to Econometrics

What is Econometrics?
2

Econometrics is based upon the development of statistical

methods for estimating economic relationships, testing economic theories and evaluating and implementing government and business policy. The most common application of econometrics is the forecasting of such important variables as interest rates, inflation rates etc. but it can be used in other areas too. Eg: in assessing the effect of school spending on student performance in field of education. Econ0metrics has evolved as a separate discipline from mathematical statistics because the former focuses on problems inherent in collecting and analyzing non experimental economic data.

Steps in empirical Economic Analysis

3

Econometric methods are relevant in virtually every branch of applied

economics. They come into play either when we have an economic theory to test or when we have a relationship in mind that has some importance for business decisions or policy analysis. An empirical analysis uses data to test a theory or to estimate a relationship. The first step in any empirical analysis is obviously the careful formulation of the question of interest. The question might deal with testing a certain aspect of an economic theory or it might pertain to testing the effect of a governmental policy In some cases, especially those that involve testing of economic theories, a formal economic model is constructed to begin with. But it is more common to use economic theory less formally, or even to rely entirely on intuition. After the economic model (formal or developed less formally or based on intuition) is specified, it needs to be turned into an econometric model.

Example of economic models

4

A formal economic model: Beckers (1968) economic model

of criminal behaviour: In a seminal article, Noble Prize winner Gary Becker postulated a utility maximizing framework to describe an individuals participation in crime. From Beckers perspective, decision to undertake illegal activity is one of resource allocation, with the benefits and costs of competing activities taken into account Y = f(x1, x2, x3, x4, x5, x6,x7) Where, y=hours spent in criminal activities; x1 = wage for an hour spent in criminal activity; x2= hourly wage in legal employment; x3 = income other than from crime or employment; x4 = probability of getting caught; x5 = probability of getting convicted if caught, x6 = expected sentence if convicted and x7 = age

Example of economic models

5

Less formal economic model: A labour economist would

like to examine the effects of workers productivity on wage. In this case there is little need for formal economic theory. Basic economic understanding is sufficient for realizing that factors workers are paid commensurate with their productivity which in turn depends on factors such as education, experience and training. Thus, one can think of a model Wage = f (education, experience, training)

Economic to Econometric model

6

First, in each of the last two models f(.) needs to specified Second, the variables in each of these models which cannot be

reasonably observed needs to be dealt with These ambiguities inherent in an economic model are resolved by specifying a particular econometric model An econometric model for economic model 1: Crime =b0+b1wagem+b2othinc+b3freqarr+b4freqconv +b5avgsen+b6age+e An econometric model for economic model 2: Wage = b0+b1edu + b2exper +b3training +e Where the term e contains factors such as innate ability, quality of education, family background etc

Data
7

Often in empirical analysis we straight away start with the econometric

model and then various hypotheses of interest can be stated in terms of unknown parameters and go on refining the model Once the econometric model is specified, the requisite data is collected The econometric methods are used to estimate the parameters in the econometric model and to formally test the hypotheses of interest

Structure of Economic Data

8

Cross-section data set consists of a sample of individuals, households,

firms, cities etc taken at a given point of time. Sometimes data on all units may not correspond to precisely the same time period. An important feature of cross-sectional data is that they can often be assumed to be obtained from random sampling from an underlying population. But this assumption may not always be true.
Time series data set- consists of observations on a variable or several

variables over time. A key feature of this data that makes it difficult to analyze is that economic observations are rarely independent across time. Second, issue is the frequency of data.

Structure of Economic Data

9

Pooled Cross Sections data- some data have both cross-sectional and

time series features. For example, two cross sectional household surveys are taken in the USA, one in1985 and one in 1990 using the same survey. To increase our sample size, we can form a pooled cross section by combining the two years. Here the econometric model normally has year as a separate variable. This data is most often analyzed as a standard cross section , except that we often need to account for the secular differences in variables across time.
Panel Data set consists of a time series for each cross-sectional

member in the data set. Key feature of this data set which distinguishes it from pooled cross section is the same cross sectional units (households, firms etc) are followed over a given time period

Causality and Notion of Ceteris Paribus in Econometric Analysis

10

In most tests of economic theory, and certainly for evaluating policies,

the economists goal is to infer that one variable has a causal effect on another variable. Simply finding an association between two or more variables might be suggestive, but unless causality can be established, it is rarely compelling.
Second, the notion of ceteris paribus- which means other (relevant)

factors being equal- plays an important role in causal analysis in econometric modeling.

Discussion ahead
11

Against the backdrop, we start with cross section data set and focus on

explaining causal relationship between the variables under study Regression analysis

12