Skip to the content

Useful for UGC NET · CSIR NET · ASRB NET · ISS

On this page
  1. Welcome to Econometrics
  2. Learning Outcomes
  3. Units in this Course
  4. Notation Used Throughout
  5. Recommended Textbooks
  6. References & Companion Tools

Welcome to Econometrics

This is the complete study package for Econometrics — the bridge between economic theory, mathematical statistics, and real-world data. The course covers the nature of econometrics and economic data, simple and general linear regression models, heteroscedasticity, multicollinearity, and autocorrelation. Every concept is illustrated with two worked examples.

Pre-requisite: Statistical Methods (correlation and regression), Inferential Statistics (the \(t\), \(F\) and \(\chi^2\) tests), Continuous Distributions (the Normal in particular), and ideally R Programming for hands-on work.

Learning Outcomes

  1. Understand what econometrics is, the types of economic data, and the steps in an empirical economic study.
  2. Build and estimate two-variable and multiple linear regression models; state and prove the Gauss–Markov theorem.
  3. Use \(R^2\), ANOVA and \(t\)-tests to assess regression model quality; diagnose and correct heteroscedasticity.
  4. Detect multicollinearity using VIF and tolerance; apply remedies (ridge regression, dropping variables, transformation).
  5. Detect and treat autocorrelation using the Durbin–Watson test; estimate the AR(1) coefficient.

Units in this Course

UNIT 1

Basic Econometrics

Nature and concept of econometrics; types of economic data — cross-section, pooled cross-section, time-series, paired data; steps in empirical analysis; the econometric model.

 UNIT 2

Models & Estimation

Two-variable linear regression; OLS; Gauss–Markov theorem; partial & multiple correlation; general linear model; BLUE properties.

 UNIT 3

Heteroscedasticity

Significance tests; \(R^2\) and ANOVA; concept, consequences, detection and correction of heteroscedasticity; specification error; errors of measurement.

 UNIT 4

Multicollinearity

Concept and consequences; detection methods; variance inflation factor (VIF) and tolerance; methods of reducing multicollinearity.

 UNIT 5

Autocorrelation

Disturbance-term assumptions; consequences of autocorrelated disturbances; Durbin–Watson test; estimation of AR(1) autocorrelation coefficient.

 PRACTICAL

Practical / Lab Exercises (10)

OLS estimation, residual diagnostics, \(R^2\), heteroscedasticity tests (White, Breusch–Pagan), VIF computation, Durbin–Watson, Cochrane–Orcutt — by hand and in R.

 REFERENCE

Official Syllabus

Course outline, textbooks, references and exam blueprint.

Notation Used Throughout

SymbolMeaning
\(Y_i\)Dependent (regressand) variable for the \(i\)-th observation.
\(X_i\)Independent (regressor) variable.
\(\beta_0, \beta_1\)Population regression coefficients (intercept and slope).
\(\hat\beta_0, \hat\beta_1\)OLS estimators of the coefficients.
\(u_i\)Disturbance / stochastic error term; \(u_i \sim N(0,\sigma^2)\) under classical assumptions.
\(\hat u_i = e_i\)OLS residual: \(Y_i - \hat Y_i\).
\(\boldsymbol\beta, \mathbf X, \mathbf Y\)Matrix notation: \(\mathbf Y = \mathbf X\boldsymbol\beta + \mathbf u\).
\(R^2\)Coefficient of determination.
VIF\((X_j)\)Variance Inflation Factor of regressor \(j\).
\(d\)Durbin–Watson statistic.

References & Companion Tools

Why econometrics? Pure statistics tells you what the data says; economic theory tells you what the data should say. Econometrics is the discipline that puts them in conversation — quantifying economic relationships, testing economic theories, and forecasting policy outcomes.
← Back to Course Hub Start with Unit 1 →

Next course in learning order: Multivariate Analysis Models & multivariate