This course provides learners with foundational and advanced econometric theory, equipping them with robust tools for economic data analysis. It will develop the quantitative skills from classical regression fundamentals to advanced estimation techniques to learners gaining them competence necessary to specify, estimate, test, and interpret econometric models enabling them conduct rigorous economic research, evaluate policy interventions, and contribute meaningfully to applied economic analysis, bridging the gap between economic theory and real-world empirical research.

CLO 1: Describe and critically explain fundamental econometric principles, classical assumptions, and data analysis tools

CLO 2: Appraise economic information and select appropriate econometric tools and techniques of analysis

CLO 3: Apply econometric methodologies to specify, estimate, and validate models of real-world economic phenomena

CLO 4: Evaluate econometric output to interpret economic relationships, forecast outcomes, and inform policy decisions

Foundations of Econometrics and Methodology: Nature and scope of econometrics; the methodology of econometrics (economic theory, mathematical model, econometric specification, estimation, forecasting and policy); types of data (cross-sectional, time series, panel); introduction to statistical software for econometric analysis. Correlation and Regression Analysis: Measures of association; Pearson and Spearman correlation coefficients; simple linear regression; -specification, OLS estimation, goodness-of-fit (R²), hypothesis testing on coefficients, confidence intervals, and prediction. The Multiple Linear Regression Model (Three Variables): Extension to three-variable OLS model; partial regression coefficients; multiple R² and adjusted R²; F-tests for overall model significance; partial F-tests; interpretation of coefficients with controlled variables. Gauss-Markov Theorem and BLUE Estimate: Classical linear regression assumptions (CLRA); proof that OLS is the Best Linear Unbiased Estimator (BLUE) under the Gauss-Markov conditions; properties of OLS estimators; -unbiasedness, efficiency, and consistency; implications of assumption violations for estimator properties. The Multivariate Linear Regression Model and Violation of Assumptions (General Case): Matrix notation for the general linear model; OLS estimation in matrix form; heteroscedasticity;- causes, detection (Breusch-Pagan, White, Goldfeld-Quandt tests), consequences, and remedies (WLS, robust standard errors); autocorrelation;- causes, detection (Durbin-Watson, Breusch-Godfrey tests), consequences, and remedies; multicollinearity;- nature, detection (VIF, condition index), consequences, and remediation strategies. Analysis of Qualitative Independent and Dependent Variable Models (Dummy Variable Analysis): Incorporation of qualitative variables as regressors; binary, ordinal, and multiple-category dummies; the dummy variable trap; interaction terms and slope differentials; structural change and the Chow test; analysis of covariance (ANCOVA). Extensions for Limited Dependent Variables: Linear probability model (LPM) and its limitations; Logit and Probit models; -specification, maximum likelihood estimation, marginal effects, and model evaluation; ordered and multinomial Logit/Probit; Tobit model for censored data; count data models (Poisson regression). Simultaneous Equations Systems (SES): Structural and reduced forms; the identification problem; -order and rank conditions; recursive and non-recursive systems; endogeneity and simultaneity bias; Indirect Least Squares (ILS); application to supply-and-demand and macroeconomic models. Instrumental Variables (IV) & Two-Stage Least Squares (2SLS): Motivation for IV estimation; properties of valid instruments (relevance and exogeneity); IV estimator derivation; 2SLS procedure; first-stage F-statistics and weak instrument tests; Hausman endogeneity test; over-identification tests (Sargan-Hansen). Distributed Lag Models and Dynamic Specification: Finite and infinite distributed lag models; Koyck transformation; Almon polynomial lags; autoregressive distributed lag (ARDL) models; error correction models (ECM); Granger causality; cointegration concepts and the Engle-Granger approach. Advanced Estimation Techniques: Generalised Least Squares (GLS) and Feasible GLS (FGLS); Maximum Likelihood Estimation (MLE); -principles, likelihood functions, and properties (consistency, asymptotic efficiency); Generalised Method of Moments (GMM);- moment conditions, optimal weighting matrix, and applications; comparison of estimators across contexts.