This course equips doctoral students with advanced theoretical and applied econometric skills for rigorous economic research and policy analysis. It emphasizes identification, estimation, inference, causal reasoning, computation, replication, and scholarly communication so that learners can specify, estimate, interpret, critique, and communicate sophisticated econometric models using real-world data and reproducible workflows.

CLO 1:Evaluate advanced econometric models by examining their assumptions, identification conditions, theoretical properties, empirical applications, and limitations.

CLO 2: Apply advanced econometric techniques in STATA and R, including dynamic panel estimation, cointegration analysis, causal inference methods, and nonlinear limited dependent variable models, using real-world datasets.

CLO 3: Analyse econometric identification strategies, robustness, validity, and suitability for addressing endogeneity, dynamics, nonlinearity, and causal inference problems.

CLO 4 Design research-ready econometric analysis by integrating data management, reproducible workflows, rigorous econometric reasoning, and policy-relevant reporting.

Foundations of Econometric Theory – Probability approach to econometrics, convergence concepts, laws of large numbers, central limit theorems, large-sample reasoning, identification, specification, and misspecification.

Generalized Linear Models and Estimation – Maximum likelihood estimation, score and Hessian, information matrix, LR/Wald/LM tests, GMM, over-identification tests, and bootstrap or simulation-based inference.

Endogeneity and Identification – Instrumental variables, 2SLS, LIML, simultaneous equation systems, weak instruments, and robust identification logic.

Panel Data Econometrics – Pooled OLS, fixed effects, random effects, first differences, Hausman testing, dynamic panel models, and practical issues in panel-data analysis.

Time Series Econometrics I – Univariate Foundations – Stationarity, autocorrelation, AR, MA, ARMA, ARIMA, differencing, and the basic logic of univariate time-series modelling.

Time Series Econometrics II – Multivariate Systems, Cointegration and Forecasting – VAR, lag selection, Granger causality, cointegration, VECM, impulse responses, variance decomposition, and forecasting.

Nonlinear and Limited Dependent Variable Models – Logit, probit, multinomial and ordered models, Tobit, truncation, and sample-selection models.

Causal Inference in Econometrics – Potential outcomes, treatment effects, propensity score matching, difference-in-differences, regression discontinuity, and threats to validity.

Frontiers in Econometrics – Bayesian econometrics, simulation-based methods, structural modelling, robustness, replication, reproducibility, and workflow transparency.

Applied Econometric Practice – Research replication, data management, reproducible workflow, interpretation, communication of findings, and a research-ready mini-project.