MPhil Econometrics
Programs Objectives
The Econometrics programs are meticulously designed to cultivate a deep understanding of both the theoretical underpinnings and practical applications of modern econometrics. Students will delve into a comprehensive range of essential topics, spanning fundamental econometric theory and applied techniques to specialized areas such as time series analysis, big data analysis, financial econometrics, panel data methods, micro and macro econometrics, Bayesian approaches, and non-parametric and semi-parametric methods. Beyond theoretical knowledge, the program places significant emphasis on the hands-on application of these concepts through targeted exercises and engaging seminars that address pertinent policy issues and empirical inquiries. Furthermore, the curriculum equips students with crucial skills in utilizing leading econometric and statistical software packages and fosters an awareness of diverse national and international data sources. To ensure a holistic and enriching learning experience, the program cultivates a competitive yet supportive environment that encourages effective learning and incorporates valuable co-curricular activities.
Eligibility criteria for MPhil Econometrics
- MA/MSc in Econometrics and Statistics/Economics/Statistics/Mathematics OR BS (4-year) in Economics/Statistics/Mathematics or equivalent degree.
- Minimum Grade and division will be followed as defined in “Admission, Registration and Examination Regulations for MPhil programmes”.
- Applicants will be selected on the basis of their performance in the admission test, interview and academic record.
Scheme of Studies of MPhil Econometrics
- Academic Program (MPhil Econometrics)
Program Structure
Total Credit Hours: 36
Course Work: 24
Thesis: 12
Duration: 2 Years (with the provision of a one-year extension)
Total Courses: 9
Core Courses: 6 (First Semester: 4, Second Semester: 2)
Optional Courses: 2 (Second Semester: 2)
Non Credit Course: 1 (Third Semester: 1)
Semester-wise Program Structure
Program Structure Semester Wise |
|||
1st Semester (Fall) |
2nd Semester (Spring) |
3rd Semester (Fall) |
4th Semester (Spring) |
ETS-600 Microeconomic Theory (3 credit hours) |
ETS-771 Applied Econometrics (3 credit hours) |
ETS-615 Research Methodology (Non credit Course) |
Thesis (6 credit hours) |
ETS-610 Macroeconomic Theory (3credit hours) |
ETS-638 Data Visualization (3 credit hours) |
||
ETS-620 Quantitative Foundation for Econometrics (3 credit hours) |
Optional I (3 credit hours) |
Thesis (6 credit hours) |
|
ETS-640 Econometric Methods (3 credit hours) |
Optional II (3 credit hours) |
||
12 Credits |
12 Credits |
6 Credits |
6 Credits |
- A student will qualify for thesis if he/she attains a minimum 3 CGPA in course work after completion of 2nd semester (excluding Research Methodology).
- any change is subject to approval from Board of Studies (BOS) where required.
Course list for PhD/MPhil
S. No. |
Course Code |
Course Name |
Credit Hours |
Course Type for PhD |
Course Type for MPhil |
1. |
ETS 600 |
Microeconomic Theory |
03 |
Deficiency |
Core |
2. |
ETS 610 |
Macroeconomic Theory |
03 |
Deficiency |
Core |
3. |
ETS 620 |
Quantitative Foundation for Econometrics |
03 |
Deficiency |
Core |
4. |
ETS 622 |
Sampling Design and Analysis |
03 |
Optional |
Optional |
5. |
ETS 624 |
Numerical Analysis and Stochastic Simulations |
03 |
Optional |
Optional |
6. |
ETS 626 |
Advanced Probability Theory |
03 |
Optional |
Optional |
7. |
ETS 630 |
Advanced Statistical Inference |
03 |
Optional |
Optional |
8. |
ETS 634 |
Big Data Analysis |
03 |
Optional |
Optional |
9. |
ETS 635 |
Asymptotic Theory and Simulations |
03 |
Optional |
Optional |
10. |
ETS 638 |
Data Visualization |
03 |
Deficiency |
Core |
11. |
ETS 640 |
Econometric Methods |
03 |
Deficiency |
Core |
12. |
ETS 641 |
Time Series Analysis |
03 |
Optional |
Optional |
13. |
ETS 643 |
Forecasting Methodology |
03 |
Optional |
– |
14. |
ETS 722 |
Financial Economics |
03 |
Optional |
Optional |
15. |
ETS 745 |
Agent Based Modeling |
03 |
Optional |
Optional |
16. |
ETS 770 |
Applied Econometrics |
03 |
Deficiency |
Core |
17. |
ETS 800 |
Panel Data Econometrics |
03 |
Optional |
Optional |
18. |
ETS 810 |
Financial Econometrics |
03 |
Optional |
Optional |
19. |
ETS 820 |
Spatial Econometrics |
03 |
Optional |
Optional |
20. |
ETS 830 |
Non-parametric and Semi Parametric Econometrics |
03 |
Optional |
Optional |
21. |
ETS 835 |
Bayesian Econometrics |
03 |
Optional |
Optional |
22. |
ETS 840 |
Micro Econometrics |
03 |
Core |
– |
23. |
ETS 845 |
Macro Econometrics |
03 |
Core |
– |
24. |
ETS 850 |
Multivariate Analysis |
03 |
Optional |
Optional |
25. |
ETS 855 |
Elements of Statistical Learning |
03 |
Optional |
– |
26. |
ETS 870 |
Static and Dynamic Optimization |
03 |
Optional |
Optional |
27. |
ETS 880 |
Operations Research |
03 |
Optional |
Optional |
28. |
ETS 890 |
Structural Equation Modeling |
03 |
Optional |
Optional |
29. |
ETS-895 |
Topics in Advanced Econometrics |
03 |
Core |
– |
30. |
ETS-615 |
Research Methodology |
00 |
– |
Core |
Course Descriptions:
CORE COURSES:
ETS-600 MICROECONOMIC THEORY [credits 3]
Pre Requisite: Nil
Course Outline:
Theory of Consumer Behaviour; Theory of Firm; Market Equilibrium; Uncertainty and Information Asymmetry. The theory of consumer behavior includes: Direct and Indirect Utility Functions, Derivation of Marshallian and Hicksian Demand Curves; Consumer Surplus. Theory of Firm includes constrained optimization of Production, Cost and Profit Functions; Derivation of Input Demand Functions, Returns to Scale, Perfect and Imperfect Market Competition. Game theoretic concepts are discussed with reference to Oligopolistic Markets.
ETS- 610 MACROECONOMIC THEORY [credits 3]
Pre requisite: Nil
Course Outline:
Introduction to Classical Economics-Utopian world of Demand and Supply, Quantity theory of money, Why supply and demand does not work in the labor market – Efficiency Wage Theories, Factors that led to Great Depression, Nonexistent demand and supply model, Household debt,Bubble in the assets market, Keynesian Economics,-Wage – Price rigidities and malfunctioning of demand – supply model, Role of money in economic activity, Government role as a leader in investment activities,Chicago plan and Islamic Chicago Plan.Post Keynesian Economics and the first Neo-Classical synthesis, Convergence and stability debate,Monetarists counter revolution, Redefining role of money, New classical economics, Rational expectations hypothesis, Policy irrelevance proposition, Macroeconomic modeling based on microeconomic foundations, New Keynesian Economics and the second Neo-Classical synthesis: The Era of Great Moderation, Rational expectations and micro foundations as norms in macroeconomics, Wrong perception of the role of money, Interest rate as monetary policy instrument despite its limited role, DSGE models and neglecting the distributional issues, , Inflation targeting regime, How did economists get it wrong, Misperception of the role of money: Werner’s theory, Limitations of interest rate targeting, Misuse of rational expectations hypothesis, Monopoly of private banks and money creation process, Explaining bubble as great moderation, Financial crisis and Great Recession, Fiscal austerity in Europe, Role of free trade in European crisis, Ideological battle in Macroeconomics.
ETS-620 QUANTITATIVE FOUNDATION FOR ECONOMETRICS [credits 3]
Pre requisite: Nil
Course Outline:
Econometric Modeling, Descriptive Study of Data, Probability, Random Variables and Probability Distribution, Random Vectors and Their Distribution, Functions of Random Variables The General Notion of Expectation, Stochastic Processes, Limit theorems, Introduction to Asymptotic Theory, Statistical Inference, Properties of Estimators, Estimation Methods, Hypothesis Testing and Confidence Regions, The Multivariate Normal Distribution, Statistical Models in Econometrics, The Gauss Linear Model, The Linear Regression Model- Specification, Estimation and Testing, The Dynamic Linear Regression Model, The Multivariate Linear Regression Model, The Simultaneous Equation Model.
Arbitrary Ranking, Sorting, Ranking and Percentiles Concept and importance of Sorting, Ranking and Percentiles , REPRESENTING: (Mean, Median and Mode), Mean, Median and Mode, Measures of Spread, and Outliers Various measures of spread are discussed like IQR Standard Deviation, Measures of Spread and Outliers, Boxplots Histograms Bivariate, Relationships , Comparison of Visual graphics. Probability, Random Variables and Probability Distribution, Random Vectors and Their Distribution,Functions of Random Variables The General Notion of Expectation, Stochastic Processes, Limit theorems, Statistical Inference, Properties of Estimators, Estimation Methods, Hypothesis Testing and Confidence Regions,Measures of Spread, and Outliers Various measures of spread are discussed like IQR Standard Deviation, The Introduction to Econometric Modelling, Statistical Models in EconometricsThe Gauss Linear Model, The Linear Regression Model- Specification, Estimation and Testing, The Dynamic Linear Regression Model,The . Random sampling, Bernoulli sequence, Discete Random Variable, Centinuom RV, Expectataive, Moments and MGF, Central Limit theorem.
ETS-638 DATA VISUALIZATION [credits 3]
Pre requisite: Nil
Course Outline:
Introduction Course Setup : What is data visualization? How can data be visualized, How can Data Visualization be used? When data visualization is suitable? Econometrics, Data Visualization and Data Science, Tools for data visualization for this course (RStudio and R library ggplot2),
- Explorative Data Analysis Start tutorials,
- R Graphics I, R Graphics II, ggplot2
- Which Chart to use When
- Visualising Categorical and Continuous data
- Time series visualization
- Scatter plots, residuals, regression discontinuity designs, nonlinearities
- Geospatial data visualization
- Advanced Charts: Tree map, Classification Trees, Heat maps etc.
- De-Clutter Graphs for Better Data Insights
- Making use of colors, facets, aesthetics, legends
- Interactive Data Visualization Using plotly/R shiny
- Dashboard Designs
- Telling Story With Data Visualization
Note: Additional resources like Excel for graphics can be used but main software to be used is R (ggplot2) as coding will help students in their data analytics in other courses as well. We shall mainly follow book Winston Chang and Nathan Yau (both use R language for data visualization).
ETS-640 ECONOMETRIC METHODS [credits 3]
Pre requisite: Nil
Course Outline:
Introduction, Stochastic Assumptions of Econometrics: Simple and Multiple Regression Analysis Ordinary Least Squares, Maximum Likelihood and Method of Moments Estimators of Parameters of the Classical General Linear Regression Model, Estimation of Non-Linear Regression Models. Properties Linear and Non-Linear Models Regression Model, Heteroscedasticity, Autocorrelation, Multicollinearity and Endogeneity: Structure, Causes, Consequences, Tests and Estimation; Structure and Assumptions of Generalized Regression Models. Generalized Least Squares (GLS) and Feasible GLS methods and Its Application, Two-Stage Least Squares (2SLS) and Instrumental Variables Least Squares (ILVLS) estimators; Likelihood Ratio, Lagrange Multiplier and Wald tests; Model Selection: Choice of Variables and Choice of Functional Form, Hausman test; Testing Between Nested and Non-Nested Models; Qualitative Response Models; Dummy variables, Structural Shifts, Seasonality, Tests of Structural Shifts and Model Stability, Splines functions; Pooled Time Series and Cross Section Data: Structure, Assumptions and Estimation Techniques; Dynamic Models Involving Pooled Data and GMM Estimation; Simultaneous Equations: Structure, Identification and Estimation; Seemingly Unrelated Regression Models: Structure, Assumptions and Estimation; Limited Dependent Variables: Linear and Non-Linear Probability Models for Bivariateand Multivariate Models, Data Censoring and Selectivity Bias, Bayesian Econometrics.
ETS 641 TIME SERIES ANALYSIS [credits 3]
Pre requisite: Nil
Course Outline:
Introduction of Time Series Analysis, Transformation of Variables, Decomposition Analysis, Spectral Analysis, Box-Jenkins Methodology; AR, MA, ARMA, ARIMA, Seasonal ARMA, and Seasonal ARIMA Models, Unit Roots Analysis, Multiple Time Series, Transfer Functions, Cointegration, Dynamic Specification, Distributed Lagged Models, Vector Autoregressive (VAR), Impulse Response Function, Testing of Structural Change, Causality Analysis, ARCH Models, Panel Unit Root And Panel Cointegration, Forecasting; Univariate and Cointegrated System, Testing Forecasting Accuracy, Exogeneity – Weak, Strong and Supper- Analysis
ETS- 770 APPLIED ECONOMETRICS [credits 3]
Pre requisite: Nil
Course Outline:
Estimation Methods; Maximum Likelihood and Generalised Method of Moments; Models of Consumption and Investment; Models Connecting Asset Market Data to Economic Aggregates and Models of the Underlying Sources of Economic Fluctuations; The Estimation of Demand and Supply Equations; Estimation of Production Relationship; Estimation of Pricing Equations in Finance and Labour Economics and Calibration of General Equilibrium Models, Monte Carlo Simulations and Computer Programming.
OPTIONAL COURSES
ETS- 622 Sampling Design and Analysis [credits 3]
Pre requisite: Nil
Course Outline:
Review of Basic Concepts of Random Sampling and its Types, Stratification, Two Way and Deep Stratification, Construction of Strata, Systematic Sampling, Area Sampling, Ratio and Regression Estimators, Comparison of Various Estimators, Two Phase Sampling, Probability Proportion to Size Sampling, Non Responses and Imputation, Theoretical Sampling.
ETS- 624 NUMERICAL ANALYSIS AND STOCHASTIC SIMULATIONS [credits 3]
Pre requisite: Nil
Course Outline:
General Issues in Simulation, Model Building; Bias-Variance Tradeoff; Model Selection; Fisher Information Matrix. Stochastic Simulations: Generating Random Variables, Simulating Normal, Gamma and Beta Random Variables. Generating Random Variables From Failure Rates. Simulating Multivariate Distributions, MCMC Methods and Gibbs Sampler, Simulating Random Fields. Comparison of Algorithms to Generate Random Variables. Resampling Methods. Variance Reduction. Discrete-Event Systems and Simulations. Simulation-Based Optimization; Regenerative Systems; Brief Introduction to SPSA. Simulation-Based Optimization by Gradient-Free Methods (FDSA And SPSA); Common Random Numbers. Simulation-Based Optimization by Gradient-Based Methods (IPA/LR and Sample Path). Markov chain Monte Carlo. Optimization Using Monte Carlo Methods, Simulated Annealing for Optimization. Solving Differential Equations by Monte Carlo Methods Input Selection and Optimal Experimental Design for Linear Models. Input Selection and Optimal Experimental Design for nonlinear Models. Statistical Methods for Selecting the Best Option Using Simulation Runs.
ETS- 626 ADVANCED PROBABILITY THEORY [credits 3]
Pre requisite: Nil
Course Outline:
Probability Review, Convergence of Sequences, Characteristics Function, Transformation of Random Variables, Discrete and Continuous Probability Models, Pearsonian System of Distributions, Cheybyclev-Hermetic Polynomials, Gram-Charlier Series, Order Statistics and Their Sampling Characteristics, Distribution of Extreme Values and Noncentral chi, t and F Distributions.
ETS-630 ADVANCED STATISTICAL INFERENCE [credits 3]
Pre requisite: Nil
Course Outline: Comparison of Point Estimators: The framework for parametric inference, Mean Square Error, Unbiased estimators, Sufficiency, Factorisation Theorem, Minimal sufficiency. Distribution Theory: Conditional distributions and expectations, Central Limit Theorem.Minimum variance unbiased estimation: Rao-Blackwell Theorem, Exponential Families, Lehmann-Scheffé Theorem.Likelihood, Fisher Information and the Cramér-Rao Inequality: The Efficient Score, Fisher Information, Cramér-Rao lower bound, Attainment of the Cramér-Rao lower bound, Multi-dimensional Cramér-Rao inequality. Maximum likelihood estimators: Elementary properties, Consistency and asymptotic efficiency. Hypothesis Testing: Definitions, The Neyman-Pearson lemma, Tests of composite hypotheses, Likelihood ratio tests. Confidence Sets: Relationship with hypothesis tests, pivotal quantities.
ETS-634 BIG DATA ANALYSIS [credits 3]
Pre requisite: Nil
Course Outline:
What Big Data Means? When Do You Have a Big Data Problem? Characteristics, Sources and importance of Big Data Analysis. Compare and contrast the roles of: data-at-rest processing, data-in-motion processing, data-warehouse processing, and contextual search. Tools available for Big Data Analytics. Ingesting and integrating data, Storage and computer platforms. Presentation and visualization: Understand the purpose of various types of data visualization, ranging from infographics to visual analytics, Apply design principles to design visualization techniques, Use visualization tools to perform visual analysis. Algorithms and analytics: Identify Big Data problems that require Statistical Techniques, Apply the Statistical Techniques correctly on Big Data Problems, Understand the properties of these techniques, and the role of assumptions, Interpret the conclusions properly, Programme in “R”, Neural nets, Support vector machines. Understand methods from machine learning: Classification and regression trees, decision trees and decision forests, Random forests, clustering and topic modelling, logistic regression and deep learning, matrix factorization and time series analysis &spatio-temporal event modelling, Boosting, Bagging, Spike and slab regression? Penalized regression (e.g., the lasso, lars, and elastic nets). Apply the methods in advanced techniques: text analytics, image and video analytics and recommendation, Apply the techniques in large scale use-cases. Security and privacy.
ETS-635 ASYMPTOTIC THEORY AND SIMULATIONS
Pre Requisite: Nil [credits 3]
Course Outline:
The purpose of this course is to enable students to understand what asymptotic theory is and how is it used to design and analyze the statistical tests and estimators. However, asymptotic could fail to perform for two reasons (a) asymptotic theory is the large sample theory and could not be very good in small/medium sizes (b) the asymptotic theory could be sometimes too complicated to be analytically solved. Simulations could serve as a substitute for the asymptotic theory where it fails to perform. The second half of the course is about simulation, where, the students will be taught how to solve econometric problems using simulation methods.
Asymptotic Theory
This part will cover selected chapters from William H Greene (Econometric Analysis), Jhonston and Dinardo (Econometric Methods) and Peter Kennedy (A Guide to Econometrics) including topics: Maximum likelihood principal and applications, Properties of maximum likelihood estimators, Wald, Lagrange Multiplier and Likelihood Ratio tests, Large sample theory, Central Limit theorem, Law of Large Numbers, Convergence in Probability, Convergence in Distribution, Convergence of Function of Random Variables, Large Sample Properties of Least Square, Instrumental Variables and GLS, More on Maximum Likelihood, Estimating Asymptotic Variance of Maximum Likelihood Estimator, 2 step maximum likelihood.
Simulations
This part will cover what is simulation? Simulating mean, median, mode and matching it with theoretical properties of the random variables, Central Limit Theorem: Verification by simulations. Properties of OLS using Monte Carlo simulations: Unbiasedness, and Consistency; biasedness in overs specified and underspecified models. Testing Correlation: Pearson and Rank Order Correlation, Computing Simulated Critical Values and Power of correlation tests, comparison of power of the two tests and choice of test. Introduction to MATLAB: How to write function and program files, loops, matrices, conditions, Using MATLAB to simulate unit root tests and cointegration tests, Introduction to R programing: comparison of features of MATLAB and R. Using built in packages of R
Helping Material: Excel Lecture Notes, MATLAB user manual, R-user manual
ETS-643 FORECASTING METHODOLOGY
Pre Requisite: Nil [credits 3]
Course Outline:
An introduction to different forecasting methods: Guessing, Extrapolation, Leading indicators, Surveys, Time-series models, Econometric systems. Forecasting in univariate processes: Stationary stochastic processes, Stochastic non-stationarity processes, deterministic non-stationarity, Forecasting fractionally integrated processes. Forecasting with non-linear models: Regime Switching Models SETAR and MS-AR models, Forecasting with ARCH errors. Forecasting in cointegrated systems: Systems for non-stationary variables, Forecasting based on the VMA representation, Forecasting based on the VAR. Forecasting using leading indicators. Forecasting with large-scale macroeconometric models: The economic system and forecasting models. Taxonomy of forecast errors: Open systems, Sources of forecast uncertainty: Parameter change, Model mis-specification, Estimation uncertainty, Variable uncertainty, Error accumulation, Large-scale model evaluation techniques. Combining forecasts: The combination of forecasts: The regression method, The variance-covariance approach, Serial correlation in the combining equation. Forecast encompassing: Encompassing, Forecast encompassing and conditional efficiency, Invariance of forecast encompassing tests. Testing forecast accuracy: Testing for predictive failure, Box-Tiao test: scalar case with multiple forecast periods, Box-Tiao test: a single horizon for a vector process, Box-Tiao test: multiple horizons for a vector process. Tests of comparative forecast accuracy: Encompassing tests, Variance-based tests. Forecasting practice on M3 competition.
ETS-722 FINANCIAL ECONOMICS
Pre Requisite: Nil [credits 3]
Course Outline:
Foundations of Risk Analysis; Measuring Risk; Application of Risk Analysis; the Portfolio Selection Problem; the Capital Asset Pricing Model; the Arbitrage Pricing theory; Common Stocks; Preferred Stocks; Bonds; Capital Structure theories; the goal of the Firm; the Economic Evaluation of Investment Proposals; the traditional Mundell Fleming Model; the Dynamic- Optimizing model with Price Flexibility; Intertemporal Model with Price Stickiness; Currency Crises; External Crises: Fiscal Policies and Taxation in the Open Economy; International Capital Flows under Asymmetric Information; and International Growth Convergence.
Note:
ETS 722: Financial Economics is the optional course offered in Department of Economics as E 722: Financial Economics.
ETS-745 Agent Based Modeling
Pre Requisite: Nil [credits 3]
Course Outline:
Description: This course is designed to understand wide variety of complex adaptive systems using agent based modelling. During the course, power of ABM in understanding the real world behaviour amenable to complex system analysis will be explored. This course will help students to learn studying economic and social phenomenon through ABM.NetLogo programming language which is developed at Northwestern University will be used for building ABM. No programming background/knowledge is required for student to register the course.
Why do we need to understand agent Based modelling.What Is Agent-Based Modeling?Creating Simple Agent-Based Models, Complex Adaptive Systems, Introduction, logic and need of Modelling, Exploring and Extending Agent-Based Models, Creating Agent-Based Models, The Components of Agent-Based Modeling, Analyzing Agent-Based Models, Verification, Validation, and Replication, Advanced Topics and Applications, Sensitivity, Uncertainty, and Robustness Analysis, Tragedy of the Commons, Networks, Diffusion of Innovation, Fads and Fashion, Collective Action, Labor market Job search and wage distribution, Growth Theories, Stock Market.
ETS-771 TOPICS IN ADVANCED ECONOMETRICS [credits 3]
Pre requisite: Nil
Course Outline:
Introduction to Large-Sample (Asymptotic Theory), Maximum Likelihood Estimation, and Generalized Method of Moments.Various Micro-Econometric Models, Including Discrete Choice, Panel Data, and Duration Models, Bootstrapping, Kernal Estimation.
ETS-800 PANEL DATA ECONOMETRICS [credits 3]
Pre requisite: Nil
Course Outline:
Introduction to Panel Data, One-Way Error Component Regression Model, Two-Way Error Component Regression Model, Test of Hypotheses with Panel Data, Heteroscedasticity and Serial Correlation in the Error Component Model, Seemingly Unrelated Regressions with Error Components, Simultaneous Equations with Error Components, Dynamic Panel Data Models, Unbalanced Panel Data Models, Panel Unit root, Panel Cointegration.
ETS-810 FINANCIAL ECONOMETRICS [credits 3]
Pre requisite: Nil
Course Outline:
Understanding Financial Data, Asset Returns and their Empirical Properties, Linear Regression Tests of Financial Models, Efficient portfolio and Capital Asset Pricing Model, Multifactor Pricing Models, Intertemporal Equilibrium and Stochastic Discount Models, Simulation Methods for Financial Derivatives, Linear Time Series Methods, An Introduction to Volatility, Risk and Volatility Models, Value at Risk, ARCH Models, GARCH and EGARCH Models, Forecast and Management of Market Risks, Modeling Long-Run Relationships in Finance, Trading Strategies and High Frequency Data Review.
ETS-820 SPATIAL ECONOMETRICS [credits 3]
Pre requisite: Nil
Course Outline:
Introduction to spatial econometrics: Spatial Econometrics, Spatial Dependence, Spatial Heterogeneity, Linear Regression Model with Spatial Data, Spatial Autoregressive Models: First-Order Spatial AR Model, Mixed Autoregressive Model, Spatial Error Model, General Spatial Model, Bayesian Spatial Autoregressive Models: Bayesian Regression Model, Bayesian FAR Model, other Spatial Autoregressive Models, Locally Linear Spatial Model: Spatial Expansion, DARP Models, Non-Parametric Locally Linear Models, Limited Dependent Variable Models: Gibbs Sampler, Heteroscedasticity Models, VAR and Error Correction Models.
ETS-830 Non-Parametric and Semi Parametric Econometrics [credits 3]
Pre requisite: Nil
Course Outline:
The Empirical Distribution Function, Likelihood, Influence Functions, Jackknife and Bootstrap Confidence Intervals and Tests, Permutation Tests, Rank Tests, Bias-Variance Tradeoff, Cross-Validation, Kernel Density Classification and Estimation, Curse Of Dimensionality, Nonparametric Regression, Basis Expansions, Splines, and Penalized Regression, Quantile Regression, Nonparametric Approaches to Multiple Regressions, Generalized Additive Models, Nonparametric Analysis of Longitudinal Data.
ETS-835 BAYESIAN ECONOMETRICS
Pre Requisite: Nil [credits 3]
Course Outline:
The overall aim of this subject is to familiarize students with essential concepts and techniques used in Bayesian inference. The course will provide students with the necessary programming skills to implement Bayesian estimation and inference for econometric model using suitable softwares. The formal course description is:
Foundations of Probability, Bernoulli &Binomial RV’s, Conventional Inference for Surveys, From Data to Densities, Prior to Posterior updating in Beta-Binomial Model, Assessment of Binomial Models, Bayesian Econometrics Multiple Matches, Match Binomial Model to Real World, Bayesian Econometrics Testing Independence, Bayesian Econometrics Chi-Square Test, Review of Normal Distribution, Bivariate Normal Distribution, Bayesian calculations for normal data, normal prior, Bayesian Calculations with Normal-Gamma Priors, Fundamental Formulas for Bayesian & Conventional Inference with IID Normal, Principles for Applications of Normal Inference on Real Data, IID Normal Inference with Real Data, Bayesian inference using IID Normal Models for real Data, Introduction to Empirical Bayes, Empirical Bayes for Panel IID Normal Data, Empirical Bayes & Stein Estimation, Empirical Bayes on Recession Probabilities and Fire Alarms, Empirical Bayes Quality Control, Empirical Bayes in Regression Models, Hierarchical Bayes and Gibbs Sampler.
ETS-840 MICRO ECONOMETRICS [credits 3]
Pre requisite: Nil
Course Outline:
Introduction to Micro-Econometric Data Structures, Data Generating Process, Incentives and Errors in Producing Data and Recording Observations, Observational Vs. Experimental Data and Estimation of Causal Effects. Discrete Choice Models, Probit and Logit. Multinomial Models, Accounting for Heterogeneity. Bayesian Estimation: Gibbs Sampling, Metropolis-Hastings Sampling, Estimating Mixed Logit. Count Models, Censored and Truncated Models, Duration Models, Quantile Regression, Variance Estimation and Power. Bootstrapping, Non-parametric Regression and Matching , Heckman Bivariate Normal Selection Model , Instrumental Variables Models , Regression Discontinuity Designs , Difference-in-Differences and Panel Data Models, Econometric Evaluation Methods, Application of Household budget, Labour Force, Agriculture and industrial Data.
ETS-845 MACROECONOMETRICS [credits 3]
Pre Requisite: Nil
Course Outline:
Time series properties of macro data, time series models, filtering and applications to business cycle. Simultaneous equation model, application to equilibrium model of demand and supply, wage- price inflation, Keynesian model. Vector Auto-Regressions and impulse responses, with applications to business cycle, monetary policy analysis and the dynamics of aggregate demand and supply shocks. Applications of the structural VAR-X for impulse response functions to structural shocks, multiplier analysis of the exogenous variables, forecast error variance decomposition. Structural breaks and model selection, applications to Non-Accelerating Inflation Rate of Unemployment (NAIRU), technology and monetary policy shocks. Structural estimation of macroeconomic models. Time series models with latent variables: economic implication of Kalman Filter toleading indicators. Forecasting and structural breaks and applications to the Phillips curve, forecasting of GDP growth and inflation dynamics. Multivariate tests for unit roots and cointegration: Application to Stochastic trends and economic fluctuations.
ETS-850 MULTIVARIATE ANALYSIS [credits 3]
Pre requisite: Nil
Course Outline:
Introduction to Multivariate Methods & Fundamental Concepts, Multivariate Normal Distribution Theory, Distribution of Linear Function of Normal Variates, Distribution of Quadratic Forms, Wishart Distribution, Hotelling’s T2 distribution, Confidence Regions and Simultaneous Confidence Intervals, Hypothesis Testing, MANOVA, Likelihood Ratio Test, Principle Component Analysis: Objectives, Analysis, Factor Analysis: Principle Factor Analysis , Canonical Correlation Analysis: Mathematical Development and Analysis, Discriminant Analysis: Estimation, Fisher’s Linear Discriminant Function, Probabilities of Misclassification, Cluster Analysis: Probabilistic Formulation, Hierarchical Methods: Single Linkage, Complete Linkage, Average Linkage.
ETS-625 ELEMENTS OF STATISTICAL LEARNING [credits 3]
Pre Requisite: Nil
Course Outline:
Introduction to Modern Statistical Learning Approaches, Summary of different methods we will cover in the course, what is Statistical Learning?, Inference vs. Prediction, Supervised vs. Unsupervised Learning Problems , Regression vs. Classification, Introduction to R, Basic Commands, Graphics, Indexing Data, Loading Data, Assessing the Accuracy of a Statistical Learning Method, Less Flexible vs. More Flexible Methods, Bayes Classifier, Bias/Variance ideas, Review of Linear Regression, Linear Regression, Logistic Regression, Using the Logistic Function for Classification, Linear Discriminant Analysis, Logistic Regression and LDA, Resampling Methods (Finite Sample Theory), The Cross-Validation and the Bootstrap (Finite Sample Theory), kNN, Best Subset Regression, Shrinkage and Dimension Reduction Methods, Shrinkage Methods, General Linear Methods, Generalized Additive Models, Polynomial Regression, Splines and GAM, Tree Methods, Bagging and Boosting, Tree Methods, Clustering Methods.
ETS- 870 STATIC AND DYNAMIC OPTIMIZATION [credits 3]
Pre requisite: Nil
Course Outline: Basic mathematical tools, integration and differential equations, Qualitative theory, Control theory, Ramsey problem of optimal consumption, Dynamic programming, Lucas’ model of endogenous growth, Stochastic models in discrete time, Discrete-time optimization, Overlapping-generations, Real-business-cycles, Stochastic models in continuous time, Stochastic differential equations and rules for differentials, Merton’s model of growth under uncertainty, Stochastic dynamic control problems, Optimal saving under uncertainty.
ETS-880 OPERATIONS RESEARCH [credits 3]
Pre requisite: Nil
Course Outline:
Introduction; Linear programming and modelling; Simplex method; Sensitivity Analysis; Decision analysis; Game theory; Queuing systems; Optimization theory; Post-optimal analysis; Dynamic programming; Network Optimization models: Critical Path Method (CPM), PERT; Project Management with PERT/CPM; Simulation; Planning over Time, Uncertainty and Forecasting; Markov Decision Process; Operations Research Applications.
ETS-890 STRUCTURAL EQUATION MODELLING [credits 3]
Pre requisite: Nil
Course Outline:
Fundamentals of Structural Equation Modeling: Basic concepts, Latent versus observed variables, Exogenous versus endogenous latent variables, The factor analytic model, The full latent variable model, General purpose and process of statistical modeling, The general structural equation model, Symbol notation, The path diagram, Structural equations, Nonvisible components of a model, Basic composition, The formulation of covariance and mean structures.Path Analysis: Introduction, Path Diagrams, Rules for Determining Model Parameters, Parameter, Estimation, Parameter and Model Identification, Model-Testing and -Fit Evaluation, Example Path Analysis Model, Modeling Results, Testing Model Restrictions in SEM, Model Modifications. AMOS: Getting to Know the AMOS Program, Structure of Input Files for SEM Programs, Introduction to the AMOS Notation and Syntax, Introduction to the AMOS Notation, Introduction to the AMOS Notation and Syntax. Confirmatory Factor Analysis: What Is Factor Analysis? Factor Analysis Model, Identification, estimation, Model Evaluation, Modeling Results, and Testing Model Restrictions: True Score Equivalence. Structural Regression Models: What Is a Structural Regression Model? An Example Structural Regression Model, Modeling Results, Factorial Invariance across Time in Repeated Measure Studies. Latent Change Analysis: Measuring change in individual growth over time: The general notion, The hypothesized dual-domain LGC model, Modeling intra individual change, Modeling inter-individual differences in change, Testing latent growth curve models: A dual-domain model, The hypothesized model, Selected AMOS output: Hypothesized model, Testing latent growth curve models: Gender as a time-invariant predictor of change.Mediation : Introduction, Applications of the Mediation Model, Single Mediator Model, Single Mediator Model Details, Multiple Mediator Model, Path Analysis Mediation Models, Latent Variable Mediation Models, Longitudinal Mediation Models, Multilevel Mediation Models, Mediation and Moderation, Mediation in Categorical Data Analysis, Computer Intensive Methods for Mediation Models, Causal Inference for Mediation Models. Moderation: Introduction, Applications of the Moderation Model, Estimation, interpretation. MIMIC Modeling: Multiple Indicators Multiple Causes (MIMIC)model involves using latent variables that are predicted by observed variables. Bootstrapping as an aid to non-normal data: Basic principles underlying the bootstrap procedure, Benefits and limitations of the bootstrap, Procedure, Caveats regarding the use of bootstrapping in SEM Modeling with AMOS Graphics, The hypothesized model, Characteristics of the sample, Applying the bootstrap procedure, Selected AMOS output, Parameter summary, Assessment of normality, Statistical evidence of non-normality, Statistical evidence of outliers, Parameter estimates and standard errors, Sample ML estimates and standard errors, Bootstrap ML standard errors, Bootstrap bias-corrected confidence intervals.
ETS- 615 RESEARCH METHODOLOGY
Pre Requisite: Nil [credits 3]
Course Outline:
This course will provide an opportunity for participants to establish and advance their understanding of research through critical exploration of problem in econometrics, and the ways to resolve them. The course will discuss how to do select the appropriate topic for thesis, how to do the literature review, what the common mistakes are in econometric research and how the mistakes could be avoided. The course will comprise lectures and detailed presentation by the students about their research topics. The students would have to produce a presentable research proposal by the end of semester and they would be evaluated based on their written research proposal. The major themes discussed during the course would be Module 1: Selection of Research Topic: Selecting an appropriate topic for research, How to do literature review, Common mistakes in literature review, What is plagiarism and how to avoid it, Research ethics. Module 2: Problems with Standard Econometric Methodology: Axiom of correct specification, Axiom of Correct Specification and the Growth Regressions, What does the axiom of correct specification has to say about this regression? Misspecification analysis, Alternative Strategies Using Causal Chains, Interpreting Regression and Axiom of Correct Specification, How policies are constructed? Hendry’s methodology and Methods of Model Comparison, The misconception of learning from data, Observational and Casual Relationship, Exploratory Data Analysis, Real versus nominal Econometrics. Module 3: Methodological Mistakes and Econometric Consequences: The Rise and Fall of Logical Positivism, Kantian background to logical positivism, Errors Due to Misunderstanding of Scientific Methodology, Econometric Methodology, An Attitude Problem: Technological Growth, The Forecast Competitions, Finding patterns versus looking for clues, Tools to fit anything, Failure of Hendry’s Methodology, Realist Methodology: Inferring Structure from Clues, Surprising Versus Strong Correlations, Using Clues to Uncover Causal Structure
Module 4: Learning To Reason with Numbers: Comparison between two Groups, How to Make Groups Comparable, Virtues of Randomization, Polio epidemic Data, Experiment of National Foundation for Infantile Paralysis (NFIP), Alternative to Avoid Problems with NFIP, Dangerous to Control the Non- Randomized Study, Historical Controls, Triple Blind Studies