Description and contextualization of the subject

Econometrics is concerned with how to use statistical methods and procedures for economic

data. Econometrics techniques have been increasingly used in macroeconomics and applied

microeconomics.



The goal of this course is to provide students with advanced knowledge and tools to conduct their own empirical research in economics, to evaluate government and business policies, to perform forecasting and to use the computer as a tool for regression analysis. Students will be provided with the required tools for the appropriate data analysis they will take on in the different courses within this master program, as well as in their final master thesis.



This course emphasizes both the theoretical and the practical aspects of statistical analysis, focusing on techniques for estimating econometric models of various kinds and for conducting tests of hypotheses of interest to economists. The goal is to help you develop a solid theoretical background in advanced level econometrics, the ability to implement the techniques and to critique empirical studies in economics.



We will develop techniques to handle common econometric problems that arise when working with economic data including heteroskedasticity, autocorrelation, endogeneity, selection bias, misspecification, and measurement errors. We will expand the kinds of data we can analyse by exploring the topics of panel data and binary response.



The course is designed to train students to explore a dataset, write code to analyze relationships and to test hypotheses about some economic phenomenon. Working with data and implementing econometric software is integrated into every aspect of the course including lecture, problem sets and exams. Students are introduced to the statistical package Stata and R. Different types of empirical data sets are introduced, and students are shown how to apply various estimation techniques and testing procedures in practice.



After completion of this course students should be able to perform tasks of data collection, modelling of econometrics relationships, estimating and testing of the model, and interpreting and using the estimation results.



While the course is ambitious in terms of its coverage of technical topics, equal importance is attached to the development of an intuitive understanding of the material that will allow these skills to be utilized effectively and creatively, and to give participants the foundation for understanding specialized applications through self-study with confidence when needed.

Learning outcomes of the subject

The expected learning outcomes include familiarization with methods of data analysis including estimation methods and regression analysis, ability to communicate the understanding of data analysis, understanding how economic theories may be used to create testable hypotheses using empirical data and econometrics, examination of the limitations of econometrics and their applications on society. Moreover, the students will learn how to apply statistical-econometric methods for analysis and evaluation of economic policies at a public or private, local, national or international level. They will be also able to carry out empirical work and to choose appropriate statistical-econometric software to carry out quantitative analysis to be presented in high quality professional reports.

Ordinary call: orientations and renunciation

The final grade for this course will be based on homework exercises students will have to do during the whole class period, on final examination, as well as on individual’s student class participation. Therefore, grades for the course will be based on:



- Homework (4 problem sets): 15%

- Class participation: 5%

- Final exam: 80%



Homework



There will be four problem sets in total. Students may work in groups, but each member of a group should submit her own write-up. In the case of group collaboration, you are required to write down the names of your group members. The group size should not exceed three students.



The evaluation will preferably be in-classroom. If this is not possible, the final exam will be taken using the services available at Egela. The student will have a limited time to download the final exam form from Egela and upload the solution to that platform (preferably in pdf and in any case in a perfectly legible format to enable evaluation). This exam is individual, so in order to ensure this aspect of the exam the use of webcam and an oral interview for verification of the answers might be requested.

Extraordinary call: orientations and renunciation

Grades for the course will be based on:



- Homework (4 problem sets): 20%

- Final exam: 80%



Homework



There will be four problem sets in total. Students may work in groups, but each member of a group should submit her own write-up. In the case of group collaboration, you are required to write down the names of your group members. The group size should not exceed three students.



The evaluation will preferably be in-classroom. If this is not possible, the final exam will be taken using the services available at Egela. The student will have a limited time to download the final exam form from Egela and upload the solution to that platform (preferably in pdf and in any case in a perfectly legible format to enable evaluation). This exam is individual, so in order to ensure this aspect of the exam the use of webcam and an oral interview for verification of the answers might be requested.

Temary

1. Regression Analysis in Practice



1.1. Multicollinearity

1.2. Heteroskedasticity

1.3. Autocorrelation

1.4. Robust standard errors

1.5. Numerical methods for ML estimation



2. Specification and measurement errors, IV Estimation



2.1. The attributes of a good model

2.2. Types of specification errors

2.2.1. Omitting a relevant variable: "Underfitting"a model

2.2.2. Inclusion of irrelevant variables: "Overfitting"a model

2.3. Instrumental variables estimation and Two Stage Least Squares (2SLS)

2.3.1. Instrumental variables estimation

2.3.2. Two Stage Least Squares

2.3.3. IV solutions to errors-in variables problems

2.4. Testing for endogeneity

2.5. Testing overidentification restrictions (exogeneity of instruments)





3. Qualitative Dependent Variables



3.1. Introduction

3.2. Binary outcomes

3.2.1. The linear probability model

3.2.2. A latent variable model for binary variables

3.2.3. ML estimation

3.2.4. Interpretation

3.2.5. Hypothesis testing

3.2.6. Goodness of fit

3.3. Ordinal Outcomes: Ordered Logit and Ordered Probit

3.3.1. A latent variable model for ordinal variables

3.3.2. ML estimation

3.3.3. Interpretation

3.4. Nominal Outcomes: Multinomial Logit

3.4.1. The MNLM as a probability model

3.4.2. The MNLM as a Discrete Choice Model

3.4.3. ML estimation and testing

3.4.4. Interpretation

3.4.5. The conditional logit model





4. Sample selection models



4.1 Censoring versus Truncation

4.2 Truncated and Censored Distribution

4.3 The Tobit Model for censored outcomes

4.4 Problems introduced by censoring

4.4.1 Analyzing censored data

4.4.2 Analyzing a truncated sample

4.5 Estimation

4.5.1 Estimation with censored data

4.5.2 Estimation with truncated data







4.6 Interpretation

4.7 Models for sample selection

4.8 Specification Issues in Tobit Models





5. Panel data analysis



5.1 Introduction

5.2 Pooling Independent Cross Sections across Time

5.3 Two-Period Panel Data Analysis

5.4 Fixed Effects Estimation

5.5 Random Effects Models

5.6 The Correlated Random Effects Approach





6. Regression Models for Count Data

6.1 The Poison distribution

6.2 The Poisson regression model

6.3 The Negative Binomial regression model

6.4 Comparison among count models

Bibliography

Compulsory materials

Mariel, P. (2023). Regression Analysis in Practice. Lecture notes UPV/EHU



Mariel, P. (2023). Specification and measurement errors, Instrumental Variables (IV) estimation. Lecture notes. UPV/EHU Mariel, P. (2023). Qualitative Dependent Variables. Lecture notes. UPV/EHU



Mariel, P. (2023). Sample Selection Models. Lecture notes. UPV/EHU Mariel, P. (2023). Panel Data. Lecture notes. UPV/EHU



Mariel, P. (2023). Regression Models for Count Data. UPV/EHU

Basic bibliography

Wooldridge, J. M. (2015). Introductory econometrics: A modern approach. Cengage learning.



Wooldridge, J. M. (2010). Econometric analysis of cross section and panel data. MIT press.

In-depth bibliography

Gujarati, D. N. (2021). Essentials of econometrics. Sage Publications







Verbeek, M. (2017). A guide to modern econometrics. John Wiley & Sons.

Journals

Econometric Reviews



Empirical Economics Journal



International Journal of Forecasting



Journal of Applied Econometrics



Journal of Business and Economic Statistics



Journal of Econometrics



Journal of Economic Dynamics and Control



Journal of Forecasting



Oxford Bulletin of Economics and Statistics



Review of Economics and Statistics1



Review of Economic Studies

Links

Basque Institute of Statistics (EUSTAT): http://www.eustat.eus/



National Institute of Statistics (INE): http://www.ine.es/



European Institute of Statistics (EUROSTAT): http://ec.europa.eu/eurostat



Spanish Association of Statistics and Operations Research: http://www.seio.es/



International Statistical Institute: http://isi-web.org/