Econometrics

about this course

Econometrics is where theory meets data. Based on statistics and probability theory, econometrics is the branch of economics that uses economic data to test theoretical relationships, estimate their size and make predictions. As a first course in data analysis, this course will prepare the student for further study of econometrics and for other data analysis fields (e.g. machine learning).

This course builds on the measures and hypothesis tests that you learned in statistics, using linear regression to measure each source of influence on an dependent variable. Then this course explores different types of datasets, how they may violate the regression model's assumptions and how to account for those violations.

what you will learn

For in-class examples of regression analysis, this course explores the effect that employment protections have on employment outcomes. By focusing on one single dataset, we cover a lot of econometric theory.

But to learn econometrics, you must do econometrics, so this course provides a few datasets and some null hypotheses to help you learn how to conduct an analysis of the data. And to help you more, one student produced a video of me exploring a dataset. I hope you enjoy it.

links and files

problem set (PDF)

monopsonist and minimum wage

answers

datasets for course project

datasets

documentation of datasets (PDF)

my Analysis of the "Biagi Law" (PDF)
Teaching with the "Biagi Law" Data

Italian data: CSV file R script Gretl data
OECD data: CSV file R script Gretl data
Phillips Curve: wikipedia doviak.net

OECD Indicators of Employment Protection

EPL dataset description (PDF)

BLS employment status by state

annual data (CSV)
monthly data, seasonally adjusted (CSV)

Vaghul & Zipperer (WCEG, 2016). minimum wage data

USA state panel -- BLS employ. with VZ min. wage

CSV file R script Gretl data

Wikipedia. Minimum Wage
Schmitt (CEPR, 2013). effect on employment

course outline

background -- statistics and probability

bivariate normal distribution, (wxM) (PDF)

lecture 1 -- ordinary least squares

Studenmund, chaps. 1, 2 and 3
notes on regression, (PDF)
OLS regression, (PDF)
OLS regression, (R script)
OLS regression, (wxM) (PDF)
problems #4 and #1

lecture 2 -- maximum likelihood

Kennedy, chaps. 1, 2 and 3
MLE mean-variance, (wxM) (PDF)
MLE regression, (wxM) (PDF)
MLE 2nd o.c., (wxM) (PDF)
problem #2

lecture 3 -- hypothesis testing

Studenmund, chaps. 4 and 5
Kennedy, chap. 4
MLE explanations, (wxM) (PDF)
distribution of beta hat, (R script)
problems #3 and #4

lecture 4 -- violations of the Gauss-Markov assumptions

Kennedy, chaps. 5, 6 and 7

lecture 5 -- panel data

Studenmund, chap. 16
Kennedy, chap. 18

lecture 6 -- heteroskedascity

Studenmund, chap. 10
Kennedy, chap. 8
heteroskedascity in the logit model

lecture 7 -- probability models

Studenmund, chap. 13
Kennedy, chaps. 16 and 17
logit model, (wxM) (PDF)

lecture 8 -- time-series

Studenmund, chaps. 9, 12 and 15
Kennedy, chaps. 10, 19 and 20
non-stationary residuals, (wxM) (PDF)

lecture 9 -- simultaneous equations

Studenmund, chap. 14
Kennedy, chap. 11

references and software

statistics

my statistics course
L.&H. Friedman's statistics course

statistical software

the R language

LearnEconometrics.com

mathematical software

Maxima and wxMaxima

wxMaxima installation instructions (U. New Haven)

Josef Leydold's Maxima for Economics
Zachary Hannan's wxMaxima for Calculus

textbooks

required:
- A.H. Studenmund. Using Econometrics: A Practical Guide.
- P. Kennedy. A Guide to Econometrics.
other suggestions:
- L. Adkins (2018). Using gretl for Principles of Econometrics.
- DeGroot and Schervish. Probability and Statistics.
- Pearce. The MIT Dictionary of Modern Economics.

Copyright © 2002-2025 Eryk Wdowiak