Table of contents
Introduction
Prerequistes
Topics
To understand the content of the course you should be familiar with these topics:
- Random variables, including expectation and variance
- Dependence/independence of random variables
- Conditional distributions
- The Bernoulli distribution and normal distribution
- Estimators and estimates
Topics that we will cover in the course, but which you should ideally have previously studied:
- Confidence intervals and standard errors
- Hypothesis tests, Errors (“Type I” and “Type II”), p-values, statistical significance
- The linear model, OLS
Skills
You will need to use the following computing techniques:
- Basic numerical computing using Python
- Data manipulation using Pandas and Numpy
numpy.random
for simulating random samples- Statsmodels for regressions. (scikit-learn does not have good support for inference.)
- Jupyter notebooks
Review materials
Nonconcerns
The following topics will not be covered in the course:
- Instrumental variables
- Difference-in-differences (diff-in-diffs)
- Regression discontinuity designs (RDD)
- Synthetic controls
- Analysis of variance (ANOVA)