Materials

Descriptive Inference

Introduction

Topics Covered:

  1. Overview and Course Requirements
  2. Course Outline
  3. Introductory Sampling Activity

Lecture:
Lecture video (2 hrs)
Lecture slides
Lecture slides (printable)

Section:
Stata section video (1 hr)
Stata code for section 

R section video (1 hr)
R code for section

Descriptive Questions

Topics Covered:

  1. Describing Univariate Populations
  2. Describing Bivariate and Multivariate Populations
  3. Summarization with Bivariate and Multivariate Regression

Lecture:
Lecture video (2 hrs)
Lecture slides

Section:
Stata section video (1 hr)
Section2.pdf Stata code for section
Leinhardt.dta

R section video (1 hr)
Section2.pdf
section2.r
leinhardt.rdata

Randomly Sampled Observations and Basic Probability

Topics Covered:

  1. Elementary Probability Theory
  2. Random Variables and Functions of Random Variables (Expectation, Variance, ...)
  3. Joint and Conditional Distributions

Lecture:
Lecture video (2 hrs)
Lecture slides
Lecture slides (printable)

Section:
Stata section video (1 hr)
section3_stata.pdf

R section video (1 hr) section3_stata.pdf section3_r.pdf functions_in_r.pdf section3_r.pdf

Random Samples and Descriptive Inference

Topics Covered:

  1. Simple Random Sampling (with and without replacement)
  2. Stratified Random Sampling (with and without replacement)
  3. Distribution of the Sample as an Estimate of the Population Distribution
  4. Sample Statistics
  5. Sampling Distributions (for means and regression parameters)
  6. Point Estimation (properties of estimators)
  7. Interval Estimation
  8. Hypothesis Testing

Lecture 4:
Lecture video (2 hrs)
Lecture slides
Lecture slides (printable)

Section 4:
Stata section video (1 hr)
section4-stata-v2.pdf section4-stata-print.pdf
section4.do
fulton.csv section4.r

R section video (1 hr)
section4-r-v2.pdf section4-r-print.pdf
section4.r fulton.rdata housedems06.rdata


Lecture 5:
Lecture video (2 hrs)
Lecture slides
Lecture slides (printable)

Section 5: housedems06.rdata Stata section video (1 hr)
section5.do

R section video (1 hr) housedems06.rdata section5.r
housedems06.rdata


Lecture 6:
Lecture video (2 hrs)
Lecture slides
Lecture slides (printable)

Section 6:
Stata section video (1 hr)
section6-stata.pdf
section6-stata-print.pdf
section6.do

R section video (1 hr)
section6-r.pdf
section6-r-print.pdf
section6.r housedems06.rdata

Diagnosing and/or Fixing Problems

Topics Covered:

  1. Multivariable Regression
  2. Nonlinearity
  3. Nonconstant Error Variance and Correlated Errors
  4. Weighted Least Squares and Generalized Least Squares
  5. "Robust" Standard Errors
  6. Nonnormality
  7. Unusual Observations (leverage points, outliers, and influence points)
  8. Data Missing Completely at Random
  9. Data Missing at Random (conditional on observables)
  10. Simple Approaches to Bounding and Sensitivity Analysis for Nonignorable Missingness
Lecture 7:

Section 7:
section7.pdf
 

Lecture 8:

Section 8:

Causal Inference

Introduction / Causal Questions

Topics Covered:

  1. Potential Outcomes and Causal Effects
  2. Causal Inference as a Missing Data Problem
  3. Introductory Causal Inference Activity
  4. Describing Univariate Distributions of Potential Outcomes
  5. Describing Univariate Distributions of Causal Effects
  6. Conditional Distributions of Potential Outcomes and Causal Effects
  7. Causal Questions Not Addressed in the Course

Lecture 9:
Lecture video (2 hrs)
Lecture slides 

Section 9 (both Stata and R):
Section video (1 hr)
section9.pdf

Randomized Treatment Assignment

Topics Covered:

  1. Identification with Randomized and Conditionally Randomized Treatment Assignment
  2. Estimation, CIs, and Testing with Randomized and Conditionally Randomized Treatment Assignment
  3. Random Variables and Functions of Random Variables (Expectation, Variance, ...)
  4. Joint and Conditional Distributions

Lecture:
Lecture video (2 hrs)
Lecture slides
Lecture slides (printable) 

Section (for both R and Stata):
Section video (1 hr)
section10.pdf

Observational Studies with Measured Confounding

Topics Covered:

  1. The Assumption of No Unmeasured Confounding
  2. Relation to Classical Econometric Assumptions
  3. Choosing Conditioning Variables
  4. Regression Based Estimation (Additive and Interactive)
     

Lecture:
Lecture video (2 hrs)
Lecture slides
Lecture slides (printable)

Section:
Stata section video (1 hr)
section_11.do

R section video (1 hr)
section_11.r

Diagnosing and/or Fixing Problems

Topics Covered:

  1. Assessing Overlap and Balance
  2. Revising the Question of Interest
  3. Simple Approaches to Bounding and Sensitivity Analysis for Unmeasured Confounding


Lecture:
Lecture video (2 hrs)
Lecture slides
Lecture slides (printable)

Section:
Stata section video (1 hr)
section12-stata.pdf
section12.do

R section video (1 hr)
Slides for R section
section12-r-print.pdf
section12.r

carpenter.csv  

section12.r

Review

Lecture 13: Recap of Course and Review of Descriptive Inference
Lecture video (2 hrs)

Lecture 14: Review of Causal Inference
Lecture video (2 hrs)
Slides for IV Lecture (Optional)