· Lecture Notes
o Week 1: Paper Illustrating Use of Rubin Causal Model and MLE
o Week 2: Review of Core Concepts
o Week 3: Counterfactuals and Causal Inference and An Example and A Paper on Instrumental Variables Estimation in Political Science
o Week 4: Regression Discontinuity and A Paper Testing RD Against an Experimental Benchmark and Computer Practicum Exercise
o Week 5: Matching and Selection on Observables
o Week 6: Parametric Panel Analysis (with Data and Syntax) and Alternative Approaches to T=2 Panel Analysis
o Week 7: Instrumental Variables Regression
o Week 8: Mediation: Bullock et al. 2009 and Mediation Potential Outcomes and Mediation Simulation
o Week 9: Maximum Likelihood for the Masses
o Week 9: MLE and Linear Regression
o Week 10: MLE details
o Week 10: Binary Response Models
o Week 13: Truncation and Censoring
· R Primer Links
Links to R Primer Notes and the R version of GREENOPT and Links to R (version 2.10)
· Gauss Primer Links
· Instructional Examples
o Regression Analysis Handouts
o Instrumental Variables Example Handout 1
o Instrumental Variables Example Handout 2
o Instrumental Variables Example: SPSS Syntax
o Mathematica Does Calculus For You: INPUT
o Mathematica Does Calculus For You: OUTPUT
o Illustration: Consistency of OLS
· Measurement Error: Consequences and Correctives
· 2SLS Practicum: Campaign Finance
· Data for Campaign Finance Example
o Bootstrapping and Simulation
o Optimization Procedure in Gauss and R
o Optimization Example in Gauss and R
o Newton-Rapheson Spreadsheet Example: Binomial Data
o Optimization Example: Logit, Probit, and Linear Probability Models in Gauss and R
o Optimization Example: Logistic Regression Monte Carlo
o Optimization Example: Probit Monte Carlo
o Optimization Example: Probit Monte Carlo with Index Variable Specification
o Optimization Example: Logistic Regression with Grouped Data
o Optimization Example: Logistic Regression with Individual Data
o Optimization Example: Logistic Regression Monte Carlo with Random Effects
o
How
Omitting Uncorrelated Variables Biases Logistic Regression
o
Graph:
moving from Log-odds to Percentages
o Spreadsheet: moving from logit, ordered logit, and multinomial logit to percentages and Accompanying Data Set
o Optimization Example: Least Squares Regression
o Optimization by means of a Grid Search: Nonlinear Least Squares Regression
o
Optimization Example: MLE for
o Optimization Example: MLE for Normal Nonlinear Regression
o Optimization Example: MLE for Heteroskedastic Regression
o Optimization Example: MLE for Heteroskedastic Regression using Infant Mortality in Africa
o
Optimization
Example: MLE for Heteroskedastic Regression using
Infant Mortality: line search
o Optimization Example: MLE for Truncated Regression
o Optimization Example: MLE for Censored Regression
o Optimization Example: MLE for Three Group Experimental Design in Gauss and R (and R syntax for goodness of fit tests)
o
Stata Dataset
and .do
file: How Bivariate Probit
Differs from 2
o Optimization Example: MLE for binary data: Hamden turnout example
o Optimization Example: MLE for binary data: Hamden data
o Alternative methods of calculating regression estimates and standard errors
o Alternative computational approaches to weighted least squares
o Simulating Poisson Random Variables
o Simulating Poisson Regression
o Poisson regression: Supreme Court appointments
o Poisson regression: Hate Crime Data from NYC
o Poisson Regression Analysis using Hate Crime Data from NYC in Gauss and R
o Comparing Poisson and Negative Binomial Distributions in Gauss and R
o
Simulating
Negative Binomial I Regression with Constant Dispersion
o Simulating Negative Binomial II Regression with Mean-Related Dispersion
o Negative Binomial Regression with Constant Overdisperstion (Hate Crime example) in Gauss and R
o Negative Binomial Regression with Overdisperstion Proportion to Lambda (Hate Crime example) in Gauss and R
o Stata Dataset: Hate Crime Data from NYC
o Normal-Exponential regression: Analysis using Hate Crime Data from NYC
o Ordered and Unordered Logistic Regression
o Simulating Panel Data: Pooled TSCS OLS vs. Fixed Effects
o Simulating Panel Data: Pooled TSCS Random Effects vs. Fixed Effects
o
Simulating
Panel Data: Random Effects vs. Fixed Effects: Bias in RE when intercepts
are correlated with X
o Analysis of Panel Data: Greene’s Example 14.1: Stata Data File
o
Analysis
of Panel Data: Greene’s Example 14.1: Stata Do
File
o Analysis of Panel Data: Greene’s Example 14.1: Gauss Data File
o
Analysis
of Panel Data: Greene’s Example 14.1: Gauss Program
o Analysis of Panel Data: Greene’s Table 13-2: Stata Data File
o
Analysis
of Panel Data: Greene’s Table 13-2: Stata Do
File
o Simulating Time-Series Data: Eviews
o Spatial/temporal Autocorrelation Models: Simulation and ML Estimation
o MLE vs. method of moments example
o Introduction to LISREL: Example 1
o Introduction to LISREL: Example 2
o Introduction to LISREL: Example 3
o Introduction to LISREL: Example 4
o Introduction to LISREL: Example 5
o Introduction to LISREL: Mood Study 2: Random Error
o Introduction to LISREL: Mood Study 2: Nonrandom Error
o Introduction to LISREL: Hispanics: Random Error
o Introduction to LISREL: Hispanics: Nonrandom Error
o How Multiple Measures Enhance the Robustness of Lisrel Models
o Checking Model Identification Using LISREL
o
Illustration
of reciprocal causation: Excel
o Some helpful links: meta analysis
o Some helpful links: robust regression
Web Site: vote.research.yale.edu
Copyright © Yale University, 2009