Virtual Office Hours will be held Tuesdays from 12:00 pm to 3:00 pm. 

Zoom Meeting ID: 930 5820 1339

Course Description: 
Principles and applications of modern statistical decision theory, with a special focus on Bayesian modeling, data analysis, inference, and optimal decision making. Prior and posterior; comparison of Bayesian and frequentist approaches, including minimax decision making and elementary game theory. Bayesian estimation, hypothesis testing, credible sets, and Bayesian prediction. Introduction to Bayesian computing software and applications to diverse fields. Grading: A-F only. Prerequisite: STAT-514 or permission of instructor... 

Virtual Office Hours will be held Tuesdays from 12:00 pm to 3:00 pm. 

Zoom Meeting ID: 930 5820 1339

American University

Jeff Gill - "Critical Differences in Bayesian and Non-Bayesian Inference and Why the Former is Better"

University of North Carolina, Chapel Hill

Santiago Olivella - "An Introduction to Tree based Models"

Santiago Olivella - "An Introduction to Latent-Variable Network Models"

Universidad de la República, Uruguay

Santiago López Cariboni - "Experiments in Political Science"

This is an introduction to survey research and polling. Surveys, generally speaking, address questions that are of interest to political researchers, political actors, corporations, government, and journalists. The scientific principles that underlie survey work come from theoretical and empirical knowledge produced by different fields such as political science, sociology, statistics, psychology, and computer science. Surveys provide researchers a way to measure attitudes, behaviors, values, and norms.

January 14

• First session. No readings.

January 21

• Jeff Gill. "Generalized Linear Models." 

January 28

• Nathaniel Beck. "Estimating Grouped Data Models with a Binary-Dependent Variable and Fixed Effects via a Logit versus a Linear Probability Model: The Impact of Dropped Units." (2019)

February 18

• Jeff Gill. "Monte Carlo Methods." 

Jonathon Homola and Jeff Gill. “A Flexible Class of Bayesian Frailty Models For Political Science Data.” (2019)

Jeff Gill. “Monte Carlo and Related Iterative Methods.” Chapter from Bayesian Methods: A Social and Behavioral Sciences Approach, Third Edition (2014)

February 25

• Graeme Blair and Kosuke Imai. “Statistical Analysis of List Experiments.” (2012)

March 3

• Gary King and Richard Nielson. “Why Propensity Scores Should Not Be Used for Matching.” (2019)

March 31

• Kosuke Imai, In Song Kim, and Erik Wang. “Matching Methods for Causal Inference with Time-Series Cross-Sectional Data.” (2020)

April 14

• Gary King. “How Not to Lie with Statistics: Avoiding Common Mistakes in Quantitative Political Science.” (1986)

April 21

• Trevor Park and George Casella. “The Bayesian Lasso.” (2008)

The Lasso Page

Regularization: Ridge, Lasso and Elastic Net (Tutorial)

May 5

• Jennifer L. Hill and Hanspeter Kriesi. “

Missing Data Lecture Slides

Monte Carlo Methods Lecture Slides

Everything You Need to Know About the Linear Model Slides

Justin Grimmer's guide to graduate school

Methods Comprehensive Exams: 2018, 2019.

R Slides for Learning (by me):

biostat_starting_R.pdf

biostat_functions.pdf  

biostat_plotting.pdf   

biostat_sampling.pdf  

Survival models for the social and biomedical sciences. An occasional course.

Description:
This course covers the theoretical and applied foundations of Bayesian statistical analysis with an emphasis on computational tools for Bayesian hierarchical models. We will discuss model checking, model assessment, and model comparison.

The course will cover Bayesian stochastic simulation (Markov chain Monte Carlo) in depth with an orientation towards deriving important properties of the Gibbs sampler and the Metropolis Hastings algorithm. Extensions and hybrids will be discussed. We will then use Markov chain Monte Carlo tools to fit linear and nonlinear specifications with multiple levels, longitudinal features, and non-normal distributional assumptions. Lectures will include theoretical discussions of modeling and estimation as well as practical guidance for fitting complex multilevel models with R and JAGS software. Applications will be drawn from political science, sociology, epidemiology, economic policy, and public administration.

Course Description

This class introduces students to a variety of statistical methods used to investigate political phenomena.

We will address the principles behind these methods, their application, and their limitations. The course will be useful to those undertaking a quantitative methods thesis in Government, but not solely. Indeed, the course aims to provide anyone interested in political science with a proficient understanding of the intuitions behind several of the methods used to analyze political data and identify causal paths. By the end of the course, students will have acquired important analytical and practical skills and will be able to evaluate the quality and reliability of scholarly and journalistic work done using quantitative methods. Students will learn statistical software skills (R). For the course's final assignment, students will be given the choice between writing a research paper using data and writing a different kind of project more suitable to those who are not interested in writing a quantitative research paper. 

Prerequisite Details: 

Government 50. 

Course Grade: 

The final grade will be based on weekly problem sets (50%) and the final assignment (50%). The problem sets are outlined below. The final assignment is designed to take a question and dataset that

Course Description: 

This course covers Bayesian statistical model development with explicitly defined hierarchies.

Such multilevel specifications allow researchers to account for different structures in the data and provide for the modeling of variation between defined groups. The course begins with simple nested linear models and proceeds on to non-nested models, multilevel models with dichotomous outcomes, and multilevel generalized linear models. In each case, a Bayesian perspective on inference and computation is featured. The focus on the course will be practical steps for specifying, fitting, and checking multilevel models with much time spent on the details of computation in the R and bugs environments. 

Learning Outcomes: 

At the conclusion of this course participants will: be able to specify and estimate Bayesian multilevel (hierarchical) models with linear and nonlinear outcomes, treat missing data in a principled and correct manner using multiple imputation, gain facility in the R and bugs statistical languages, know how to compute the appropriate sample size and power calculations for Bayesian models, gain exposure to Bayesian approaches including MCMC computation, and be able to assess model reliability and fit in complex models. 

Prerequisite Details: 

This course assumes a knowledge of basic statistics as taught in

Statistical Horizons Workshop, Instructor Profile.

SLIDES FROM THE WORKSHOP:

Introduction:
Normal Model Specifications:
Models, Part 1:
Multilevel Specifications:
Markov Chain Monte Carlo:
Using JAGS:
Models, Part 2:

DATASETS FROM THE WORKSHOP:

hpd.gamma function in R

state.short.dat dataset

pbm.pim2.dat dataset

Multivariate normal code

North Carolina dataset

Trauma dataset

Indomethacin dataset

Dogs dataset

Poverty in Europe dataset

Africa dataset

ANES 2012 face-to-face dataset, ANES 2012 internet dataset

Scotland dataset

Tobit Gibbs sampler code

OECD data, OECD code

Attitudes dataset, Attitudes code, abortion_cluster.sav.txt

BAAD data

Thermonuclear Testing data

ANES 1960 data, ANES 1960 model

Pixels.zip

asap.jags.dat