Posts Tagged ‘ Methods/Statistics ’

Another Benefit of Publicly Version-Controlled Research

June 4, 2014
By

I've been thinking quite a bit lately about why and how political scientists should publicly version control their research projects. By research projects, I mean data, manuscript, and code. And by publicly version control, I mean use Git to version-control and post a public GitHub repository, from the beginning of the project, so that other […]

Read more »

More on Product Terms and Interaction in Logistic Regression Models

February 20, 2014
By

I noticed that Bill Berry, Justin Esarey, and Jackie DeMeritt's (BDE) long-time R&R'ed paper at AJPS is finally forthcoming. I really like seeing highly applied, but rigorous, work like this being published at top journals. You should definitely have a look at their paper if you use logit or probit models to argue for interaction. […]

Read more »

Creating Marginal Effect Plots for Linear Regression Models in R

August 27, 2013
By
Creating Marginal Effect Plots for Linear Regression Models in R

I discuss how to use R to create marginal effect plots as a part of evaluating interactive theories as suggested by Brambor, Clark, and Golder (2006).

Read more »

compactr is now on CRAN

August 5, 2013
By
compactr is now on CRAN

I've been working on a package called [crayon-53c3fb9f86848864224918-i/]  that helps create nice-looking plots in R and it is now up on CRAN. You can get it by typing [crayon-53c3fb9f8685a442559877/] directly into the command line in R. See how it works by typing [crayon-53c3fb9f86861250510619-i/]  or reading the details here. Below I describe the basic structure and functions. […]

Read more »

Arguing for Negligible Effects

July 23, 2013
By

I just uploaded a newer version of my re-titled paper "Arguing for a Negligible Effect." You can find the latest version here. It has a "revise and resubmit" at AJPS and I'm sending it back on August 15 (when they re-open after the summer break), so I...

Read more »

Testing for Interaction in Logit Models

July 11, 2013
By
Testing for Interaction in Logit Models

Andrew Gelman recently posted about testing for interaction in logistic regression models. This is something I've read and thought a little about, so I'm linking to several articles on the topic and offering my quick take. The Debate in Political Science As far as I can tell, the debate started in political science when Wolfinger […]

Read more »

More on What Can Be Learned from Statistical Significance

July 8, 2013
By
More on What Can Be Learned from Statistical Significance

A while back, I reacted to a post by Justin Esarey, in which he argues that not much can be learned from statistical significance. The basic question he's asking is as follows: For a fixed sample size, what does the posterior probability of the null hypothesis look like if we update based on the result of […]

Read more »

Preemptive Review Comments

February 14, 2013
By

I link to and briefly discuss the paper "Rookie Mistakes," recently published in PS.

Read more »

Preemptive Review Comments

February 14, 2013
By

I link to and briefly discuss the paper "Rookie Mistakes," recently published in PS.

Read more »

The Problem with Testing for Heteroskedasticity in Probit Models

February 12, 2013
By
The Problem with Testing for Heteroskedasticity in Probit Models

A friend recently asked whether I trusted the inferences from heteroskedastic probit models. I said no, because the heteroskedastic probit does not allow a researcher to distinguish between non-constant variance and a mis-specified mean function. In particular, my friend had a hypothesis that the variance of the latent outcome (commonly called "y-star") should increase with an […]

Read more »


Subscribe

Email:

  Subscribe