Selected Publications

This graphic shows the probability of providing a correct response to an item in a multidimensional item response theory (MIRT) model. In the 1PL, 2PL, and 3PL MIRT models, the choice of compensatory parameterizations can greatly affect the probability of a correct response.

We use a factor analytic approach to assess the dimensionality of the Interpersonal Reactivity Index (IRI). Specifically, we examine the validity of structures that have been commonly used in empathy research, but have yet to be psychometrically validated.

Recent Publications

More Publications

  • Construct Irrelevant Variance


  • A Hierarchical IRT Model for Identifying Group Level Aberrant Growth to Detect Cheating

    Details PDF

  • Creating an R package for a Reproducible Workflow in Educational Assessment.

    Details Dynamic Learning Maps

  • Visualizing different levels of compensation in multidimensional item response theory models

    Details PNG

  • Evaluating an initialization tool for student placement into a map-based assessment.


Recent Posts

More Posts

This is the final post in the tidy sports analytics series, in which I’ve been using play-by-play from the 2016 NFL season to demonstrate the power of the tidyverse. Previously, I’ve discussed: Part 1: Data manipulation using dplyr; Part 2: Data reshaping and tidying using tidyr; Part 3: Data visualization using ggplot2. This post doesn’t feature any new data analysis. Instead, I want to use this last post to talk about the tidyverse more generally and cover some of other advantages of using these packages for data analysis.


This is the third post in the tidy sports analytics series. In this series, I’ve been demonstrating how the collection of tidyverse packages can be used to explore and analyze sports data. Specifically, I’ve been using the 2016 NFL play-by-play data from Armchair Analysis. Part one in the series showed how dplyr can be used for data manipulation, and part two demonstrated reshaping and tidying data using tidyr. This post focuses on data visualization using ggplot2.


This is the second in a series of posts that demonstrates how the tidyverse can be used to easily explore and analyze NFL play-by-play data. In part one, I used the dplyr package to calculate the offensive success rate of each NFL offense in during the 2016 season. However, when we left off, I noted that really we should look at the success rate of both offenses and defenses in order to get a better idea of which teams were the best overall.


Recent & Upcoming Talks

More Talks


Other useful R-related blogs and resources:



Template for writing theses at the University of Kansas using rmarkdown and bookdown.

Soccer predictions using Bayesian mixed effects models

Models developed for the prediction of individual games, European domestic leagues, and the UEFA Champions League.


Sports analytics website for the analysis of college football and men’s college basketball.