I am a Social Psychology PhD student at Baylor University. My interests are fairly diverse, and over time have drifted toward improving quantitative methods within social psych.

Substantive interests include the meaning maintenance model; attitudes toward science and religion; sociocultural functions of religiosity; and religious prejudices (e.g., implicit anti-Muslim attitudes).

Upon discovering and immersing myself in Bayesian statistics, my research focus has substantially shifted toward building better models and making more powerful inferences. In teaching myself how to do Bayesian GLMs, GLMMs, latent variable models, mixture models, location-scale-shape models, meta-analysis, integrated data analysis, and many others, I realized that the statistical world of social psychology could be significantly improved (no pun intended). With fancier theoretical models, freer assumptions, and a potent inferential framework, researchers can gain more information (substantively), more information (in the Fisher sense of the word), make better predictions, and generally create and compare models with as many or as few assumptions, with as little or as much complexity as desired.

Quantitative interests include Bayesian SEM (with normal or non-normal assumptions), robust modeling (principled handling of skew, “outliers”, heteroskedasticity), measurement models and invariance assessment, improving analytic techniques for common methods (e.g., the SC-IAT), and in general assessing performance of novel modeling techniques/assumptions and inferential methods through simulation (e.g., BF vs HDI; effect-size driven stopping rules vs Pocock and Le Mets alpha spending functions, shrinkage priors vs alpha adjustments).


Separate frequentist inference, frequency probability, and estimation

This is a short post, but I think people need to separate frequentist inference, frequency probability, and estimation a bit better when describing statistical practices. Some concepts in an oversimplified nutshell: Frequentist inference: Inferring about an unknown parameter or process based on assumed or known frequentist properties. E.g., “If the generative parameter were zero, the …

Thought Droppings on Substantive and Statistical Hypotheses

The recent “use p=.005”, “use BFs”, “no, use estimation”, “no, justify your alpha” discussion rekindled some of my thinking about substantive and statistical hypotheses. This posts will truly be a rambling, without any organization or goals, but maybe it will have something interesting in there somewhere. Researchers need to understand that a statistical hypothesis is …


Contact links can be found in the footer.

The background image and favicon are available here.