Selection Accuracy Analysis for Partial Invariance

A web app for performing selection accuracy analysis in the presence of partial invariance.


An R package for bootstrap resampling for multilevel models.

Recent & Upcoming Talks

Advancing Quantitative Science with Monte Carlo Simulation
May 15, 2019 9:30 AM
Introduction to Multilevel Modeling
Nov 27, 2018 2:00 PM
Bayesian Data Analysis Workshop
May 2, 2017 10:00 AM

Recent Posts

Complexity of MLM Information Criteria Example Selecting Fixed Effects How to Choose Between AIC and BIC? Including Lv-2 Predictors Workflow Regularization Bibliography In social sciences, many times we use statistical methods to answer well-defined research questions that are derived from some theory or previous research. For example, theory may suggest that interventions to improve students’ self-efficacy may help benefit their academic performance, so we would like to test a mediation model of intervention –> self-efficacy –> academic performance.


Quasi-Bayesian/Monte Carlo CI With the mediation Package Analytical Approaches for CI With the RMediation Package Distribution of Product of Coefficients Asymptotic Normal CI Case Bootstrap Bootstrap CI Fully Bayesian Approach With rstan Posterior (Credible) Intervals Summary Table of Different CIs: Bibliography The data are from the mediation package, which are simulated data with the source of the Education Longitudinal Study of 2002. For the interest of time as well as to consider situations where asymptotic normality may not hold, I only select 50 schools (out of 568) from the sample.


The Problem Demonstration Group mean centering with lme4 Same analyses with Bayesian using brms Group mean centering treating group means as latent variables With Random Slopes Using the Full Data With lme4 With Bayesian taking into account the unreliability Bibliography This post is updated on 2018-11-24 with cleaner and more efficient STAN code. In the past week I was teaching a one-and-a-half-day workshop on multilevel modeling (MLM) at UC, where I discussed the use of group mean centering to decompose level-1 and level-2 effects of a predictor.



Courses I am and will be teaching at USC:

  • PSYC 314: Experimental Research Methods
  • PSYC 621: Seminar in Quantitative Psychology (Multilevel Modeling)
  • PSYC 621: Seminar in Quantitative Psychology (Bayesian Data Analysis)

Courses I have taught at UC:

  • EDST 7010: Statistical Data Analysis I
  • EDST 7011: Statistical Data Analysis II
  • EDST 8075: Bayesian Data Analysis
  • EDST 7082: Getting Started With Multilevel Modeling
  • EDST 8087: Multilevel Modeling for Educational Research


  • [email protected]
  • Department of Psychology, University of Southern California, 3620 S McClintock Ave., CA 90089-1061, USA