Performance simulations for categorical mediation: Analyzing khb estimates of mediation in ordinal regression models. (December 2019)

• Record Type: Journal Article
• Authors: Smith, E. Keith; Lacy, Michael G.; Mayer, Adam
• Is Part Of: Stata journal. Volume 19:Number 4(2019)
• Page Start: 913
• Page End: 930
• Publication Date: 2019-12
• Subjects: st0583 -- khb -- performance simulation -- mediation -- ordinal logistic regression; Statistics -- Periodicals; Statistics -- Computer programs -- Periodicals; 001.422
• DOI: 10.1177/1536867X19893638
• Languages: English
• ISSNs: 1536-867X

Abstract

Standard mediation techniques for fitting mediation models cannot readily be translated to nonlinear regression models because of scaling issues. Methods to assess mediation in regression models with categorical and limited response variables have expanded in recent years, and these techniques vary in their approach and versatility. The recently developedkhb technique purports to solve the scaling problem and produce valid estimates across a range of nonlinear regression models. Prior studies demonstrate thatk hb performs well in binary logistic regression models, but performance in other models has yet to be investigated. In this article, we evaluatekhb 's performance in fitting ordinal logistic regression models as an exemplar of the wider set of models to which it applies. We examined performance across 38, 400 experimental conditions involving sample size, number of response categories, distribution of variables, and amount of mediation. Results indicate that under all experimental conditions, khb estimates the difference (mediation) coefficient and its associated standard error with little bias and that the nominal confidence interval coverage closely matches the actual. Our results suggest that researchers usingkhb can assume that the routine reasonably approximates population parameters.