Am J Epidemiol. 2021 Aug 19:kwab220. doi: 10.1093/aje/kwab220. Online ahead of print.
ABSTRACT
Effect measure modification is often evaluated using parametric models. These models, though efficient when correctly specified, make strong parametric assumptions. While nonparametric models avoid important functional form assumptions, they often requirelarger samples to achieve a given accuracy. We conducted a simulation study to evaluate performance tradeoffs between correctly specified parametric and nonparametric models to detect effect modification of a binary exposure by both binary and continuousmodifiers. We evaluated generalized linear models (GLM) and doubly robust (DR) estimators, with and without sample splitting. Continuous modifiers were modeled with cubic splines, fractional polynomials, and nonparametric DR-learner. For binary modifiers, GLM showed the greatest power to detect effect modification, ranging from 0.42 to 1.00 in the worst and best scenario, respectively. Augmented Inverse Probability Weighting had the lowest power, with an increase of 23% when using sample splitting. For continuous modifiers, the DR-learner was comparable to flexible parametric models in capturing quadratic and non-linear monotonic functions. However, for non-linear, non-monotonic functions, the DR-learner had lower integrated bias than splines and fractional polynomials, with values of 141.3, 251.7 and 209.0, respectively. Our findings suggest comparable performance between nonparametric and correctly specified parametric models in evaluating effect modification.
PMID:34409985 | DOI:10.1093/aje/kwab220
