Semiparametric and nonparametric modeling for effect modification in matched studies Academic Article

abstract

• This study describes a new graphical method for assessing and characterizing effect modification by a matching covariate in matched case-control studies. This method to understand effect modification is based on a semiparametric model using a varying coefficient model. The method allows for nonparametric relationships between effect modification and other covariates, or can be useful in suggesting parametric models. This method can be applied to examining effect modification by any ordered categorical or continuous covariates for which cases have been matched with controls. The method applies to effect modification when causality might be reasonably assumed. An example from veterinary medicine is used to demonstrate our approach. The simulation results show that this method, when based on linear, quadratic and nonparametric effect modification, can be more powerful than both a parametric multiplicative model fit and a fully nonparametric generalized additive model fit. 2003 Elsevier B.V. All rights reserved.

authors

• Cohen, Noah

published proceedings

• COMPUTATIONAL STATISTICS & DATA ANALYSIS

author list (cited authors)

• Kim, I., & Cohen, N.

citation count

• 7

complete list of authors

• Kim, I||Cohen, N

publication date

• July 2004

publisher

• Elsevier  Publisher

published in

• Computational Statistics and Data Analysis  Journal

keywords

• Conditional Logistic Regression
• Effect Heterogeneity
• Effect Modification
• Local Likelihood Regression
• Matched Case-control Studies
• Varying Coefficient Model

Digital Object Identifier (DOI)

• 10.1016/j.csda.2003.09.002

start page

• 631

end page

• 643

volume

• 46

issue

• 4

URL

• http://dx.doi.org/10.1016/j.csda.2003.09.002