Application of a Variable Importance Measure Method to HIV-1 Sequence Data

Merrill D. Birkner, Division of Biostatistics, School of Public Health, University of California, Berkeley
Mark J. van der Laan, Division of Biostatistics, School of Public Health, University of California, Berkeley

Abstract

van der Laan (2005) proposed a method to construct variable importance measures and provided the respective statistical inference. This technique involves determining the importance of a variable in predicting an outcome. This method can be applied as an inverse probability of treatment weighted (IPTW) or double robust inverse probability of treatment weighted (DR-IPTW) estimator. A respective significance of the estimator is determined by estimating the influence curve and hence determining the corresponding variance and p-value. This article applies the van der Laan (2005) variable importance measures and corresponding inference to HIV-1 sequence data. In this data application, protease and reverse transcriptase codon position on the HIV-1 strand are assessed to determine their respective variable importance, with respect to an outcome of viral replication capacity. We estimate the W-adjusted variable importance measure for a specified set of potential effect modifiers W. Both the IPTW and DR-IPTW methods were implemented on this dataset