Analysis of longitudinal multivariate outcome data from couples:
application to HPV infection dynamics from couple cohort studies
Xiangrong Kong, PhD
Assistant Professor
Department of Biostatistics and Epidemiology
UMass-Amherst School of Public Health and Health Sciences
Wednesday, November 15th, 4:00 PM
Waterman - 458
Abstract:
We consider a specific situation of correlated data where multiple binary outcomes are repeatedly measured on each member within a couple. Such multivariate longitudinal data from couples generate multi-faceted correlations which can be further complicated if there are polygamous partnerships. An example is data from cohort studies on human papilloma virus (HPV) transmission dynamics in heterosexual couples. HPV is a common sexually transmitted disease with 14 known oncogenic types causing anogenital cancers. The binary outcomes on the multiple types measured in couples over time introduce inter-type, intra-couple, and temporal correlations. Simple analysis using generalized estimating equations or random effects model lacks interpretability and cannot fully utilize the available information. We develop a hybrid modeling strategy using Markov transition technique together with pairwise composite likelihood for analysis of such data. The method can be used to identify risk factors associated with HPV transmission and persistence, estimate difference in risks between male-to-female and female-to-male HPV transmission, compare type-specific transmission risks within couples, and characterize the inter-type and intra-couple associations. Applying the method to HPV couple data collected in a Ugandan male circumcision (MC) trial, we assess the effect of MC and role of gender on risks of HPV transmission and persistence.
Time permitting, another topic on evaluation of the population impact of HIV prevention programs (such MC scale-up) on the HIV epidemic in Uganda will also be introduced to showcase how biostatistical skills are applied in addressing important public health questions.