Sampling biases and missing data in explorations of sexual partner networks for the spread of sexually transmitted diseases

Abstract

The structures of sexual partner networks are important in determining patterns of transmission of STDs including HIV. Empirical data on sexual partnerships and sexual partner networks collected through sampling individuals are a non-random sample of partnerships and network structures even if individuals are sampled randomly. This has the potential to bias estimates of measures describing the sexual partner network. In addition, biases may be introduced through non-response and missing data. Using Monte Carlo simulation, we investigate the biases that are introduced in estimates measures of the sexual partner network through three common sampling methods. The results indicate that substantial systematic biases are introduced. The direction and magnitude of these biases suggest that, by ignoring them, the risk for the establishment and persistence of infection in a population may be underestimated.