Skip to Main Content

Exposure effects across the life course

Former Ph.D. student, Dr. Sarah Peskoe, submitted a manuscript for publication entitled "There is no impact of exposure measurement error on latency estimation in linear models", which is now provisionally accepted by the journal, Statistics in Medicine. She is working on revising this manuscript. In addition, she has been working on finalizing a manuscript entitled "Latency estimation and inference in the Cox proportional hazards model in the presence of exposure measurement error". In these two manuscripts, Sarah, working with Drs. Molin Wang and Donna Spiegelman, shows that there is no impact of exposure measurement error on the estimates of latency parameters in in linear and Cox models with time-varying exposures. The exposure measurement error does cause bias in the estimates of exposure-outcome associations; the papers also provide the formula to correct such bias.