Statistical Methods In Epidemiology--general

National Institute Of Environmental Health Sciences

Investigators

Linked publications, trials & patents

Abstract

This project develops new statistical methods for epidemiology with broad applications and also methods as needed for ongoing projects in epidemiology, particularly those related to reproductive studies. The work this year involved seven main projects. (1) A project that is collaborative with David Umbach, Min Shi and Katie O'Brien proposed improved methods of adjustment of concentrations from pooled specimens for creatinine (if urine) and for serum lipids (if serum). (2) In work with a biostatistics graduate student at UNC (Mitchell) we are developing a stochastic search algorithm to identify the risk-relevant components of a complex mixture, based on case-control data. (3) In work that is joint with Shanshan Zhao we have developed improved risk prediction models that account for family structure and breast cancer history and applied them to data from the Sister Study on incident breast cancer. (4) Work is continuing related to mediation analysis in scenarios where the exposure interacts with a mediator. (5) We (with Diaz) are developing methods for aggregating information from pregnancy history data for use in risk models, e.g. occurrences of gestational diabetes in relation to later risk of chronic diabetes. (6) I developed an improved approach for adjusting for induced abortion as a competing risk in studies of spontaneous abortion. (7) We are developing methods for assessing evidence for heritability of age at diagnosis and applying those methods to data from the NIEHS Sister Study.