New Statistical Approaches to Semiparametric Regression with Application to Air Pollution Research

Research Report 175,
2013

This report describes semiparametric methods for epidemiologic investigations of the short-term effects of air pollution on health, intended specifically to improve the reliability of point estimates and confidence intervals. Dr. James Robins of the Harvard School of Public Health and colleagues developed the new methods, used simulations to compare them with other methods, and applied them to a large epidemiologic data set from the National Morbidity, Mortality, and Air Pollution Study (NMMAPS) to assess their effectiveness. The report is accompanied by a short editorial to assist the reader in understanding this study and its contributions to epidemiologic methods for air pollution.