Development, Application, and Testing of Multi-pollutant Statistical Models and Methods.
HEI has had a long term commitment, and record of success, in the examination of key statistical challenges such as model selection, and development, application, and testing of cutting edge statistical models and methods to analyze the relation between air pollution and health. Several HEI projects have included strong methodologic components; in addition, HEI has funded studies aimed at methods development through specific RFAs and other mechanisms. In as much as air pollution science is concerned with testing whether it is possible to parse relatively small associations of health and air pollution in the context of myriad other variables, the need for development and improvement in methods continues to occupy a very important place in HEI’s future research plans.
Recently, HEI published three studies to develop and apply advanced statistical methods for multi-pollutant research. Please see RFA 09-1 for more information. Another recent study developed methods for causal inference methods applied to accountability research.
This study will examine health effects of low levels of air pollution in the US using data from about ~56 million people enrolled in Medicare and Medicaid. In addition, they will develop new causal modeling methods to characterize the shape of the exposure-response function. See also this Program Summary of HEI's research program on low levels of air pollution.
This study aims to improve estimates of concentrations of traffic-related air pollutants using source-oriented emission and dispersion models and Bayesian Melding, a novel data fusion technique that combines measured and modeled concentrations of traffic pollutants.