Clyde, M.A. Model uncertainty and health effect studies for particulate matter. Environmetrics. 2000; in press.  Home/Search   Document Details and Download   Summary   Related Articles

....in the course of variable selection, an issue raised by the 1998 National Research Council report on Research Priorities for Airborne Particulate Mater . Different model selection strategies have, in some cases, led to very different models and conclusions for the same set of data (Schwartz 1993; Clyde 2000). Rather than selecting a single model, we approach the problem using Bayesian Model Averaging (BMA) a technique that accounts for model uncertainty by averaging over a wide class of models supported by the data. It has been hypothesized that fine particles are more damaging to human health than ....

....to represent seasonal variation in mortality due to flu or other unmeasured trends such as population growth over time. We consider 30 knots spaced approximately a month apart to capture variation on a scale of one month or greater. Uncertainty regarding the number of knots was addressed as in Clyde 2000. We also adjust for the potential confounding meteorological variables of minimum and maximum daily temperature, specific humidity, lags of 0, 1, 2, and 3 days in each of these variables, and quadratic terms in each. We consider particle size (fine and coarse) as well as the 5 lag of the effect ....

[Article contains additional citation context not shown here]

Clyde, M.A. Model uncertainty and health effect studies for particulate matter. Environmetrics. 2000; in press.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC