Experimental designs and emission rate modeling for chamber experiments

Abstract

This paper considers some of the statistical aspects of estimating specimen emission rate profiles from chamber concentration level measurements, which is a major step in assessing indoor pollution levels. Parametric and nonparametric modeling approaches are applied to the problem, and their relative advantages and disadvantages are discussed. The issue of experimental design is also addressed, and the choice of an optimal set of experimental conditions and sampling times is considered. Some simulation results are presented to contrast the efficiencies of various experimental designs.