Comparison of multivariate classification and regression methods for the indoor radon measurements

Abstract

We present the results of a test usage of multivariate methods, as developed for data analysis in high-energy physics and implemented in the toolkit for multivariate analysis software package, in our analysis of the dependence of the variation of indoor radon concentration on climate variables. The method enables the investigation of the connections of the wide spectrum of climate variables with radon concentrations. We find that multivariate classification and regression methods work well, giving new information and indications, which may be helpful in further research of the variation of radon concentration in indoor spaces. The method may also lead to considerable prediction power of the variations of indoor radon concentrations based on the knowledge of climate variables only.