Search

The article discusses a study which examined the presence of residential radon in Sweden using a multi-level approach. The study was designed to compare various methods of estimating the national average radon level. It utilized over 8,000 measurements of residential radon levels from 50 percent of the municipalities across the country. Participants of the study were selected from municipalities that have lung cancer cases. The study found that multi-level modeling is more efficient than single-level ordinary least squares (OLS) model. Study authors concluded that multi-level approach can increase understanding of radon data patterns.

This paper describes an alternative approach for testing for the existence of trend among time series. The test method has been constructed using wavelet analysis which has the ability of decomposing a time series into low frequencies (trend) and high-frequency (noise) components. Under the normality assumption, the test is distributed as F. However, using generated empirical critical values, the properties of the test statistic have been investigated under different conditions and different types of wavelet. The Harr wavelet has shown to exhibit the highest power among the other wavelet types. The methodology here has been applied to real temperature data in Sweden for the period 1850-1999. The results indicate a significant increasing trend which agrees with the 'global warming' hypothesis during the last 100 years. [ABSTRACT FROM AUTHOR]