Combined parametric-nonparametric method for breast cancer risk assessment

The bootstrapping (BS) of rhythmometric characteristics, a mathematical resampling procedure, is used to introduce inferential considerations into discriminant analysis. It is recommended for broad routine use in nonparametric hypothesis testing and biomedical signal simulation. BS is used to introduce inferential considerations into biomedical discriminant analysis and to test results obtained with limited sample sizes. The data from 12 plasma hormones from clinically healthy adult women sampled systematically around the clock and the year are analyzed by circadian BS. Results from BS validate differences in circadian MESOR (midline-estimation statistic of rhythm M) for insulin in spring and summer, complementing earlier results from circannual BS validating a difference in circannual M for insulin between groups having low and high risk of developing breast cancer. It is found that the use of BS serves to introduce inferential considerations into discriminant analysis and to test results obtained with very limited sample sizes, before embarking upon the actual labor-intensive, costly resampling required in circannual and circadian work