Numerical resampling supports melatonin as a potential marker of breast cancer risk

摘要

On the average, the circadian amplitude (A) of melatonin (ML) is larger in clinically healthy women at high vs. low risk of developing breast cancer (RDBG). The scope of this result, obtained using data from a relatively small group of subjects sampled systematically around the clock and the year, is extended by numerical resampling, i.e., by bootstrapping (BS). Results from BS validate differences in circadian A of ML between the low- and high-RDBC groups throughout the year. A computer-implemented BS procedure is suggested to introduce inferential considerations into discriminant analysis. It is recommended for broad routine use in nonparametric hypothesis testing and biomedical signal simulation.