Exploratory biochemical data analysis: a comparison of two sample means and diagnostic displays

The occurrence of acne in women with hyperandrogenemia is well known; a que stion remains, however, as to whether a further positive relationship can b e detected between the intensity of acne and the levels of testosterone, an drogen precursors and sex hormone binding globulin (SHBG). A procedure of i nteractive data analysis extracting relevant information from original data was applied. Exploratory data analysis (EDA) identifies basic statistical features and patterns of data using a variety of diagnostic displays. The n eed for this step is particularly acute in biochemical and clinical data, t he distribution of which is mostly non-Gaussian and often corrupted by the outliers. The omission of EDA can lead to incorrect results and false concl usions. In the EDA (i) several graphical tools for summarizing data are app lied, (ii) the peculiarities of a sample distribution are investigated, (ii i) a construction of distribution is carried out, (iv) a graphical comparis on of the sample distribution with selected theoretical distributions is em ployed. The proposed procedure is illustrated by typical case study in the evaluation of differences between mean values of serum levels of testostero ne, androgen precursors and SHBG in a group of patients with mild and sever e forms of acne. A knowledge of the interval estimate of the mean value in both groups enables their comparison at the chosen probability level. As wi ll be apparent from the evaluation of inter-group SHBG differences, an inco rrect approach to the determination of group mean values could result in a complete misinterpretation of the data. The results indicate that androgens are not significantly related to the intensity of acne, and that SHBG is h igher in patients with more severe forms of acne.