Classification of Girls’ Sexual Maturity Using Factor Analysis and Analysis of Moderated Mediation

In this paper results of a research were presented, which started with statistical analysis, performed to extract parameters on the basis of which it would be possible to assess girls’ sexual maturity. The parameters selected during the analysis were used in classification. Three classifiers (Random Forest, Linear Discriminant Analysis and Support Vector Machine) were used. Their effectiveness was evaluated using the following measures: sensitivity, specificity, precision, accuracy and F-score. The obtained results suggested that girls’ sexual maturity assessment can be performed on the basis of anthropometric data including measurements in the area of the hips, fat folds and fat content in the body. The maturity status of a girl can be also estimated using parameters extracted from her voice combined with the information about her age. The best accuracy for these features was archived for Random Forest classifier (88.70\(\%\) for voice and 89.13\(\%\) for anthropometric data).