The differences in the frequencies of some parts of speech (POS), particularly function words, and lexical diversity in male and female speech have been pointed out in a number of papers. The classifiers using exclusively context-independent parameters have proved to be highly effective. However, there are still issues that have to be addressed as a lot of studies are performed for English and the genre and topic of texts is sometimes neglected. The aim of this paper is to investigate the association between context-independent parameters of Russian written texts and the gender of their authors and to design predictive re-gression models. A number of correlations were found. The obtained data is in good agreement with the results obtained for other languages. The model based on 5 parameters with the highest correlation coefficients was designed.