Investigation of causality based on complex use of statistical methods (case study of social research)

Abstract

The article deals with the problem of revealing cause–effect relations in the social research by a complex of statistical methods. The ways for solving the problem for experimental and non-experimental data are regarded. In the research the role of the statistical methods in formation of causal relation hypotheses is revealed and the methods of hypotheses verification in conditions of experiment or upon latent structure modelling are discussed. The possibilities of the use of the factor analysis and the analysis of variance in revealing cause–effect relations are also considered. Special attention is paid to the interpretation of the analysis results depending on the character of the empirical data and the conditions they were obtained in. The approaches to causal relations revealing based on the development of the schemes of the complex analysis of the empirical data by the statistical methods aimed at investigation of the cause and effect relation in a long-term research are suggested. We take into account the hierarchical structure of the schemes reflecting the structure of the subject of cognition, the specificity of which requires the use of “rigid” and “flexible” models in combination. Its variant could be the method of structural equation modelling. The article gives an example of the research of causal relations in the assessment of the quality of education services in higher institution. Each stage of the assessment is provided with building of certain “rigid” or “flexible” mathematical models. Their combination allows using the obtained quality parameters as an instrument of regulation of interaction between education service providers and clients.