Informacja a priori w ocenie jakości modeli TAM na przykładzie platformy Moodle

The article is devoted to the role of a priori information on the basis of a meta- -analysis in the evaluation of the fit and accuracy of Technology Acceptance Model (TAM). This type of model is particularly used to analyze the attitudes and behavior towards new technologies (Moodle platform). In model construction three approaches are compared: structural model with the latent variables (SEM), Bayesian SEM with informative priors based on metanalysis. The aim of the paper is to assess the role of information a priori (subjective knowledge of the researcher and the results of past studies) to assess the stability of the model parameters and fit of the model. Use of information about the prior distributions of parameters and values of point estimates allows to determine the starting points of estimation process and is an essential condition for building a model in bayesian approach. In the process of modeling two models are compared: one built solely on the basis of data (without prior information) and the other that use subjective knowledge of the researcher.