Linear regression is one of the most used statistical techniques due to the fact that the linear model can be applied to many different problems. Multiple linear regression will be presented in diploma as well as the multiple linear regression model adequacy. The model adequacy can be assessed with different statistical tests of the model and its coefficients. Based on described theoretical backgrounds, the practical implementation of the multiple linear regression will be presented. Techniques of the parameter selection, their statistical evaluation and assessment of the model adequacy will be presented on the hydrostatic-season-time model, which is used to monitor dam activities and assuring it's safety. The parameter selection procedure can be very demanding and does not result an unique solution. Therefore it is necessary to perform various statistical tests and to observe several parameters to define statistically most influential parameters and an optimal model.
|
