We have now discussed methods for specifying models and for efficiently estimating the parameters in those models. Model diagnostics, or model criticism, is concerned with testing the goodness of fit of a model and, if the fit is poor, suggesting appropriate modifications. We shall present two complementary approaches: analysis of residuals from the fitted model and analysis of overparameterized models; that is, models that are more general than the proposed model but that contain the proposed model as a special case.
KeywordsStandardize Residual Time Series Plot Model Diagnostics Residual Autocorrelation Parameter Redundancy
Unable to display preview. Download preview PDF.