Many discussions of logistic regression state that having the wrong variables or the wrong functional form will weaken the model and this will be apparent in the chi square test (apparently a negative two log liklihood value which has a chi square distribution). For example:
You should try different functional forms by logging the independent variables, adding squared terms, etc. Then consult the Wald statistics and model chi-square statistics to determine which model performs best.
Does anyone know how this is done in SAS. I assume you add terms (either new variables or new functional forms) and then conduct this test. But I don't know how this is done, or how to interpret the results of the test.
Quote:
You should try different functional forms by logging the independent variables, adding squared terms, etc. Then consult the Wald statistics and model chi-square statistics to determine which model performs best.