Goodness of Fit

Goodness of fit, classification, prediction; computes various goodness of fit indices based on a variable containing observed values or classification, and one or more variables containing predicted values or classifications. Both continuous variables (for regression-type problems) and categorical variables (for classification problems) can be analyzed. Various goodness of fit measures are available for classification and regression-type problems.

General

Element Name Description
Detail of computed results reported Detail of computed results; if All results is selected, the analysis will report histograms and scatterplots.
Variable type Specifies the variable type of observed and predicted variables.

Continuous

Element Name Description
Least squares deviation Specifies whether to calculate the least squares deviation (LSD) goodness-of-fit measure.
Average deviation Specifies whether to calculate the average deviation goodness-of-fit measure.
Relative squared error Specifies whether to calculate the relative squared error goodness-of-fit measure; note that all observed values in this case must be greater than zero.
Relative absolute error Specifies whether to calculate the relative absolute error goodness-of-fit measure; note that all observed values in this case must be greater than zero.
Correlation coefficient Specifies whether to calculate the correlation coefficient goodness-of-fit measure.

Categorical

Element Name Description
Chi-squared test Specifies whether to calculate the Chi-squared test goodness-of-fit measure.
G-squared test Specifies whether to calculate the G-squared test (maximum likelihood Chi-square) goodness-of-fit measure.
Percent disagreement Specifies whether to calculate the percent disagreement goodness-of-fit measure.
Quadratic loss function Specifies whether to calculate the quadratic loss function goodness-of-fit measure.
Information loss function Specifies whether to calculate the information loss function goodness-of-fit measure.