Bayesian Linear Regression Models: F-tests

You can create one or more partial F-tests. An F-test is any statistical test in which the test statistic has an F-distribution under the null hypothesis. F-tests are commonly used when comparing statistical models that have been fitted to a data set, in order to identify the model that best fits the population from which the data were sampled.

Available variables

Lists the factor and covariate variables that are selected from the main Bayesian Linear Regression dialog. When factor and covariate variables are added or removed from the main dialog, the list is updated accordingly.

Test variable(s)

Select the factor/covariate variables to test from the Available variables list and add them to the Testing variable(s) list.

Note: The Include intercept term option must be selected when no test factors or covariates are selected.

Testing variable(s) and value(s)

Specify the values to be tested. The number of values must match the number of parameters in the original model. When values are specified, the first value must be specified for the intercept term (assume all values are 0 when not explicitly defined).

Include intercept term

When selected, the intercept terms are included in the test. By default, the setting is not selected.

When enabled, use the Testing value field to specify a value.

Test label (optional)

You can optionally specify a label for each test. You can specify a string value with a maximum length of 255 bytes. Only one label per each F-test is allowed.