Stepwise Discriminant Analysis

Creates stepwise (forward, backward) discriminant function analysis, and computes various classification statistics. For best-subset and stepwise selection of predictor effects in ANCOVA-like designs, see the General Discriminant Function Analysis (GDA) facilities.

Element Name Description
General
Stepwise method Select the method for stepwise selection of predictors.
Missing data deletion Missing data can be deleted casewise or substituted by the respective predictor means.
F To enter Specifies the F-to-enter value for forward or backward selection of predictors.
F to remove Specifies the F-to-remove value for forward or backward selection of predictors.
Maximum number of steps Maximum number of steps for stepwise selection of predictors.
Tolerance value Specifies the tolerance value for detecting redundancy among the predictor variables. The tolerance of a variable is defined as 1 minus the squared multiple correlation of this variable with all other predictors in the model. The smaller the tolerance of a variable, the more redundant is its contribution to the model.
A priori class. probabilities Specifies how to compute a priori classification probabilities; a priori classification probabilities can either be computed proportional to the observed class (group) sizes or they can be the same for all groups.
Generates data source, if N for input less than Generates a data source for further analyses with other Data Miner nodes if the input data source has fewer than k observations, as specified in this edit field; note that parameter k (number of observations) will be evaluated against the number of observations in the input data source, not the number of valid or selected observations.
Canonical Analysis Performs canonical analysis; Statistica will compute Chi-square tests of successive canonical roots, and optionally compute the canonical scores for each case (observation).
Canonical analysis
Creates canonical scores Creates scores for each case (observation) for each canonical variate.
Classification
Classification statistics Creates classification summaries.
Creates posterior p Creates posterior classification probabilities for each case (observation) and for each class.
Creates Mahalanobis d Creates Mahalanobis distances for each case (observation) and for each class.
Creates predicted class Creates predicted classifications (best, second best, ....).