DataLab is a compact statistics package aiming at exploratory data analysis. Please visit the DataLab Web site for more information....

Home Features of DataLab Mathematical/Statistical Analysis Classification & Clustering Linear Discriminant Analysis Apply an LDA Model
See also: Create an LDA Classifier, Loading MLB Files 

Apply an LDA Model

Command: Math -> Linear Dicriminant Analysis -> Apply Model...

The command Math/Linear Dicriminant Analysis/Apply Model... allows to apply a previously calculated and stored LDA model to other datasets. After loading the model the most important model parameters are shown:

When clicking the button "Apply Model", first the validity of the model is checked by matching the model variables and the variables of the current dataset (the matching is performed by comparing the variable names). If the variables match, the user has to select the target variable, otherwise an error message is displayed. The target column is named after the model name and is marked by the preceding string [*].

As an option you can create the raw classifier estimates by unchecking the box "Create Dichotomous Results". If this box is checked (which is the default case) the classifier uses the original target values to indicate the result.

Hint: If one of the independent variables of the model is selected as the target column (option "store in data matrix"), the model cannot be applied a second time since the basis of the model will be destroyed. It is therefore recommended to append the results of a model as an extra column (option "append results to matrix") or to store the results in the matrix clipboard.