Naive Bayes

Select Naive Bayes Classifiers from the Machine Learning Startup Panel - Quick tab and click the OK button to display the Naive Bayes dialog box. You can also double-click Naive Bayes Classifiers to display the dialog box, which contains four tabs: Quick, Sampling, Distributions, and Memory usage.

OK

After specifying desired options, click the OK button to begin the Naive Bayes Classifier analysis and display the Results dialog box.

Cancel

Click the Cancel button to close the Naive Bayes dialog box without performing an analysis and return to the STATISTICA Machine Learning Startup Panel.

Options

Click the Options button to display the Options menu.

Select Cases

Click the Select Cases button to display the Analysis/Graph Case Selection Conditions dialog box, which is used to create conditions for which cases will be included (or excluded) in the current analysis. More information is available in the case selection conditions overview, syntax summary, and dialog box description.

W

Click the W (Weight) button to display the Analysis/Graph Case Weights dialog box, which is used to adjust the contribution of individual cases to the outcome of the current analysis by "weighting" those cases in proportion to the values of a selected variable.

MD deletion

Missing data can be deleted Casewise, substituted by means (Mean substitution), or used (Use missing) depending on the option selected in the MD deletion group box.

Casewise

Select the Casewise option button to include only the cases that do not contain any missing data for any of the selected variables in the analysis.

Mean substitution

Select the Mean substitution option button to replace missing data by the means for the respective variables (for this analysis only, not in the data file).

Use missing

Because of the nature of Naive Bayes model fitting, you can make use of data cases with partially missing values. For example, a data case with missing inputs can still be used in estimating the prior probabilities of class membership should the output values be valid. Likewise, a data case with partially missing inputs can be used to estimate the conditional densities of the inputs variables. This option is particularly useful when the original data set is sparse (i.e., with lots of missing values).