Builds a logistic regression model to predict binary Target Variable column value from Predictor Variable(s) column values.
Input data should contain following columns.
Target Variable - A column that has logical values (TRUE/FALSE) to be predicted by the logistic regression model. (For how to convert other types of columns to logical type, take a look at the reference.)
Predictor Variable(s) - Column(s) that has values on which the prediction by logistic regression model is based.
Metrics of Variables - Metric of variables to use on Y-axis of scatter plot on Coefficients View.
Average Marginal Effect
P Value Threshold to be Significant - P value must be smaller than this value for coefficients to be considered statistically significant.
Confidence Intervals for Marginal Effects - Enable/disable calculation of confidence interval for marginal effect. Default is FALSE. Note that this is a calculation that takes some time.
Sort Variables by Coefficients - If set to TRUE, variables displayed in Coefficients View are sorted by coefficients.
Cut Point for TRUE/FALSE
Sample Data Size - Number of rows to sample before building linear regression model.
Random Seed - Seed used to generate random numbers. Specify this value to always reproduce the same result.
Max # of Categories for Predictor Vars - If categorical predictor column has more categories than this number, less frequent categories are combined into 'Other' category.
Imbalanced Data Adjustment
Adjust Imbalanced Data - Adjust imbalance of data in Target Variable (e.g. FALSE being majority and TRUE being minority.) by SMOTE (Synthetic Minority Over-sampling Technique) altorithm.
Target % of Minority Data
Maximum % Increase for Minority Size
Neighbors to Sample for Populating Data
Test Mode - Enable/Disable Test Mode. In Test Mode, data is split into training data and test data, and test data is not used for building model, so that it can be used for later test, without bias.
Ratio for Test Data - A value between 0 and 1.
Data Splitting Method
Random - Specified ratio of data that is picked randomly is used as test data.
Reserve Order in Data - Specified ratio of data that appears last are used as test data.
Click Analytics View tab.
If necessary, click "+" button on the left of existing Analytics tabs, to create a new Analytics.
Select "Logistic Regression Analysis" for Type.
Select Target Variable column.
Select Predictor Variable(s) columns.
Set Analytics Properties if necessary.
Click Run button to run the analytics.
Select view type by clicking view type link to see each type of generated visualization.