Run a Logistic Regression

Use the Logistic Regression tab to analyze the relationship between the dependent variable and one or more independent variables by estimating probabilities using a logistic function, which is the cumulative logistic distribution. For example, if you want to determine factors that contribute to ever using alcohol (variable = alcflag), you can look at age, gender, and education. Here, alcohol use is the dependent variable and age, gender, and education are the independent variables.

This feature is only available for PDAS.

NOTE: For more information on analyzing crosstabs, refer to the Analysis Methodology section.

To run a logistic regression report, perform the following:

  1. Click the Logistic Regression tab. If you added any favorites in the Variables list, those display at the top of the list.
  2. Search for the appropriate variable and click it to see the available options:
Option Description
Add to Favorites Star See the Add to Favorites section.
Set Dependent
  • Click to add the variable as the Dependent Variable to the field on the right.
  • This response or outcome variable is described in terms of other variables (independent variables).
  • The system will only allow appropriate variables to be listed as dependent for the logistic regression analysis feature.
  • Only one dependent variable can be selected.
  • In the Variable Browser on the Survey Info tab, the dependent variables will have a value of "Yes" for the "Eligible to be a logistic regression dependent variable" option.
  • This is a required field.
Set Independent
  • Click to add the variable as the Independent Variable to the field on the right.
  • This predictor variable is used to predict or explain the dependent variable.
  • Multiple independent variables can be selected.
  • This is a required field.
Weight Variable The weight will make the results representative of a target population.
  1. Click the Dependent button for the appropriate variable.
  2. Click the Independent button for the appropriate variable.
  3. If you change your mind on any of the variables, you can:
  4. If you are unsure about which variable to select, click the arrow () in the Variables pane to view additional information about the variable.
  5. Click Run Logistic Regression. The chart displays with the dependent and independent variables selected.