Launch the Logistic Platform

Launch the Logistic platform by selecting Analyze > Fit Y by X. The Fit Y by X launch window is used for four different types of analyses. When you enter an ordinal or nominal Y variable and a continuous X variable, the Logistic platform is launched.

Figure 8.3 The Logistic Launch Window 

For more information about the options in the Select Columns red triangle menu, see “Column Filter Menu” in Using JMP. The Logistic launch window contains the following options:

Y, Response

The response variable or variables that you want to analyze. The response variable is often called the dependent variable. These variables must have an ordinal or nominal modeling type.

X, Factor

The predictor variable or variables that you want to analyze. The factor variables are often called independent variables. These variables must have a continuous modeling type.

Block

(Not applicable for a logistic analysis.) A column that specifies a Blocking variable.

Weight

A column containing a weight for each observation in the data table. A row is included in the analyses only when its value is greater than zero.

Freq

Assigns a frequency to each row in the analysis. Assigning a frequency is useful when your data are summarized.

By

Produces a separate report for each level of the By variable. If more than one By variable is assigned, a separate report is produced for each possible combination of the levels of the By variables.

Target Level

(Available only when there is one binary response that has a nominal modeling type.) Enables you to specify the level of the response whose probability you want to model.

Tip: The default level that is used in the logistic model as the target value is based on the order of the levels. Use the Value Order column property to change the default target value.

Data Format

In the Logistic platform, your data can consist of unsummarized or summarized data:

Unsummarized data

There is one row for each observation and columns for X and Y values.

Summarized data

Each row represents a set of observations with common X and Y values. The data table must contain a frequency column that contains the counts of observations for each row. Enter this column as Freq in the launch window.

For an example of summarized data in the Logistic platform, see Example of Nominal Logistic Regression.

Note: The Fit Y by X launch window accommodates columns with continuous, ordinal, and nominal modeling types. The Logistic platform is launched for all pairs of ordinal or nominal Y, Response and continuous X, Factor columns. The Fit Y by X launch window launches the Bivariate, Oneway, or Contingency platforms for other column type combinations.