In the Fit Model launch window, the Model Specification red triangle menu contains the following options:
Center Polynomials
Centers by its mean any continuous term that is involved in an effect with a degree greater than one. This option is checked by default, except when a term involved in the effect is assigned the Mixture Effect attribute or has the Mixture column property. Terms with the Coding column property are centered midway between their specified High and Low values.
Centering is useful in making regression coefficients more interpretable and in reducing collinearity between low-order and high-order effects.
Informative Missing
Provides a coding system for missing values. This system allows estimation of a predictive model despite the presence of missing values. It is useful in situations where missing data are informative. See Informative Missing.
This option is available for the following personalities: Standard Least Squares, Stepwise, Generalized Regression, MANOVA, Loglinear Variance, Nominal Logistic, Ordinal Logistic, Proportional Hazard, Parametric Survival, Generalized Linear Model, and Response Screening.
Suppress Coding
(Available only if one or more of the effects columns contains a Coding column property.) Ignores any Coding column properties for the effects columns and fits a model using the uncoded effects. Estimates in the report are therefore shown on the original scale. This option is not recommended unless you need it.
Set Alpha Level
Sets the alpha level for confidence intervals in the Fit Model analysis. The default alpha level is 0.05.
Error Specification
(Available only for the Standard Least Squares personality when there are no random effects.) Specifies the error variance and the error degrees of freedom that are used for standard errors and tests in the Fit Least Squares report. Note that the Studentized Residuals plot and the Box Cox Transformations report are not affected by changing the Error Specification. When the Error Specification is Pure Error or Specified, an additional column appears in the Analysis of Variance report. See “Analysis of Variance”.
Default Estimate
Uses the standard root mean square error and error degrees of freedom from the model to calculate all tests and standard errors.
Pure Error
Uses the Pure Error mean square and associated degrees of freedom from the Lack of Fit report to calculate all tests and standard errors. See “Lack of Fit”.
Caution: If the pure error degrees of freedom is 1, a warning message is displayed indicating that tests are weak and confidence limits are large.
Specified
Uses user-specified values for the error variance and error degrees of freedom to calculate all tests and standard errors.
Save to Data Table
Saves your Fit Model launch window specifications as a script that is attached to the data table. The script is named Model. When a table contains a script called Model, this script automatically populates the launch window when you select Analyze > Fit Model. (Simply rename the script if this is not desirable.)
For more information about JSL scripting, see Introduction to Writing JSL Scripts in the Scripting Guide.
Save to Script Window
Copies your Fit Model launch window specifications to a script window. You can save the script window and re-create the model at any time by running the script.
Create SAS job
Creates a SAS program that can re-create the current analysis and data table in SAS in a script window. Once created, you have several options for submitting the code to SAS.
1. Copy and paste the code into the SAS Program Editor. This method is useful if you are running an older version of SAS (pre-version 8.2).
2. Select Edit > Submit to SAS.
3. Save the file and double-click it to open it in a local copy of SAS. This method is useful if you would like to take advantage of SAS ODS options, such as generating HTML or PDF output from the SAS code.
See Submit SAS Code in Using JMP.
Submit to SAS
Submits code to SAS and displays the results in JMP. If you are not connected to a SAS server, prompts guide you through the connection process.
See Submit SAS Code in Using JMP.
Convergence Settings
The Convergence Settings menu contains the following options:
Maximum Iterations
Specifies the maximum number of iterations that are used in the model fitting. By default, the maximum number of iterations is 100. If your model does not readily converge, you might want to increase the number of iterations. If you have a very large data set or a complicated model, you might want to limit the number of iterations.
Convergence Limit
Specifies the convergence limit for the model fitting. If you model does not readily converge, you might want to increase the convergence limit. By default, the convergence limit is 0.00000001.
Note: The Convergence Settings menu appears only for certain personalities. In the Standard Least Squares personality, the Convergence Settings menu appears only when there is a random effect and REML is selected as the Method in the launch window.
Options for Many Responses
The Options for Many Responses menu contains options that enable you to suppress and consolidate results when a model has many responses:
Suppress Reports
Specifies that the individual model reports are hidden. When there are thousands of responses, this option reduces computation time. The fitting objects and some menu items are still available.
Tip: Use the Results in Data Table option to collect the results from the model reports.
Results in Data Table
Saves the individual model results across many responses into data tables. The contents and number of output data tables depends on the model being fit.
Dispose Reports
Specifies that no individual model reports are shown and that they are removed from memory after fitting. When there are many thousands of responses, this option reduces computation time and saves memory.
Tip: Use this option with the Results in Data Table option to collect the results from the fitted models.
Note: The Options for Many Responses menu appears only when there are multiple responses in certain personalities.