Model Fit Options
In the Generalized Linear Mixed Model report, each model fit report has a red triangle menu that contains the following options:
Model Reports
Enables you to customize the reports that are shown for the specified model fit. The reports that are available are determined by the type of analysis that you conduct. Several of these reports are shown by default.
Fit Statistics
Shows or hides a report for model fit statistics. See Fit Statistics and Model Summary.
Random Effects Covariance Parameter Estimates
(Available only when there are random effects specified in the launch window.) Shows or hides a report of random effects covariance parameter estimates. See Random Effects Covariance Parameter Estimates.
Fixed Effects Parameter Estimates
Shows or hides a report of fixed effects parameter estimates. See Fixed Effects Parameter Estimates.
Random Coefficients
(Available only when there are random effects specified in the launch window.) Shows or hides a report of random coefficients. See Random Coefficients.
Random Effects Predictions
(Available only when there are random effects specified in the launch window.) Shows or hides a report of random effect predictions. For each random effect in the model, the report provides an estimate known as the best linear unbiased predictor (BLUP), its standard error, degrees of freedom, and a Satterthwaite-based confidence interval. Estimation of the standard errors requires calculation of the BLUP covariance matrix, which can be time-intensive. If the calculation time is noticeable, a progress bar appears.
Indicator Parameterization Estimates
(Available only when there are nominal columns among the fixed effects and the model contains an intercept.) Shows or hides the Indicator Function Parameterization report. This report gives parameter estimates for the fixed effects based on a model where nominal fixed effect columns are coded using indicator (SAS GLM) parameterization and are treated as continuous. Ordinal columns remain coded using the usual JMP coding scheme. The SAS GLM and JMP coding schemes are described in The Factor Models.
Caution: Standard errors, t-ratios, and other results given in the Indicator Function Parameterization report differ from those in the Parameter Estimates report. This is because the estimates are estimating different parameters.
Fixed Effects Tests
(Available only for models that contain at least one fixed effect.) Shows or hides the tests of fixed effects. See Fixed Effects Tests.
Multiple Comparisons
(Available only for models that contain at least one categorical fixed effect.) Opens the Multiple Comparisons launch window which provides various methods for comparing least squares means of main effects and interaction effects. For more information about the multiple comparisons options, see “Multiple Comparisons”.
Once you click OK in the Multiple Comparisons launch window, a Multiple Comparisons report is added to the GLMM report window. A new Multiple Comparisons report is added each time you use the Multiple Comparisons option. Each Multiple Comparisons report contains estimates of the least squares means, standard error, and a 95% confidence interval on the original data scale. The report also contains estimates of the means or probabilities, standard errors, and a confidence interval on the inverse link scale. You can change the α level in the Fit Model window by selecting Set Alpha Level from the Model Specification red triangle menu. This report is followed by the multiple comparisons test that you select. The All Pairwise Comparisons report provides equivalence tests.
Diagnostic Bundle
(Available only if Poisson is selected as the Distribution and there are no random effects in the model.) Shows or hides a set of four graphs including a plot of residuals by predicted values, residuals by row number, a histogram of the residuals, and a histogram of the probability of observing a response larger than the observed response.
The Fitted Probability of Observing a Larger Response histogram helps you assess goodness of fit of the model. The “correct” model should display an approximately uniform distribution of values.
Conditional Diagnostic Bundle
(Available only if Poisson is selected as the Distribution and there are random effects in the model.) Shows or hides a set of four graphs including a plot of residuals by predicted values, residuals by row number, a histogram of the residuals, and a histogram of the probability of observing a response larger than the observed response.
The Fitted Probability of Observing a Larger Response histogram helps you assess goodness of fit of the model. The “correct” model should display an approximately uniform distribution of values.
Marginal Model Inference
Produces profilers that are based on marginal predicted values. The predicted values are shown in terms of counts for Poisson models and percents for binomial models.
Profiler
Shows or hides a prediction profiler to examine the relationship between the response and model terms, without accounting for random effects.
Contour Profiler
Shows or hides a contour profiler to examine the relationship between the response and model terms, without accounting for random effects.
Surface Profiler
Shows or hides a surface profiler to examine the relationship between the response and model terms, without accounting for random effects.
Conditional Model Inference
(Available only when there are random effects specified in the launch window.) Produces profilers that are based on conditional predicted values. Conditional predicted values reflect both fixed and random effects. The predicted values are shown in terms of counts for Poisson models and percents for binomial models.
Conditional Profiler
Shows or hides a prediction profiler to examine the relationship between the response and the model terms, accounting for random effects.
Conditional Contour Profiler
Shows or hides a contour profiler to examine the relationship between the response and the model terms, accounting for random effects.
Conditional Surface Profiler
Shows or hides a surface profiler to examine the relationship between the response and the model terms, accounting for random effects.
Covariance and Correlation Matrices
Contains options to view the covariance and correlation matrices that are associated with the model.
Covariance of Fixed Effects
Shows or hides the covariance matrix for the fixed effects in the model.
Covariance of Covariance Parameters
Shows or hides the covariance matrix for the random effects in the model.
Covariance of All Parameters
Shows or hides the covariance matrix for all effects in the model.
Correlation of Fixed Effects
Shows or hides the correlation matrix for the fixed effects in the model.
Save Columns
Contains options to save various model results as one or more new columns in the data table. The predicted values are saved in terms of counts for Poisson models and percents for binomial models.
Prediction Formula
Creates a new column called Pred Formula <colname> that contains both the formula and the marginal mean predicted values. A Predicting column property is added, noting the source of the prediction.
Standard Error of Predicted
Creates a new column called StdErr Pred <colname> that contains standard errors for the predicted marginal mean responses.
Mean Confidence Interval
Creates two new columns called Lower 95% Mean <colname> and Upper 95% Mean <colname>. These columns contain the lower and upper 95% confidence limits for the mean response. These intervals include the variation in the estimation, but not in the response. You can change the α level in the Fit Model launch window by selecting Set Alpha Level from the Model Specification red triangle menu.
Save Residual Formula
(Not available if Binomial is selected as the Distribution.) Creates a new column called Residual <colname> that contains a formula for the residuals, given in the form Y minus the prediction formula.
Conditional Prediction Formula
(Available only when there are random effects specified in the launch window.) Creates a new column called Cond Pred Formula <colname> that contains both the formula and the conditional mean predicted values. A Predicting column property is added, noting the source of the prediction.
Standard Error of Conditional Predicted
(Available only when there are random effects specified in the launch window.) Creates a new column called StdErr Cond Pred <colname> that contains standard errors for the predicted conditional mean responses.
Conditional Mean CI
(Available only when there are random effects specified in the launch window.)Creates two new columns called Lower 95% Cond Mean <colname> and Upper 95% Cond Mean <colname>. These columns contain the lower and upper 95% confidence limits for the expected value from conditional prediction. The confidence intervals include random effect estimates for models with random effects. You can change the α level in the Fit Model launch window by selecting Set Alpha Level from the Model Specification red triangle menu.
Save Conditional Residual Formula
(Not available if Binomial is selected as the Distribution or if there are no random effects in the model.) Creates a new column called Cond Residual <colname> that contains the observed response values minus their conditional mean predicted values.
Save Simulation Formula
(Not available when a By variable is specified in the Fit Model launch window.) Saves a column to the data table that contains a formula that generates simulated values using the estimated parameters for the model that you fit. This column can be used in the Simulate utility as a Column to Switch In. See Simulate in Basic Analysis.