Model Fitting: Logistic Regression

Output Variables Tab

You can use the Output Variables tab to add analysis variables to the data table. (See Figure 23.13.) If you request a plot that uses one of the output variables, then that variable is automatically created even if you did not explicitly select the variable on the Output Variables tab.

The following list describes each output variable and indicates how the output variable is named. Y represents the name of the response variable. If you use events/trials syntax, then Y represents the name of the events variable.

Proportions for events/trials


adds a variable named Proportion_$ET$, where E is the name if the events variable and T is the name of the trials variable. The value of the variable is the ratio $E/T$. This variable is added only when you use events/trials syntax.

Predicted probabilities


adds predicted probabilities. The variable is named LogiP_Y.

Confidence limits for predicted probabilities


adds 95% confidence limits for the predicted probabilities. The variables are named LogiLclm_Y and LogiUclm_Y.

Linear predictor (log odds)


adds the linear predictor values. The variable is named LogiXBeta_Y.

Pearson chi-square residuals


adds the Pearson chi-square residuals. The variable is named LogiChiSqR_Y.

Deviance residuals


adds the deviance residuals. The variable is named LogiDevR_Y.

Confidence interval displacement (C)


adds the confidence interval displacement diagnostic, C. The variable is named LogiC_Y.

Scaled confidence interval displacement (CBAR)


adds the confidence interval displacement diagnostic, $\bar{C}$. The variable is named LogiCBar_Y.

Leverage (H)


adds the leverage statistic. The variable is named LogiH_Y.

DIFCHISQ (influence on chi-square goodness-of-fit)


adds the change in the chi-square goodness-of-fit statistic that is attributed to deleting the individual observation. The variable is named LogiDifChiSq_Y.

DIFDEV (influence on deviance)


adds the change in the deviance that is attributed to deleting the individual observation. The variable is named LogiDifDev_Y.

DFBETAS (influence on coefficients)


adds m variables, where m is the number of parameters in the model. The variables are scaled measures of the change in each parameter estimate and are calculated by deleting the ith observation. Large probabilities of DFBETAS indicate observations that are influential in estimating a given parameter. The variables are named DFBETA_X, where X is the name of an interval regressor (including the intercept). For classification variables, the variables are named DFBETA_$CL$, where C is the name of the variable and L represents a level.

Figure 23.13: The Output Variables Tab

The Output Variables Tab