Regression Models for Censored Data - Quick Tab

Select the Quick tab of the Regression Models for Censored Data dialog box to access options to specify one of four different regression models: Cox's proportional hazard regression, exponential regression, lognormal linear regression, and normal linear regression.

Model. Use the Model drop-down box to choose from the four different regression models available in Survival Analysis: Proportional hazard (Cox) regression, Exponential regression, Lognormal regression, and Normal regression.

Variables (survival times, indep., censoring, [optional] grouping). Click the Variables button to display the standard variable selection dialog box for specifying the variable(s) with the survival times, a list of independent variables (covariates), the censoring indicator variable, and an optional grouping variable (for a stratified, by-group analysis).

Specifying survival times. There are three ways to specify survival times. Select one variable with survival times (e.g., number of weeks surviving), select two variables containing the start and end dates respectively, or select six variables containing dates. Specifically, these variables should contain the month (1 to 12), day (1 to 31), and year when the particular observation began (e.g., when the patient was admitted to the hospital), and the month, day, and year when the observation was terminated (due to death/failure or censoring, e.g., when a patient was dismissed from the hospital). While processing the data, Survival Analysis will compute the number of days that elapsed between dates and perform the analysis on this measure. Note that if the value of the year is less than 100, Statistica will automatically assume that the year refers to the 20th century; for example, the year 88 will be converted to 1988. The censoring indicator variable should contain the integer codes or text labels that uniquely identify complete and censored observations.

The (optional) variable with group codes should contain the integer codes or text labels that uniquely identify to which group (sample) each observation belongs. If no grouping variable is specified, a regular analysis will be performed on all data. If a variable is specified here, then a stratified analysis will be performed. In a stratified analysis, separate regression models are first fit to each group and the log-likelihoods for those models are summed up. This log-likelihood is then compared to that of the overall model (collapsed across groups).

Code for complete responses. Enter the codes or text labels that were used in the censoring indicator variable to uniquely identify complete (uncensored) observations in the Code for complete responses field. To review all codes in the respective variable, double-click on this field (or press the F2 key on your keyboard) to display the Variable dialog box.  

Code for censored responses. Enter the codes or text labels that were used in the censoring indicator variable to uniquely identify incomplete (censored) observations in the Code for censored responses field. To review all codes in the respective variable, double-click on this field (or press the F2 key on your keyboard) to display the Variable dialog box.  

Codes (for groups). Click the Codes button to display the Select Codes for Grouping Variable dialog box, which is used to specify the codes or text labels that were used in the grouping variable to uniquely identify to which one of the two groups each observation belongs. To review all codes in the respective variable, double-click on this field. The default selection is all codes.