You can model multiple causes of failure in a system using the Survival platform. For example, suppose that a manufacturing process has several stages and the failure of any stage causes a failure of the whole system. If the different causes are independent, the failure times can be modeled by an estimation of the survival distribution for each cause. A censored estimation is undertaken for a given cause by treating all the event times that are not from that cause as censored observations.
The Competing Causes red triangle menu contains the following options:
Omit Causes
Enables you to remove specific cause values from the analysis. The survival estimates are automatically recalculated. This option can be used to illustrate the alternative where specific causes are no longer hazardous.
Save Cause Coordinates
Saves a new column to the original data table. The new column is calculated as log(–log(Surv)). This value is often plotted against the time variable for the different values of a grouping variable, such as the code for type of failure.
Weibull Lines
Shows or hides Weibull lines in the survival plot.
Hazard Plot
Shows or hides a plot of the hazard functions for the data based on the competing causes analysis.
Simulate
Creates a new data table that contains simulated time and cause information. The fitted Weibull distribution is used to simulate the new data.