Survival Analysis Models for Estimating and Predicting the Risks of Confession of Criminal Defendants

In this paper, we presented the results of the application of survival analysis models for estimating and forecasting the risks of pleading guilty to criminal offenses under conditions of incomplete data. The technique of life tables was used to calculate the probability of guilty pleas by suspects at a specific stage (time interval) of the trial. Significant differences in the confessions of adults and minors were revealed. The Kaplan-Meier model was used to determine the probability of obtaining confessional evidence after the investigation was completed. A Cox proportional hazards model was built to establish the interconnection between the stages of the court proceedings at which the accused gives confessions, the duration of the trial and the fact that the accused has reached the age of majority.