Background/Aim. Frequent expression of negative affects, hostility and violent behavior in individuals suffering from posttraumatic stress disorder (PTSD) were recognized long ago, and have been retrospectively well documented in war veterans with PTSD who were shown to have an elevated risk for violent behavior when compared to both veterans without PTSD and other psychiatric patients. The aim of this study was to evaluate the accuracy of clinical prediction of violence in combat veterans suffering from PTSD. Methods. The subjects of this study, 104 male combat veterans with PTSD were assessed with the Historical, Clinical and Risk Management 20 (HCR-20), a 20-item clinicianrated instrument for assessing the risks for violence, and their acts of violence during one-year follow-up period were registered based on bimonthly check-up interviews. Results. Our findings showed that the HCR-20, as an actuarial measure, had good internal consistency reliability (α = 0.82), excellent interrater reliability (Interaclass Correlation ICC = 0.85), as well as excellent predictive validity for acts of any violence, non-physical violence or physical violence in the follow-up period (AUC = 0.82-0.86). The HCR-20 also had good interrater reliability (Cohen's kappa = 0.74), and acceptable predictive accuracy for each outcome criterion (AUC = 0.73-0.79). Conclusion. The results of this research confirm that the HCR-20 may also be applied in prediction of violent behavior in the population of patients suffering from PTSD with reliability and validity comparable with the results of previous studies where this instrument was administered to other populations of psychiatric patients.