Background: The Intergroup 0116 and the MAGIC trials changed clinical practice for resectable gastric cancer in the Western world. In these trials, overall survival improved with post-operative chemoradiotherapy (CRT) and perioperative chemotherapy (CT). Intention-to-treat analysis in the CRITICS trial of post-operative CT or post-operative CRT did not show a survival difference. The current study reports on the per-protocol (PP) analysis of the CRITICS trial. Patients and methods: The CRITICS trial was a randomized, controlled trial in which 788 patients with stage Ib–Iva resectable gastric or esophagogastric adenocarcinoma were included. Before start of preoperative CT, patients from the Netherlands, Sweden and Denmark were randomly assigned to receive post-operative CT or CRT. For the current analysis, only patients who started their allocated post-operative treatment were included. Since it is uncertain that the two treatment arms are balanced in such PP analysis, adjusted proportional hazards regression analysis and inverse probability weighted analysis were used to minimize the risk of selection bias and to estimate and compare overall and event-free survival. Results: Of the 788 patients, 478 started post-operative treatment according to protocol, 233 (59%) patients in the CT group and 245 (62%) patients in the CRT group. Patient and tumor characteristics between the groups before start of the post-operative treatment were not different. After a median follow-up of 6.7 years since the start of post-operative treatment, the 5-year overall survival was 57.9% (95% confidence interval: 51.4% to 64.3%) in the CT group versus 45.5% (95% confidence interval: 39.2% to 51.8%) in the CRT group (adjusted hazard ratio CRT versus CT: 1.62 (1.24-2.12), P = 0.0004). Inverse probability weighted analysis resulted in similar hazard ratios. Conclusion: After adjustment for all known confounding factors, the PP analysis of patients who started the allocated post-operative treatment in the CRITICS trial showed that the CT ...