evaluation of parametric models by the prediction error in colorectal cancer survival analysis

background and objectives: survival models are statistical technique to estimate or predict the overall time up to specific events. prediction is important in medical science and the accuracy of prediction is determined by a measurement, generally based on loss functions, called prediction error. the aim of this study is using parametric models to determine the factors influencing predicted survival time for patients with colorectal cancer (crc) and select the best model by predicting error’s technique. materials and methods: 600 colorectal cancer patients whom admitted to the cancer registry center of gastroenterology and liver disease research center, taleghani hospital, tehran, who were followed at least for 5 years and have completed information selected for this study. body mass index (bmi), sex, family history of crc, tumor site, stage of disease and histology of tumor included in the analysis. the survival time was compared by the log-rank test and multivariate analysis was carried out using parametric. for selecting the best model, the prediction error by apparent loss was used. result : log rank test showed better survival for females, bmi more than 25, patients with early stage at diagnosis and patients with colon tumor site. prediction error by apparent loss was estimated indicated that weibull model was the best one for multivariate analysis. bmi and stage were independent prognostic factors according to weibull model. conclusion : in this study, weibull regression showed a better fit according to prediction error. prediction error would be a criterion to select the best model with ability to make prediction of prognostic factors in survival analysis.