This analysis was conducted to evaluate the independent relationship between survival and response to chemotherapy in advanced colorectal cancer. In order to correct for the guarantee time effect, patients dying before the response evaluation were excluded from the analyses. A previously constructed prognostic model containing 11 variables was applied to 324 patients. When the response categories were analysed together with the prognostic variables, it was found that a response was associated with a definite survival advantage (P < 0.001), whereas the influence of all the other variables decreased. The corrected survival advantage (relative progressive disease) was 11 months after a complete response, 6 months after a partial response and 4 months after stable disease. The survival advantage was of a similar magnitude when the analyses were repeated in an independent population comprising 198 patients in whom the prognostic model was extended to include also a set of laboratory values. The results show that a response to chemotherapy is associated with a longer survival also after correction for the guarantee time effect and the distribution of prognostic variables.