Objective <p>Prediction of ovarian cancer prognosis is crucial for decision-making. In this study, we predicted the prognostic factors for ovarian cancer using parametric models and compared the accuracy of the results using bootstrap analysis.</p> Methods <p>In this study, 169 ovarian cancer patients registered at Malabar Cancer Centre were considered. The demographic, clinical, and treatment details were studied. The parametric distributions of exponential, lognormal, Weibull, and log-logistic were used for predicting the prognostic factors. The Akaike information criterion (AIC) was used to find the best-fitted model for the ovarian cancer survival data. The accuracy of the results was compared using bootstrap analysis.</p> Results <p>The average age of ovarian cancer patients was 54&#xa0;years. The majority (39%) of the patients were registered with stage 3 disease. Considering different parametric models, the lognormal distribution was found to be the best fit for the ovarian cancer survival data using Akaike information criteria. Using lognormal distribution, the predicted prognostic factors for ovarian cancers were stage and intention to treat.</p> Conclusion <p>The predicted prognostic factors for ovarian cancer survival data were composite stage and intention to treat, and the predicted factors were equivalent to the bootstrapped method revealing enhanced accuracy with 500 re-sampling iterations.</p>