Estimation of cancer survival from population-based registries. Data on hispanics

Cancer prevalence is the proportion of people in a population diagnosed with cancer in the past and still alive. One way to estimate prevalence is via population-based registries, where data on diagnosis and life status of all incident cases occurring in the covered population are collected. In Gigli and Simonetti (2002) some methods regarding the fitting of in- cidence and survival models to data collected by the SEER9 and SEER11 registries in the United States on various cancer sites, various race/ethnicity categories and two sexes, were applied. However, data scarcity for hispanic patients in SEER11 dataset caused an unsatisfactory survival modelling, therefore further investigation has been performed in this paper. The paper is organized as follows: section 1 provides the general setting for the estimation of survival models; section 2 proposed two methods to estimate the survival parameters, when data is scarse; section 3 examines the performance of the methods proposed by graphical evaluation; finally in appendix the results are reported in a table and the fitting of the models is shown via plots.