Fitting of Age-period-Cohort Models to Study time trends in the incidence of Cancer of the Larynx

Abstract

In this paper, the date on incidence of cancer of the larynx for SC011end Over the period 1960-1989 are used to fir age-period-cohort models presented by Clayton and Schiffters (1967), Clecarti and La Vecchia (1987) and Robertson and Boyle (1986,1987) to study the fernporat variation in the incidence of cancer in the larynx_ For females any of the two factor models is sufficient to represent the grouped data but the age-cohort model IS best. The method used by Robertson and Boyle suggest that full age-period-cohort Model should be used to represent the male data with individual records on males and age-cohort sufficiently represents the female data in the form of 3 way table data with individual records on females. For all the three methods, the age•cohort model is found to represent the data on incidence of cancer of the larynx for Scottish females, The main conclusion is that whilie the incidence rates are higher in older people the increase ever time is mainly a result of cohort effects,