한국 여성의 유방암 발생에 대한 코호트 효과

Objectives: The purpose of the study is to review various methods in age-period-cohort (APC) analysis and to provide a guideline to choose adequate method evaluating age, period, and cohort effects. We investigated age, period, and cohort effects of breast cancer incidence between 1999 and 2011 in Korea. Methods: Data on female breast cancer incidence from 1999 to 2011 were drawn from the Korean national statistical office. The 5-year period of data units (1999-2003, 2004-2008, and 2009-2011) and 5-year age interval (30-34-80-84) were used to calculate 13 birth cohorts. The graphical approach, constrained generalized linear model (CGLM) approach, median polish approach and intrinsic estimator (IE) approach were used to estimate age, period, and cohort effects. Results: The age and period effects existed significantly in CGLM, median polish, IE approaches. The breast cancer incidence increased along with age and period. However, there was a difference in cohort effect. For CGLM, positive cohort effects for recent cohort emerged significantly, but for the other methods, no significant effects shown. Conclusions: While previous studies have used the CGLM method, CGLM depends on arbitrary parameter constraints. Therefore, we suggest median polish approach or IE approach for analyzing APC models to obtain more accurate results.