Abstract
Abstract We develop an age-period-cohort model for repeated cross-section data with individual covariates, which identifies the non-linear effects of age, period and cohort. This is done for both continuous and binary dependent variables. The age, period and cohort effects in the model are represented by a parametrization with freely varying parameters that separates the identified non-linear effects and the unidentifiable linear effects. We develop a test of the parametrization against a more general ‘time-saturated’ model. The method is applied to analyse the obesity epidemic in England using survey data. The main non-linear effects we find in English obesity data are age-related among women and cohort-related among men.
Highlights
We use repeated cross-section data to examine the socio-demographic determinants of obesity in England, using both continuous and binary measures of obesity
We find that English obesity data can be parsimoniously described using an age-c ohort (AC) or cohort-drift (Cd) model for men and an age- drift (Ad) model for women
We develop a test of the reparametrized APC model against a more general model, where each cell in the AC array has its own parameter
Summary
We use repeated cross-section data to examine the socio-demographic determinants of obesity in England, using both continuous and binary measures of obesity. The proposed models are generalized linear models (GLMs) for repeated cross-sectional data with age, period and cohort (APC) effects and individual covariates. For an individual h with age i and cohort k, observed in period j = i + k−1, the linear predictor will include the APC component ik = i + j + k +. We proceed to introduce generalized linear models with APC effects for individual level data. It should be recognized that overall effect of age or cohort on log BMI combines the identified concave non-linear effect with an unidentified linear effect. The logit coefficients are broadly speaking in line with those reported for log BMI
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Journal of the Royal Statistical Society Series A: Statistics in Society
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
