Dataset Information

Should age-period-cohort studies return to the methodologies of the 1970s?

ABSTRACT: Social scientists have recognized the importance of age-period-cohort (APC) models for half a century, but have spent much of this time mired in debates about the feasibility of APC methods. Recently, a new class of APC methods based on modern statistical knowledge has emerged, offering potential solutions. In 2009, Reither, Hauser and Yang used one of these new methods - hierarchical APC (HAPC) modeling - to study how birth cohorts may have contributed to the U.S. obesity epidemic. They found that recent birth cohorts experience higher odds of obesity than their predecessors, but that ubiquitous period-based changes are primarily responsible for the rising prevalence of obesity. Although these findings have been replicated elsewhere, recent commentaries by Bell and Jones call them into question - along with the new class of APC methods. Specifically, Bell and Jones claim that new APC methods do not adequately address model identification and suggest that "solid theory" is often sufficient to remove one of the three temporal dimensions from empirical consideration. They also present a series of simulation models that purportedly show how the HAPC models estimated by Reither et al. (2009) could have produced misleading results. However, these simulation models rest on assumptions that there were no period effects, and associations between period and cohort variables and the outcome were perfectly linear. Those are conditions under which APC models should never be used. Under more tenable assumptions, our own simulations show that HAPC methods perform well, both in recovering the main findings presented by Reither et al. (2009) and the results reported by Bell and Jones. We also respond to critiques about model identification and theoretically-imposed constraints, finding little pragmatic support for such arguments. We conclude by encouraging social scientists to move beyond the debates of the 1970s and toward a deeper appreciation for modern APC methodologies.

SUBMITTER: Reither EN

PROVIDER: S-EPMC4357521 | biostudies-literature | 2015 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Should age-period-cohort studies return to the methodologies of the 1970s?

Reither Eric N EN Masters Ryan K RK Yang Yang Claire YC Powers Daniel A DA Zheng Hui H Land Kenneth C KC

Social science & medicine (1982) 20150113

Social scientists have recognized the importance of age-period-cohort (APC) models for half a century, but have spent much of this time mired in debates about the feasibility of APC methods. Recently, a new class of APC methods based on modern statistical knowledge has emerged, offering potential solutions. In 2009, Reither, Hauser and Yang used one of these new methods - hierarchical APC (HAPC) modeling - to study how birth cohorts may have contributed to the U.S. obesity epidemic. They found t ...[more]

PMID: 25617033

Similar Datasets

Project description:Background Tuberculosis (TB) poses a severe public health challenge in China and worldwide. This study evaluated the effects of age, period, and birth cohort on reported incidence trends of TB based on population and refined the characteristics of high-risk groups. Methods Aggregate data that reported pulmonary tuberculosis (PTB) cases from China Tuberculosis Management Information System (TBIMS) from 2006 to 2020 were used to analyze effect coefficients through the age–period–cohort (APC) model based on intrinsic estimator (IE) method, and converted them into relative risk (RR) to estimate trends. Results A total of 14.82 million cases of PTB were reported in China from 2006 to 2020, showing a continuous downward trend. The reporting rate increased with age by age group, with 70–74 years old being 2–3 times higher than that in 20–24 years old. APC analysis model showed that age effects were bimodal in 20–24 years old [RR = 2.29, 95% confidence interval (CI): 1.73–3.03] and 70–74 years old (RR = 1.95, 95% CI: 1.67–2.27), and lower than the overall average in the groups under 15 years old. Stratified results showed that the risk was higher for women under age 40 than men and higher for men over 40. The risk was higher in urban than in rural areas under 30 years old and slightly higher in rural than in urban between 30 and 64 years old. The risk for 15–34 years old was significantly higher in the east than in other regions. The period effects showed a decreasing trend, and the risk was higher in rural in recent years. Except for cohorts born in 1961–1965 and 2001–2005, where the RR increased, the later the cohort was born, the lower the risk. The cohort 1926–1930 in eastern had the highest risk (RR = 3.49, 95% CI: 2.44–4.98). Conclusions The reported incidence of PTB continued to decline in China from 2006 to 2020. The young (20–24 years old) and the elderly (70–74 years old) were equally at high risk. There were differences in the age, period and cohort effects on PTB incidence among gender, urban–rural and regions. Our findings better reflected the characteristics of high-risk populations, thus contributing to the development of timely and effective intervention strategies, and providing clues for etiological research. Graphical abstract Supplementary Information The online version contains supplementary material available at 10.1186/s40249-022-01009-4.

Dataset Information

Should age-period-cohort studies return to the methodologies of the 1970s?

Publications

Should age-period-cohort studies return to the methodologies of the 1970s?

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets