Evolution of obesity prevalence in France: an age-period-cohort analysis

Abstract

Background: A rapid increase in the prevalence of obesity has been reported in France since 1990. We investigated the impact of birth cohort on the changes in obesity prevalence after taking into account age and survey period.

Methods: We analyzed data from 4 national surveys in 1997, 2000, 2003, and 2006. For each survey, self-reported data on weight and height were recorded on mailed questionnaires sent to a sample of 20,000 households, representative of the French population. Obesity was defined according to World Health Organization criteria as body mass index >or=30 kg/m. We modeled the prevalence of obesity using logistic regression with age, cohort, and period as explanatory variables. As these variables are linearly dependent, only nonlinear effects can be estimated uniquely and interpreted, after including specific chosen constraints in the models.

Results: There was a progressive increase in the prevalence of obesity between 1997 and 2006, attributable either to a period effect or to a cohort effect. There was a substantial departure from a linear trend for the cohort effect only, which seemed to be stronger in women: there was an acceleration in the prevalence of obesity with birth cohort for individuals born after the mid-1960s, in both sexes.

Conclusions: Our results are consistent with previous studies in other countries. Compared with older generations, men and women born in the late 1960s may have been subject to early exposures that increased their lifelong susceptibility to obesity.

FIGURE 1

Data from the 1997 and 2000 surveys for women in a Lexis diagram: we display the percentage of obese (in bold) and the total number of women for all 3-year age groups. The squares in grey correspond to women in the same birth cohort in the four different survey periods.

FIGURE 2

The prevalence of obesity (in 3-year age groups) by period in men and women.

FIGURE 3

The prevalence of obesity by age (3-year age groups), separately in each 3-year birth cohort in men and women. For example, at 40 years of age, women born in 1966 had a higher prevalence than women born in 1957 (15.0% vs 7.9%, respectively, as shown by dotted lines).

FIGURE 4

Odds Ratios (pointwise 95% confidence intervals) for birth cohort effect on obesity prevalence in reference to the cohort born in 1957, in the year 1997 (reference survey period), in men and women. A., combined drift and nonlinear effect and B., nonlinear effect.