Using Gamma and Quantile Regressions to Explore the Association between Job Strain and Adiposity in the ELSA-Brasil Study: Does Gender Matter?

Abstract

This paper explores the association between job strain and adiposity, using two statistical analysis approaches and considering the role of gender. The research evaluated 11,960 active baseline participants (2008-2010) in the ELSA-Brasil study. Job strain was evaluated through a demand-control questionnaire, while body mass index (BMI) and waist circumference (WC) were evaluated in continuous form. The associations were estimated using gamma regression models with an identity link function. Quantile regression models were also estimated from the final set of co-variables established by gamma regression. The relationship that was found varied by analytical approach and gender. Among the women, no association was observed between job strain and adiposity in the fitted gamma models. In the quantile models, a pattern of increasing effects of high strain was observed at higher BMI and WC distribution quantiles. Among the men, high strain was associated with adiposity in the gamma regression models. However, when quantile regression was used, that association was found not to be homogeneous across outcome distributions. In addition, in the quantile models an association was observed between active jobs and BMI. Our results point to an association between job strain and adiposity, which follows a heterogeneous pattern. Modelling strategies can produce different results and should, accordingly, be used to complement one another.

Keywords: adiposity; body mass index; job strain; quantile regression models; waist circumference.

Figure 1

Association between job strain and adiposity (BMI and WC) in adjusted quantile regression models among women. ELSA-Brasil, 2008–2010 (n = 6252). On the horizontal axes are the BMI and WC distribution percentiles; the vertical axes show the values of the coefficients estimated. The dashed parallel line represents the null value (zero), and a solid line stands for quantile estimates. The grey area surrounding the solid line represents the 95% CI for the quantile estimates. The coefficients are adjusted by age, schooling, per capita family income, hours worked weekly, and study center for BMI; and by age, schooling, per capita family income, and study center for WC.

Figure 2

Association between job strain and adiposity (BMI and WC) in adjusted quantile regression models among men. ELSA-Brasil, 2008–2010 (n = 5708). On the horizontal axes are the BMI and WC distribution percentiles; the vertical axes show the values of the coefficients estimated. The dashed parallel line represents the null value (zero), and a solid line stands for quantile estimates. The grey area surrounding the solid line represents the 95% CI for the quantile estimates. The coefficients are adjusted by age, marital status, and study center for BMI; and by age, marital status, schooling, hours worked weekly, and study center for WC.