Abstract
Risk factors may affect the variability as well as the mean of health outcomes. Understanding this can aid aetiological understanding and public health translation, in that interventions which shift the outcome mean and reduce variability are preferable to those which affect only the mean. However, few statistical tools routinely test for differences in variability. We used GAMLSS (Generalised Additive Models for Location, Scale and Shape) to investigate how multiple risk factors (sex, childhood social class and midlife physical inactivity) related to differences in health outcome mean and variability. The 1970 British birth cohort study was used, with body mass index (BMI; N = 6,025) and mental wellbeing (Warwick-Edinburgh Mental Wellbeing Scale; N = 7,128) as outcomes. For BMI, males had a 2% higher mean than females yet 28% lower variability. Lower social class and physical inactivity were associated with higher mean and higher variability (6% and 13% respectively). For mental wellbeing, gender was not associated with the mean while males had 4% lower variability. Lower social class and physical inactivity were associated with lower mean yet higher variability (−7% and 11% respectively). This provides empirical support for the notion that risk factors can reduce or increase variability in health outcomes. Such findings may be explained by heterogeneity in the causal effect of each exposure, by the influence of other (typically unmeasured) variables, and/or by measurement error. This underutilised approach to the analysis of continuously distributed outcomes may have broader utility in epidemiological, medical, and psychological sciences.
Publisher
Cold Spring Harbor Laboratory
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献