Background Most research is affected by differential participation, where individuals who do not participate have different characteristics to those who do. This is often assumed to induce selection bias. However, selection bias only occurs if the exposure-outcome association differs for participants compared to non-participants. We empirically demonstrate that selection bias does not necessarily occur when there is varying participation in a study.
Methods We used data from the first three waves of the longitudinal Survey of Family, Income and Employment (SoFIE). We examined baseline associations of labour market activity and education with self-rated health using logistic regression in four participation samples: A) the original sample at year one (N=22 265); B) drop outs over 3 years (n=3880); C) those remaining in the sample over 3 years (n=18 350); and D) those (year 3) consenting to further data linkage (n=14 340).
Results Loss to follow-up was more likely among lower socioeconomic groups and those with poorer health. However, for labour market activity and education, the odds of reporting fair/poor health were similar across all samples, including after adjustment for sociodemographic variables. Thus, there was little evidence of selection bias.
Conclusions Differential loss to follow-up did not lead to selection bias in the association between socioeconomic measures and self-rated health. When assessing the possibility of selection bias researchers should consider whether differential participation affects the exposure-outcome association, not just participation by exposure or outcome separately.
Statistics from Altmetric.com
If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.