Florence Ashley, “Simpson’s Paradox in LGBTQ+ Policy: A Case Study” (2020) Sexuality Research and Social Policy
Simpson’s paradox refers to cases when trends found in the data disappear or inverse when groups are aggregated. Because reported data are used to guide policymaking, understanding and being able to identify instances of Simpson’s paradox are crucial to LGBTQ+ policy. This article offers a theoretical introduction to Simpson’s paradox before looking to a recent LGBT poverty study as an example of the paradox and of its dangers in the context of LGBTQ+ policy. The study found that the aggregate of cisgender bisexual women was much poorer than other cisgender LGB groups and comparable in poverty levels to trans respondents, but the pattern was largely absent from age-disaggregated data—the aggregate pattern emerged from the comparatively young age of cisgender bisexual women in the study. Some thoughts are offered on how researchers can best mitigate the impact of Simpson’s paradox on policymaking as well as on how data users should engage with statistics to avoid distortions in the decision-making process.