Effects of Multiple Forms of Information Bias on Estimated Prevalence of Suicide Attempts by Sexual Orientation: An Application of a Bayesian Misclassification Correction Method to Data from a Systematic Review

Abstract

Multiple epidemiologic studies demonstrate a disparity in suicide risk between sexual minority (lesbian, gay, bisexual) and heterosexual populations; however, both 'exposure' (sexual minority status) and outcome (suicide attempts) may be affected by information bias related to errors in self-reporting. We therefore applied a Bayesian misclassification correction method to account for possible information biases. A systematic literature search identified studies of lifetime suicide attempts in sexual minority and heterosexual adults, and frequentist meta-analysis was used to generate unadjusted estimates of relative risk. A Bayesian model accounting for prior information about sensitivity and specificity of exposure and outcome measures was used to adjust for misclassification biases. In unadjusted frequentist analysis, the relative risk of lifetime suicide attempt comparing sexual minority to heterosexual groups was 3.38 (95% confidence interval: 2.65, 4.32). In Bayesian re-analysis, the estimated prevalence was slightly reduced in heterosexual adults and increased in sexual minority adults, yielding a relative risk of 4.67 (95% credible interval: 3.94, 5.73). The disparity in lifetime suicide attempts between sexual minority and heterosexual adults is greater than previously estimated, when accounting for multiple forms of information bias. Additional research on the impact of information bias in studies of sexual minority health should be pursued.