Leah M. Smith

Background: The regression discontinuity design (RDD) is a quasi-experimental approach used to avoid confounding bias in the assessment of new policies and interventions. It is applied specifically in situations where individuals are assigned to a policy/intervention based on whether they are above or below a pre-specified cut-off on a continuously measured variable, such as birth date, income or weight. The strength of the design is that, provided individuals do not manipulate the value of this variable, assignment to the policy/intervention is considered as good as random for individuals close to the cut-off. Despite its popularity in fields like economics, the RDD remains relatively unknown in epidemiology where its application could be tremendously useful. Methods: In this paper, we provide a practical introduction to the RDD for health researchers, describe four empirically testable assumptions of the design and offer strategies that can be used to assess whether these assumptions are met in a given study. For illustrative purposes, we implement these strategies to assess whether the RDD is appropriate for a study of the impact of human papillomavirus vaccination on cervical dysplasia. Results: We found that, whereas the assumptions of the RDD were generally satisfied in our study context, birth timing had the potential to confound our effect estimate in an unexpected way and therefore needed to be taken into account in the analysis. Conclusions: Our findings underscore the importance of assessing the validity of the assumptions of this design, testing them when possible and making adjustments as necessary to support valid causal inference.

BACKGROUND: Despite widespread promotion of quadrivalent human papillomavirus (qHPV) vaccination for young girls, there is limited information on the vaccine’s real-world effectiveness and none on the effectiveness of qHPV vaccination programs. We assessed the impact of the qHPV vaccine and Ontario’s grade 8 qHPV vaccination program on cervical dysplasia and anogenital warts (AGW). METHODS: By using administrative health databases of Ontario, Canada, we identified a population-based retrospective cohort of girls in grade 8 before (2005/2006–2006/2007) and after (2007/2008–2008/2009) program implementation. Vaccine exposure was ascertained in grades 8 to 9 and outcomes in grades 10 to 12. A quasi-experimental approach known as regression discontinuity was used to estimate absolute risk differences (RDs), relative risks (RRs), and 95% confidence intervals (CIs) attributable to vaccination and program eligibility (intention-to-treat analysis). RESULTS: The cohort comprised 131 781 ineligible and 128 712 eligible girls (n = 260 493). We identified 2436 cases of dysplasia and 400 cases of AGW. Vaccination significantly reduced the incidence of dysplasia by 5.70 per 1000 girls (95% CI −9.91 to −1.50), corresponding to a relative reduction of 44% (RR 0.56; 95% CI 0.36 to 0.87). Program eligibility also had a significant protective effect on dysplasia: RD −2.32/1000 (95% CI −4.02 to −0.61); RR 0.79 (95% CI 0.66 to 0.94). Results suggested decreases in AGW attributable to vaccination (RD −0.83/1000, 95% CI −2.54 to 0.88; RR 0.57, 95% CI 0.20 to 1.58) and program eligibility (RD −0.34/1000, 95% CI −1.03 to 0.36; RR 0.81, 95% CI 0.52 to 1.25). CONCLUSIONS: This study provides strong evidence of the early benefits of qHPV vaccination among girls aged 14 to 17 years, offering additional justification for not delaying vaccination.