Regression discontinuity was a valid design for dichotomous outcomes in three randomized trials

Regression discontinuity (RD) is a quasi-experimental design that may provide valid estimates of treatment effects in case of continuous outcomes. We aimed to evaluate validity and precision in the RD design for dichotomous outcomes.We performed validation studies in three large RCTs (CRASH, GUSTO and PROSPER). To mimic the RD design, we selected patients above and below a cut-off (e.g. age 75 years) randomized to treatment and control respectively. Adjusted logistic regression models using restricted cubic splines (RCS) and polynomials, and local logistic regression models estimated the odds ratio (OR) for treatment, with 95% confidence intervals to indicate precision.

Source: Journal of Clinical Epidemiology - February 24, 2018 Category: Epidemiology Authors: Nikki van Leeuwen, Hester F. Lingsma, Simon P. Mooijaart, Daan Nieboer, Stella Trompet, Ewout W. Steyerberg Source Type: research