TY - JOUR
T1 - The regression discontinuity design showed to be a valid alternative to a randomized controlled trial for estimating treatment effects
AU - Maas, Iris L.
AU - Nolte, Sandra
AU - Walter, Otto B.
AU - Berger, Thomas
AU - Hautzinger, Martin
AU - Hohagen, Fritz
AU - Lutz, Wolfgang
AU - Meyer, Björn
AU - Schröder, Johanna
AU - Späth, Christina
AU - Klein, Jan Philipp
AU - Moritz, Steffen
AU - Rose, Matthias
N1 - Publisher Copyright:
© 2016 Elsevier Inc.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2017/2/1
Y1 - 2017/2/1
N2 - Objectives To compare treatment effect estimates obtained from a regression discontinuity (RD) design with results from an actual randomized controlled trial (RCT). Study Design and Setting Data from an RCT (EVIDENT), which studied the effect of an Internet intervention on depressive symptoms measured with the Patient Health Questionnaire (PHQ-9), were used to perform an RD analysis, in which treatment allocation was determined by a cutoff value at baseline (PHQ-9 = 10). A linear regression model was fitted to the data, selecting participants above the cutoff who had received the intervention (n = 317) and control participants below the cutoff (n = 187). Outcome was PHQ-9 sum score 12 weeks after baseline. Robustness of the effect estimate was studied; the estimate was compared with the RCT treatment effect. Results The final regression model showed a regression coefficient of −2.29 [95% confidence interval (CI): −3.72 to −.85] compared with a treatment effect found in the RCT of −1.57 (95% CI: −2.07 to −1.07). Conclusion Although the estimates obtained from two designs are not equal, their confidence intervals overlap, suggesting that an RD design can be a valid alternative for RCTs. This finding is particularly important for situations where an RCT may not be feasible or ethical as is often the case in clinical research settings.
AB - Objectives To compare treatment effect estimates obtained from a regression discontinuity (RD) design with results from an actual randomized controlled trial (RCT). Study Design and Setting Data from an RCT (EVIDENT), which studied the effect of an Internet intervention on depressive symptoms measured with the Patient Health Questionnaire (PHQ-9), were used to perform an RD analysis, in which treatment allocation was determined by a cutoff value at baseline (PHQ-9 = 10). A linear regression model was fitted to the data, selecting participants above the cutoff who had received the intervention (n = 317) and control participants below the cutoff (n = 187). Outcome was PHQ-9 sum score 12 weeks after baseline. Robustness of the effect estimate was studied; the estimate was compared with the RCT treatment effect. Results The final regression model showed a regression coefficient of −2.29 [95% confidence interval (CI): −3.72 to −.85] compared with a treatment effect found in the RCT of −1.57 (95% CI: −2.07 to −1.07). Conclusion Although the estimates obtained from two designs are not equal, their confidence intervals overlap, suggesting that an RD design can be a valid alternative for RCTs. This finding is particularly important for situations where an RCT may not be feasible or ethical as is often the case in clinical research settings.
UR - http://www.scopus.com/inward/record.url?scp=85010518301&partnerID=8YFLogxK
U2 - 10.1016/j.jclinepi.2016.11.008
DO - 10.1016/j.jclinepi.2016.11.008
M3 - Journal articles
C2 - 27865902
AN - SCOPUS:85010518301
SN - 0895-4356
VL - 82
SP - 94
EP - 102
JO - Journal of clinical epidemiology
JF - Journal of clinical epidemiology
ER -