TY - JOUR
T1 - Effect Estimates in Randomized Trials and Observational Studies
T2 - Comparing Apples With Apples
AU - Lodi, Sara
AU - Phillips, Andrew
AU - Lundgren, Jens
AU - Logan, Roger
AU - Sharma, Shweta
AU - Cole, Stephen R
AU - Babiker, Abdel
AU - Law, Matthew
AU - Chu, Haitao
AU - Byrne, Dana
AU - Horban, Andrzej
AU - Sterne, Jonathan
AU - Porter, Kholoud
AU - Sabin, Caroline A
AU - Costagliola, Dominique
AU - Abgrall, Sophie
AU - Gill, Michael
AU - Touloumi, Giota
AU - Pacheco, Antonio Guilherme
AU - van Sighem, Ard
AU - Reiss, Peter
AU - Bucher, Heiner C
AU - Giménez, Alexandra
AU - Jarrin, Inmaculada
AU - Wittkop, Linda
AU - Meyer, Laurence
AU - Pérez-Hoyos, Santiago
AU - Justice, Amy
AU - Neaton, James D.
AU - Hernán, Miguel A
PY - 2019/5/7
Y1 - 2019/5/7
N2 - Effect estimates from randomized trials and observational studies may not be directly comparable because of differences in study design, other than randomization, and in data analysis. We propose a three-step procedure to facilitate meaningful comparisons of effect estimates from randomized trials and observational studies: 1) harmonization of the study protocol (eligibility criteria, treatment strategies, outcome, start and end of follow-up, causal contrast) so that the studies target the same causal effect, 2) harmonization of the data analysis to estimate the causal effect, and 3) sensitivity analyses to investigate the impact of discrepancies that could not be accounted for in the harmonization process. To illustrate our approach, we compared estimates of the effect of immediate with deferred initiation of antiretroviral therapy (ART) in HIV-positive individuals from the START randomized trial and the observational HIV-CAUSAL Collaboration.
AB - Effect estimates from randomized trials and observational studies may not be directly comparable because of differences in study design, other than randomization, and in data analysis. We propose a three-step procedure to facilitate meaningful comparisons of effect estimates from randomized trials and observational studies: 1) harmonization of the study protocol (eligibility criteria, treatment strategies, outcome, start and end of follow-up, causal contrast) so that the studies target the same causal effect, 2) harmonization of the data analysis to estimate the causal effect, and 3) sensitivity analyses to investigate the impact of discrepancies that could not be accounted for in the harmonization process. To illustrate our approach, we compared estimates of the effect of immediate with deferred initiation of antiretroviral therapy (ART) in HIV-positive individuals from the START randomized trial and the observational HIV-CAUSAL Collaboration.
U2 - 10.1093/aje/kwz100
DO - 10.1093/aje/kwz100
M3 - Article (Academic Journal)
C2 - 31063192
JO - American Journal of Epidemiology
JF - American Journal of Epidemiology
SN - 0002-9262
ER -