Effect Estimates in Randomized Trials and Observational Studies: Comparing Apples With Apples

Sara Lodi, Andrew Phillips, Jens Lundgren, Roger Logan, Shweta Sharma, Stephen R Cole, Abdel Babiker, Matthew Law, Haitao Chu, Dana Byrne, Andrzej Horban, Jonathan Sterne, Kholoud Porter, Caroline A Sabin, Dominique Costagliola, Sophie Abgrall, Michael Gill, Giota Touloumi, Antonio Guilherme Pacheco, Ard van SighemPeter Reiss, Heiner C Bucher, Alexandra Giménez, Inmaculada Jarrin, Linda Wittkop, Laurence Meyer, Santiago Pérez-Hoyos, Amy Justice, James D. Neaton, Miguel A Hernán

Research output: Contribution to journalArticle (Academic Journal)peer-review

70 Citations (Scopus)
111 Downloads (Pure)


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.
Original languageEnglish
Number of pages9
JournalAmerican Journal of Epidemiology
Early online date7 May 2019
Publication statusE-pub ahead of print - 7 May 2019


Dive into the research topics of 'Effect Estimates in Randomized Trials and Observational Studies: Comparing Apples With Apples'. Together they form a unique fingerprint.

Cite this