In Reply We would like to thank Claggett and coauthors for their discussion of the limitations of conventional meta-analysis approaches, and for pointing to interesting new work on potential alternatives. As they note, we had to make some choices and assumptions to conduct our analyses—these were made after careful consideration of information available in the studies that we relied on, as well as by considering common practices in the field of meta-analysis.1 However, we do not believe that the methodology proposed by the authors is fully relevant to our work. First, we disagree about the lack of interpretability of hazard ratios. Researchers are comfortable seeing and interpreting them, and they have a good feeling for appreciating small and large effects in this scale. The remaining criticism and alternative approach are more applicable to the estimation of absolute effects, such as the prevalence of a certain feature in the population. Our article1 focuses on relative effects, which are not applicable to individuals, but only parameters. The units of our analysis are studies, and the relevant “superpopulation” is that of all potential studies addressing the effectiveness of high-dose therapy and autologous stem cell transplantation in meta-analysis that could be conducted.
Dhakal B, Szabo A, Hari P. Meta-analysis to Evaluate High-Dose Therapy Followed by Stem Cell Transplant in Patients With Multiple Myeloma—Reply. JAMA Oncol. 2018;4(11):1618. doi:10.1001/jamaoncol.2018.3501
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: