In Reply We write this letter in response to the comments by Hwang and colleagues on our study.1 First, we would like to point out that the Kaplan-Meier curves and the log-rank tests were only used to initially describe the distribution of adverse events (AEs) in different treatment regimens. Afterwards, as stated in “Methods” section and in the heading of our Figure 3, we used a multivariate Cox regression model, to account for the time-dependent nature of AEs.
Sanlorenzo M, Vujic I, Ortiz-Urda S. Time-Dependent Measurement of Adverse Events—Reply. JAMA Dermatol. 2015;151(12):1392-1393. doi:10.1001/jamadermatol.2015.3578