The inverse-probability-of-censoring weighting (IPCW) adjusted win ratio statistic: an unbiased estimator in the presence of independent censoring

ABSTRACT The win ratio method has received much attention in methodological research, ad hoc analyses, and designs of prospective studies. As the primary analysis, it supported the approval of tafamidis for the treatment of cardiomyopathy to reduce cardiovascular mortality and cardiovascular-related hospitalization. However, its dependence on censoring is a potential shortcoming. In this article, we propose the inverse-probability-of-censoring weighting (IPCW) adjusted win ratio statistic (i.e., the IPCW-adjusted win ratio statistic) to overcome censoring issues. We consider independent censoring, common censoring across endpoints, and right censoring. We develop an asymptotic variance estimator for the logarithm of the IPCW-adjusted win ratio statistic and evaluate it via simulation. Our simulation studies show that, as the amount of censoring increases, the unadjusted win proportions may decrease greatly. Consequently, the bias of the unadjusted win ratio estimate may increase greatly, producing either an overestimate or an underestimate. We demonstrate theoretically and through simulation that the IPCW-adjusted win ratio statistic gives an unbiased estimate of treatment effect.

[1]  J. Verbeeck,et al.  Evaluation of inferential methods for the net benefit and win ratio statistics , 2020, Journal of biopharmaceutical statistics.

[2]  L. Tian,et al.  On the empirical choice of the time window for restricted mean survival time , 2020, Biometrics.

[3]  P. Hansen,et al.  [Transthyretin amyloid cardiomyopathy]. , 2020, Ugeskrift for laeger.

[4]  R. Betensky,et al.  Inverse probability weighting methods for Cox regression with right‐truncated data , 2019, Biometrics.

[5]  D. Hoaglin,et al.  The win ratio: Impact of censoring and follow‐up time and use with nonproportional hazards , 2019, Pharmaceutical statistics.

[6]  G. Molenberghs,et al.  Generalized pairwise comparison methods to analyze (non)prioritized composite endpoints , 2019, Statistics in medicine.

[7]  S. Pocock,et al.  Statistical Appraisal of 6 Recent Clinical Trials in Cardiology: JACC State-of-the-Art Review. , 2019, Journal of the American College of Cardiology.

[8]  D. Hoaglin,et al.  The Win Ratio: On Interpretation and Handling of Ties , 2019, Statistics in Biopharmaceutical Research.

[9]  H. Katki,et al.  Prioritized concordance index for hierarchical survival outcomes , 2019, Statistics in medicine.

[10]  M. Ellison,et al.  Statistical methods for survival trial design: with applications to cancer clinical trial using R , 2018, Journal of Biopharmaceutical Statistics.

[11]  D. Schoenfeld,et al.  Graphing the Win Ratio and its components over time , 2018, Statistics in medicine.

[12]  Sanjiv J. Shah,et al.  Tafamidis Treatment for Patients with Transthyretin Amyloid Cardiomyopathy , 2018, The New England journal of medicine.

[13]  L. Mao,et al.  On the alternative hypotheses for the win ratio , 2018, Biometrics.

[14]  Jianrong Wu.  Statistical Methods for Survival Trial Design , 2018 .

[15]  Duolao Wang,et al.  The stratified win ratio , 2018, Journal of biopharmaceutical statistics.

[16]  Bo Huang,et al.  Comparison of the restricted mean survival time with the hazard ratio in superiority trials with a time‐to‐event end point , 2018, Pharmaceutical statistics.

[17]  M. Buyse,et al.  An extension of generalized pairwise comparisons for prioritized outcomes in the presence of censoring , 2018, Statistical methods in medical research.

[18]  Xiaodong Luo,et al.  Weighted win loss approach for analyzing prioritized outcomes , 2017, Statistics in medicine.

[19]  Shu Yang,et al.  Estimation of the cumulative incidence function under multiple dependent and independent censoring mechanisms , 2017, Lifetime Data Analysis.

[20]  D. Oakes.  On the win-ratio statistic in clinical trials with multiple types of event , 2016 .

[21]  M. Vandemeulebroecke,et al.  A generalized analytic solution to the win ratio to analyze a composite endpoint considering the clinical importance order among components , 2016, Pharmaceutical statistics.

[22]  M. Buyse,et al.  The Net Chance of a Longer Survival as a Patient-Oriented Measure of Treatment Benefit in Randomized Clinical Trials. , 2016, JAMA oncology.

[23]  S. Pocock,et al.  A win ratio approach to comparing continuous non‐normal outcomes in clinical trials , 2016, Pharmaceutical statistics.

[24]  W. Tsai,et al.  An alternative approach to confidence interval estimation for the win ratio statistic , 2015, Biometrics.

[25]  Lihui Zhao,et al.  Predicting the restricted mean event time with the subject's baseline covariates in survival analysis. , 2014, Biostatistics.

[26]  M. H. R. Khan,et al.  Robust bias estimation for Kaplan-Meier survival estimator with jackknifing , 2013, Journal of Statistical Theory and Practice.

[27]  S. Pocock,et al.  The win ratio: a new approach to the analysis of composite endpoints in clinical trials based on clinical priorities , 2011, European heart journal.

[28]  M. Pencina,et al.  On the C‐statistics for evaluating overall adequacy of risk prediction procedures with censored survival data , 2011, Statistics in medicine.

[29]  S. Cole,et al.  Limitation of inverse probability-of-censoring weights in estimating survival in the presence of strong selection bias. , 2011, American journal of epidemiology.

[30]  M. Buyse.  Generalized pairwise comparisons of prioritized outcomes in the two‐sample problem , 2010, Statistics in medicine.

[31]  Terry M Therneau,et al.  A long-term study of prognosis in monoclonal gammopathy of undetermined significance. , 2002, The New England journal of medicine.

[32]  J. Robins,et al.  Correcting for Noncompliance and Dependent Censoring in an AIDS Clinical Trial with Inverse Probability of Censoring Weighted (IPCW) Log‐Rank Tests , 2000, Biometrics.

[33]  Robert Gray,et al.  A Proportional Hazards Model for the Subdistribution of a Competing Risk , 1999 .

[34]  E. Lehmann.  Elements of large-sample theory , 1998 .

[35]  Stefun D. Leigh.  U-Statistics Theory and Practice , 1992 .

[36]  Lee-Jen Wei,et al.  Combining dependent tests with incomplete repeated measurements , 1985 .

[37]  W. Hoeffding.  A Class of Statistics with Asymptotically Normal Distribution , 1948 .

[38]  J. Lachin,et al.  Large sample inference for a win ratio analysis of a composite outcome based on prioritized components. , 2016, Biostatistics.