A wild bootstrap approach for the Aalen–Johansen estimator

We suggest a wild bootstrap resampling technique for nonparametric inference on transition probabilities in a general time-inhomogeneous Markov multistate model. We first approximate the limiting distribution of the Nelson-Aalen estimator by repeatedly generating standard normal wild bootstrap variates, while the data is kept fixed. Next, a transformation using a functional delta method argument is applied. The approach is conceptually easier than direct resampling for the transition probabilities. It is used to investigate a non-standard time-to-event outcome, currently being alive without immunosuppressive treatment, with data from a recent study of prophylactic treatment in allogeneic transplanted leukemia patients. Due to non-monotonic outcome probabilities in time, neither standard survival nor competing risks techniques apply, which highlights the need for the present methodology. Finite sample performance of time-simultaneous confidence bands for the outcome probabilities is assessed in an extensive simulation study motivated by the clinical trial data. Example code is provided in the web-based Supplementary Materials.

[1]  H. Einsele,et al.  Chronic graft-versus-host disease: long-term results from a randomized trial on graft-versus-host disease prophylaxis with or without anti-T-cell globulin ATG-Fresenius. , 2011, Blood.

[2]  Elena Losina,et al.  Evaluation of exposure-specific risks from two independent samples: A simulation study , 2011, BMC medical research methodology.

[3]  R. Gill,et al.  A Survey of Product-Integration with a View Toward Application in Survival Analysis , 1990 .

[4]  Lee-Jen Wei,et al.  Confidence bands for survival curves under the proportional , 1994 .

[5]  Markus Pauly,et al.  Bootstrapping Aalen-Johansen processes for competing risks: Handicaps, solutions, and limitations , 2014 .

[6]  Markus Pauly,et al.  Weak Convergence of the Wild Bootstrap for the Aalen–Johansen Estimator of the Cumulative Incidence Function of a Competing Risk , 2013 .

[7]  Martin Schumacher,et al.  Competing Risks and Multistate Models , 2012, Clinical Cancer Research.

[8]  Per Kragh Andersen,et al.  The clinical course of cirrhosis: The importance of multistate models and competing risks analysis , 2015, Hepatology.

[9]  D. Lin,et al.  Non-parametric inference for cumulative incidence functions in competing risks studies. , 1997, Statistics in medicine.

[10]  Markus Pauly,et al.  Non-strange Weird Resampling for Complex Survival Data , 2015, 1507.02838.

[11]  Markus Pauly.  Weighted resampling of martingale difference arrays with applications , 2011 .

[12]  Martin Schumacher,et al.  Understanding competing risks: a simulation point of view , 2011, BMC medical research methodology.

[13]  Mei-Jie Zhang,et al.  Extensions and Applications of the Cox‐Aalen Survival Model , 2003, Biometrics.

[14]  R. Hehlmann,et al.  Recommendations to meet statistical challenges arising from endpoints beyond overall survival in clinical trials on chronic myeloid leukemia , 2011, Leukemia.

[15]  Martin Schumacher,et al.  Empirical Transition Matrix of Multi-State Models: The etm Package , 2011 .

[16]  Z. Ying,et al.  Checking the Cox model with cumulative sums of martingale-based residuals , 1993 .

[17]  J. Wagner,et al.  Risk Factors for Acute and Chronic Graft-versus-Host Disease after Allogeneic Hematopoietic Cell Transplantation with Umbilical Cord Blood and Matched Sibling Donors. , 2016, Biology of blood and marrow transplantation : journal of the American Society for Blood and Marrow Transplantation.

[18]  Bradley Efron,et al.  Censored Data and the Bootstrap , 1981 .

[19]  Regina Y. Liu.  Bootstrap Procedures under some Non-I.I.D. Models , 1988 .

[20]  N. Chau,et al.  Cannabis use stages as predictors of subsequent initiation with other illicit drugs among French adolescents: use of a multi-state model. , 2012, Addictive behaviors.

[21]  Sergey Tarima,et al.  Handling Time-dependent Variables: Antibiotics and Antibiotic Resistance. , 2016, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[22]  M. Schumacher,et al.  Nonparametric inference for the cumulative incidence function of a competing risk, with an emphasis on confidence bands in the presence of left‐truncation , 2012, Biometrical journal. Biometrische Zeitschrift.

[23]  J. Kalbfleisch,et al.  The Statistical Analysis of Failure Time Data: Kalbfleisch/The Statistical , 2002 .

[24]  Amy Salter,et al.  Multi-state models and arthroplasty histories after unilateral total hip arthroplasties , 2012, Acta orthopaedica.

[25]  H. Putter,et al.  Multi-state analysis illustrates treatment success after stem cell transplantation for acute myeloid leukemia followed by donor lymphocyte infusion , 2016, Haematologica.

[26]  J. Klein,et al.  Inference for current leukemia free survival , 2008, Lifetime data analysis.

[27]  Lee-Jen Wei,et al.  Prediction of cumulative incidence function under the proportional hazards model. , 1998, Biometrics.

[28]  Emmanuel Flachaire,et al.  The wild bootstrap, tamed at last , 2001 .

[29]  Hein Putter,et al.  Reduced-rank proportional hazards regression and simulation-based prediction for multi-state models. , 2008, Statistics in medicine.