Zu den Inhalten springen

Planning and nonparametric inference for multistate time-to-event data such as disease occurrences and disease durations

Funding: 36 months, since 2011

Subsequent funding: 24 months, since 2016

Abstract

Multistate time-to-event data are frequent in medical studies. E.g., a common endpoint in clinical studies is disease-free survival. A competing risks multistate model would more specifically address disease occurrences in contrast to death. More complex multistate data arise, if patients are followed after disease recurrence. Such data would also allow to study disease durations. Regression models for the event-specific hazards have been developed during the last 30 years, and much progress has been made for direct regression models for multistate outcome probabilities during the last decade. However, methodology for planning studies with multistate data is scarce, as is methodology for analyses where the aim is to simultaneously compare multistate transition probabilities over whole time regions. The aim of this project is to develop such methodology. Planning is, e.g., relevant to account for situations where a non-harmful effect on the death hazard may blur a beneficial effect on the hazard of disease recurrence in the analysis of ‘disease-free survival’. Simultaneous confidence bands for multistate transition probabilities are relevant to study how group differences develop over time.

Publications

  • Di Termini S, Hieke S, Schumacher M, Beyersmann J. Nonparametric inference for the cumulative incidence function of a competing risk, with an emphasis on confidence bands in the presence of left-truncation. Biometrical Journal, 2012; 54(4), 568-578. http://dx.doi.org/10.1002/bimj.201100161
  • Beyersmann J, Di Termini S, Pauly M. Weak Convergence of the Wild Bootstrap for the Aalen-Johansen Estimator of the Cumulative Incidence Function of a Competing Risk. Scandinavian Journal of
    Statistics
    , 2013; 40(3), 387-402. http://dx.doi.org/10.1111/j.1467-9469.2012.00817.x
  • Ohneberg K, Schumacher M. Sample Size Calculations for Clinical Trials. In: Handbook of Survival Analysis , Klein JP, van Houwelingen HC, Ibrahim JG, Scheike TH. Chapman and Hall/CRC, 2013.
  • Ohneberg K, Wolkewitz M, Beyersmann J, Palomar-Martinez M, Olaechea-Astigarraga P, Alvarez-Lerma F, Schumacher M. Analysis of Clinical Cohort Data Using Nested Case-control and Case-cohort Sampling Designs: A Powerful and Economical Tool. Method Inform Med, 2015; 54: 505-514. http://dx.doi.org/10.3414/ME14-01-0113
  • Ohneberg K, Schumacher M, Beyersmann J. Modelling two cause-specific hazards of competing risks in one cumulative proportional odds model? Stat Med, 2017. http://dx.doi.org/10.1002/sim.7437 (in press)
Researchers

Dr. rer. nat. Susanna Di Termini

Dipl.-Math. Kristin Ohneberg