Optimal Designs for Event History Analysis
Abstract
The aim of event history analysis is to study the occurrence and timing of events, such as premature psychotherapy termination or drinking onset, and to relate the probability of event occurrence to relevant covariates. In the social sciences, the timing of the event is often measured discretely by using time intervals, which implies the exact timing of event occurrence is unknown. The optimal number of subjects and time intervals need to be decided upon in the design stage of a trial with discrete-time survival endpoints. This paper shows how the optimal design depends on the underlying survival function and the costs to include a subject relative to the costs to take a measurement. Furthermore, the effects of attrition on the optimal design are studied. An example on drinking onset illustrates the proposed methodology.
References
2003). Modelling survival data in medical research (2nd ed.). New York, NY: Chapman and Hall/CRC.
(1972). Regression models and life tables. Journal of the Royal Statistical Society Series B, 34, 187–220.
(2006). The use of unequal randomisation ratios in clinical trials: A review. Contemporary Clinical Trials, 27, 1–12.
(2009). Discovering statistics using SPSS. London, UK: Sage.
(2008). Applied survival analysis. Regression modeling of time-to-event data (2nd ed.). Hoboken, NJ: Wiley.
(2012). Cost-effective designs for trials with discrete-time survival endpoints. Computational Statistics and Data Analysis, 56, 2086–2096.
(2013a). Accrual by cohorts in trials with discrete-time survival endpoints. Clincal Trials, 10, 33–42.
(2013b). PODSE: A computer program for optimal design of trials with discrete-time survival endpoints. Computer Methods and Programs in Biomedicine, 111, 115–127.
(2013c). Optimal treatment allocation and study duration for trials with discrete-time survival endpoints. Journal of Statistical Planning and Inference, 143, 971–982.
(2006). Survival analysis: A practical approach (2nd ed.). Chichester, UK: Wiley.
(2013). Covariate adjustment strategy increases power in the randomized controlled trial with discrete-time survival endpoints. Journal of Educational and Behavior Statistics, 38, 355–380.
(1993). It’s about time: Using discrete-time survival analysis to study duration and the timing of events. Journal of Educational and Behavior Statistics, 18, 155–195.
(2003). Applied longitudinal data analysis. Modeling change and event occurrence. New York, NY: Oxford University Press.
(2013). Using multivariate statistics. Boston, MA: Pearson.
(2008). Designing randomised trials in health, education and the social sciences. New York, NY: Palgrave Macmillan.
(2010). Predicting drinking onset with discrete-time survival analysis in offspring from the San Diego prospective study. Drug and Alcohol Dependence, 107, 215–220.
(