本研究主要針對觀察值相依的重覆觀察資料進行分析，如觀察初次接受口腔餵食訓練的早產兒餵食訓練前後兩段時間內發生心跳異常事件的分配情況，即為成對重覆觀察事件(paired recurrent events)之一例。針對成對重覆觀察事件的資料，本研究提出檢定方法，檢定餵食訓練前和餵食訓練後兩段時間內心跳異常事件發生的頻率是否相同。進一步假設重覆觀察事件為混合卜瓦松過程模型(mixed Poisson process model)，在模型的強度函數(intensity function)中使用脆弱因子(frailty)表示每個早產兒不能觀測到變異，計算達特定檢定力所需之樣本數公式，並利用模擬資料，嘗試不同的參數組合，計算模擬情況下之經驗型I錯誤率與經驗檢定力，最後分析該筆早產兒餵食訓練資料。

The purpose of the research is to develop a method for calculating the required sample size for paired recurrent events data.
The developed method is based on robust nonparametric tests for comparing the marginal mean function of events between paired samples.
This calculation can accommodate the associations among a sequence of paired recurrent event times with a specification of correlated gamma frailty variables for a proportional intensity model.
We evaluate the performance of the proposed method with comprehensive simulations including the impacts of paired correlations, homogeneous or nonhomogeneous processes, marginal hazard rates, censoring rate, accrual and follow-up times as well as the sensitivity analysis for the assumption of the assumption of the frailty distribution.
The application is also demonstrated using a premature infant study from the neonatal intensive care unit of a tertiary center in southern Taiwan.

Aalen, O. (1978). Nonparametric inference for a family of counting processes. The Annals
of Statistics, 6(4), 701-726.
Chang, Y.-J. (2003). Energy expenditure and clinical indicators of premature infants. JOURNAL
OF NURSING-TAIPEI-, 50(4), 17–22.
Cook, R. J. (1995). The design and analysis of randomized trials with recurrent events.
Statistics in Medicine, 14(19), 2081–2098.
Cook, R. J., Lawless, J. F., & Lee, K.-A. (2010). A copula-based mixed poisson model
for bivariate recurrent events under event-dependent censoring. Statistics in medicine,
29(6), 694–707.
Frank, M. J. (1979). On the simultaneous associativity off (x, y) andx+y- f (x, y). Aequationes
mathematicae, 19(1), 194–226.
Gumbel, E. J. (1960). Bivariate exponential distributions. Journal of the American Statistical
Association, 55(292), 698–707.
Ingel, K., & Jahn-Eimermacher, A. (2014). Sample-size calculation and reestimation for
a semiparametric analysis of recurrent event data taking robust standard errors into
account. Biometrical Journal, 56(4), 631–648.
Lawless, J. F., & Nadeau, C. (1995). Some simple robust methods for the analysis of recurrent
events. Technometrics, 37(2), 158-168.
Matsui, S. (2005). Sample size calculations for comparative clinical trials with over-dispersed
poisson process data. Statistics in Medicine, 24(9), 1339–1356.
Minhajuddin, A. T., Harris, I. R., & Schucany, W. R. (2004). Simulating multivariate distributions
with specific correlations. Journal of Statistical Computation and Simulation,
74(8), 599–607.
Rebora, P., & Galimberti, S. (2012). Sample size calculation for recurrent events data in
one-arm studies. Pharmaceutical statistics, 11(6), 494–502.
Rebora, P., Galimberti, S., & Valsecchi, M. G. (2010). Robust non-parametric one-sample
tests for the analysis of recurrent events. Statistics in medicine, 29(30), 3137–3146.
Rondeau, V., Mazroui, Y., & Gonzalez, J. R. (2012). frailtypack: an r package for the analysis
of correlated survival data with frailty models using penalized likelihood estimation or
parametrical estimation. Journal of Statistical Software, 47(4), 1–28.
Ross, S. (2013). Simulation (fifth edition). Academic Press.
Song, R., Kosorok, M. R., & Cai, J. (2008). Robust covariate-adjusted log-rank statistics
and corresponding sample size formula for recurrent events data. Biometrics, 64(3),
741–750.
Yan, J., et al. (2007). Enjoy the joy of copulas: with a package copula. Journal of Statistical
Software, 21(4), 1–21.