現狀數據常見於社會學、流行病學及醫學研究中。此數據皆無法直接觀測研究事件的真實發生時間，僅能在檢查或調查時間當下得知事件是否已發生。Williamson, Lin and Kim (2009) 對於以 Weibull 為基線分佈的柯斯迴歸提出一個現狀數據的樣本數計算。然而，在過去的研究中，說明柯斯迴歸模型在不同母數的基線模型下，所需的樣本數可能有極大的差異。因此本論文對於以積分樣條模型 (I-splines) 模式未特定基線分佈的半母數柯斯迴歸，提供一個現狀數據樣本數的計算公式。透過模擬驗證公式的正確性，並以兩個實例作為公式的例證。

Current status data are commonly arisen in sociology, epidemiology and medical studies, where we cannot directly observe the actual occurrence time of the research event. The only be observation consists of the time of inspection and a status indicator of the event has occurred by the time of inspection. Williamson, Lin and Kim (2009) proposed a sample size calculation for current status data under the Cox model with Weibull baseline. However, in previous studies, it was shown that samples sizes required for the Cox regression with different baseline models may vary greatly. In this thesis, we provide a sample size formula for semiparametric Cox regression analysis of current status data under unspecified baseline distribution. The baseline distribution is modelled by I-splines (Ramsay 1988). The proposed formula is verified by simulation studies and illustrated by two real examples.

目錄
第一節 前言	1
第二節 方法	4
第三節 模擬試驗	12
第四節 實例分析	19
RFM老鼠肺腫瘤數據分析	19
白內障數據分析	24
第五節 結論與討論	29
參考文獻	31
附錄	34
表目錄
表 3-1(a)	15
表 3-1(b)	16
表 3-1(c)	17
表 3-1(d)	18
表 4-1(a)	22
表 4-1(b)	23
表 4-2	27
圖目錄
圖 2-1	7
圖 4-1	21
圖 4-2	25
圖 4-3	26

[1]	Cai B., Lin X., Wang L. (2011) Bayesian proportional hazards model for current status data with monotone splines. Computation Statistics and Data Analysis 55(9), 2644-2651.

[2]	Cantor A. B. (1992) Sample size calculations for the log rank test: A Gompertz model approach. Journal of Clinical Epidemiology 45(10), 1131–1136.

[3]	Cheng W. L. (2016). Sample Size Calculation for the Proportional Hazards Model with Current Status Data. Master thesis, Tamkang University.

[4]	Cox D. R. (1972). Regression models and life-table. Journal of the Royal Statistical Society: Series B (Methodological) 34(2), 187-220.

[5]	Eng K. H., Kosorok M. R. (2005) A sample size formula for the supremum log-rank statistic. Biometrics 61(1), 86–91.

[6]	Finkelstein D. M. (1986) A proportional hazards model for interval-censored failure time data. Biometrics 42(4), 845-854.

[7]	Gail M. H. (1985) Applicability of sample size calculations based on a comparison of proportions for use with the log rank test. Controlled Clinical Trials 6(2), 112–119.

[8]	Hoel D. G., Walburg H. E. (1972) Statistical analysis of survival experiments. Journal of National Cancer Institute 49(2), 361-372.

[9]	Hsieh F. Y., Lavori P. W. (2000) Sample size calculations for the Cox proportional hazards model with nonbinary covariates. Controlled Clinical Trials 21(6), 552–560.

[10]	Huang, J. (1996). Efficient estimation for the proportional hazards model with interval censoring. The Annals of Statistics 24(2), 540-568.

[11]	Huang J., Wellner J. A. (1997) Interval censored survival data: a review of recent progress. Springer, New York.

[12]	Jung S. H. (2008) Sample size calculation for the weighted rank statistics with paired survival data. Statistics in Medicine 27(17), 3350–3365.

[13]	Lin D. Y., Oakes D., Ying Z. (1998). Additive hazards regression with current status data. Biometrika 85(2), 289-298.

[14]	Lin X., Wang L. (2010) A semiparametric probit model for case 2 interval-censored failure time data. Statistics in Medicine 29(9), 972-981.

[15]	Ma S. (2009) Cure model with current status data. Statistica Sinica 19(1), 233–249.

[16]	Martinussen T., Scheike T. H. (2002) Efficient estimation in additive hazards regression with current status data. Biometrika 89(3), 649-658.

[17]	Ramsay J. O. (1988) Monotone Regression Splines in Action. Statistical Science 3(4), 425-441.

[18]	Rossini A. J., Tsiatis A. A. (1996). A semiparametric proportional odds regression model for the analysis of current status data. Journal of the American Statistical Association 91(434), 713-721.

[19]	Ryan T. P. (2013). Sample Size Determination and Power. Hoboken, New Jersey: John Wiley & Sons.

[20]	Schoenfeld D. A. (1983). Sample-size formula for the proportional-hazards regression model. Biometrics 39(2), 499–503.

[21]	Sun J. (2006). The Statistical Analysis of Interval-censored Failure Time Data. Springer, New York.

[22]	Sun J., Sun L. (2005). Semiparametric linear transformation models for current status data. The Canadian Journal of Statistics 33(1), 85-96.

[23]	Tian L., Cau T. (2006). On the accelerated failure time model for current status and interval censored data. Biometrika 93(2), 329-342.

[24]	Wang L., Dunson D. B. (2011) Semiparametric Bayes’ Proportional Odds Models for Current Status Data with Underreporting. Biometrics 67(3), 1111-1118.

[25]	Wang L., McMahan C. S., Hudgens M. G., Qureshi Z. P. (2016) A Flexible, Computationally Efficient Method for Fitting the Proportional Hazards Model to Interval-Censored Data. Biometrics 72(1), 222-231

[26]	Wang N., Wang L., McMahan C. S. (2015) Regression analysis of bivariate current status data under the Gamma-frailty proportional hazards model using the EM algorithm. Computation Statistics and Data Analysis 83(C), 140-150.

[27]	Williamson J. M., Lin H. M., Kim H. Y. (2009). Power and sample size calculations for current status survival analysis. Statistics in Medicine 28(15), 1999–2011.

[28]	Zhang Z., Sun J. (2010). Interval censoring. Statistical Methods in Medical Research 19(1), 53-70.