Statistical Inference for Clinical Trials with Protocol Amendments

• Main Authors: Lan-YanYang, 楊嵐燕
• Other Authors: Yunchan Chi
• Format: Others
• Language: en_US
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/21011110302573580052

博士 === 國立成功大學 === 統計學系碩博士班 === 98 === It is not uncommon to modify trial procedures and/or statistical methods of on-going clinical trials through protocol amendments. A major modification could result in a shift in target patient population. In addition, frequent and significant modifications could lead to a totally different study, which is unable to address the medical questions that the original study intends to answer. Chow and Shao (2005) proposed a covariate-adjusted model with continuous study endpoint. Chow et al. (2005) proposed using a sensitivity index, as defined in Chow et al. (2002), to measure the impact of population shift. Under the assumption that the shift in location parameter is random and the shift in scale parameter is fixed, Chow et al. (2005) proposed a Bayesian approach for inferences of the treatment effect. In this dissertation, following similar ideas of Chow and Shao (2005) and Chow et al. (2005), statistical inference and sample size adjustment based on a binary study endpoint for trials with protocol amendments are derived.