非同質 統制集團設計에서의 政策效果의 推定 : 構成員들이 成長하는 경우 = Estimation of Policy Effectiveness in the Non-equivalent Control Group Design with Subjects Growth

다국어 초록 (Multilingual Abstract)

Many experimental programs aim to accelerate the growth of individuals on some dimension of interest. Random assignment of subjects to the program and control group assures an unbiased comparison between treatments. Without randomization there may be important differences between groups in terms of pretreatment or selection characteristics and growth potential. In the non-test comparison based mainly on pretest measures. It is the purpose of this paper to consider the adequacy of various statistical techniques proposed, from the alternative assumptions about the nature of growth, so the performance of various commonly used methods is examined. It is concluded that statistical adjustments are generally inadequate in non-equivalent growth systems across treatment groups.

목차 (Table of Contents)

• Ⅰ. 序論
• Ⅱ. 非同質 統制集團設計의 基本論理
• Ⅲ. 線型調整의 基本方法
• Ⅳ. 線型調整模型 設定
• Ⅴ. 線型調整模型 分析
• Ⅵ. 結論