본문 바로가기 주메뉴 바로가기
국회도서관 홈으로 정보검색 소장정보 검색

목차보기

Title page

Contents

Abstract 3

1. Introduction 4

1.1. Related literature 8

2. A motivating example 9

3. Setup 13

4. Implementability 15

4.1. Which decision functions can be implemented? 16

4.2. Alternative characterizations of implementability 18

4.3. Are pre-analysis messages needed? 20

5. Frequentist hypothesis testing 21

5.1. Decision-maker and analyst objectives 22

5.2. Decision-maker solution: Pre-specified full-data tests 22

5.3. Analyst solution: Linear programming 23

6. Case study 26

7. Conclusion 30

Appendix 32

A. Proofs 32

B. Case study continued: Simple PAPs 40

References 41

Figures

Figure 1. Rejection probabilities for different testing rules 10

Figure 2. Power curves 10

Figure 3. Timeline 14

Figure 4. Analyst knows J 28

Figure 5. Analyst is uncertain about J 28

Figure 6. Which treatment arms should be registered? 29

Figure 7. Optimal simple pre-specified rejection regions for arm-specific cutoffs 40