Hilfe Warenkorb Konto Anmelden
 
 
   Schnellsuche   
     zur Expertensuche                      
Design of Observational Studies  
Design of Observational Studies
von: Paul R. Rosenbaum
Springer-Verlag, 2009
ISBN: 9781441912138
384 Seiten, Download: 2474 KB
 
Format:  PDF
geeignet für: Apple iPad, Android Tablet PC's Online-Lesen PC, MAC, Laptop

Typ: B (paralleler Zugriff)

 

 
eBook anfordern
Inhaltsverzeichnis

  Preface 7  
  Acknowledgments 8  
  Contents 9  
  Part I: Beginnings 15  
     1 Dilemmas and Craftsmanship 16  
        1.1 Those Confounded Vitamins 16  
        1.2 Cochran’s Basic Advice 17  
        1.3 Maimonides’ Rule 20  
        1.4 Seat Belts in Car Crashes 22  
        1.5 Money for College 23  
        1.6 Nature’s ‘Natural Experiment’ 24  
        1.7 What This Book Is About 26  
        1.8 Further Reading 31  
        References 31  
     2 Causal Inference in Randomized Experiments 34  
        2.1 Two Versions of the National Supported Work Experiment 34  
        2.2 Treatment Effects in Randomized Experiments 38  
        2.3 Testing the Null Hypothesis of No Treatment Effect 42  
        2.4 Testing Other Hypotheses 53  
        2.5 Attributable Effects 62  
        2.6 Internal and External Validity 69  
        2.7 Summary 70  
        2.8 Further Reading 70  
        2.9 Appendix: Randomization Distribution of m-statistics 71  
        References 74  
     3 Two Simple Models for Observational Studies 77  
        3.1 The Population Before Matching 77  
        3.2 The Ideal Matching 78  
        3.3 A Na ¨ ive Model: People Who Look Comparable Are Comparable 82  
        3.4 Sensitivity Analysis: People Who Look Comparable May Differ 88  
        3.5 Welding Fumes and DNA Damage 91  
        3.6 Bias Due to Incomplete Matching 97  
        3.7 Summary 98  
        3.8 Further Reading 99  
        3.9 Appendix: Exact Computations for Sensitivity Analysis 100  
        References 102  
     4 Competing Theories Structure Design 107  
        4.1 How Stones Fall 107  
        4.2 The Permanent-Debt Hypothesis 110  
        4.3 Guns and Misdemeanors 112  
        4.4 The Dutch Famine of 1944–1945 112  
        4.5 Replicating Effects and Biases 113  
        4.6 Reasons for Effects 116  
        4.7 The Drive for System 120  
        4.8 Further Reading 121  
        References 122  
     5 Opportunities, Devices, and Instruments 125  
        5.1 Opportunities 125  
        5.2 Devices 128  
        5.3 Instruments 143  
        5.4 Summary 152  
        5.5 Further Reading 152  
        References 153  
     6 Transparency 158  
        References 160  
  Part II: Matching 161  
     7 A Matched Observational Study 162  
        7.1 Is More Chemotherapy More Effective? 162  
        7.2 Matching for Observed Covariates 163  
        7.3 Outcomes in Matched Pairs 166  
        7.4 Summary 168  
        7.5 Further Reading 170  
        References 170  
     8 Basic Tools of Multivariate Matching 171  
        8.1 A Small Example 171  
        8.2 Propensity Score 173  
        8.3 Distance Matrices 176  
        8.4 Optimal Pair Matching 180  
        8.5 Optimal Matching with Multiple Controls 183  
        8.6 Optimal Full Matching 187  
        8.7 Efficiency 191  
        8.8 Summary 192  
        8.9 Further Reading 192  
        References 193  
     9 Various Practical Issues in Matching 195  
        9.1 Checking Covariate Balance 195  
        9.2 Almost Exact Matching 198  
        9.3 Exact Matching 200  
        9.4 Missing Covariate Values 201  
        9.5 Further Reading 202  
        References 202  
     10 Fine Balance 204  
        10.1 What Is Fine Balance? 204  
        10.2 Constructing an Exactly Balanced Control Group 205  
        10.3 Controlling Imbalance When Exact Balance Is Not Feasible 208  
        10.4 Fine Balance and Exact Matching 210  
        10.5 Further Reading 211  
        References 211  
     11 Matching Without Groups 213  
        11.1 Matching Without Groups: Nonbipartite Matching 213  
        11.2 Some Practical Aspects of Matching Without Groups 217  
        11.3 Matching with Doses and Two Control Groups 219  
        11.4 Further Reading 226  
        References 226  
     12 Risk-Set Matching 228  
        12.1 Does Cardiac Transplantation Prolong Life? 228  
        12.2 Risk-Set Matching in a Study of Surgery for Interstitial Cystitis 229  
        12.3 Maturity at Discharge from a Neonatal Intensive Care Unit 233  
        12.4 Joining a Gang at Age 14 236  
        12.5 Some Theory 237  
        12.6 Further Reading 238  
        References 239  
     13 Matching in R 241  
        13.1 241  
        13.2 Data 242  
        13.3 Propensity Score 244  
        13.4 Covariates with Missing Values 244  
        13.5 Distance Matrix 246  
        13.6 Constructing the Match 247  
        13.7 Checking Covariate Balance 248  
        13.8 College Outcomes 250  
        13.9 Further Reading 251  
        13.10 Appendix: A Brief Introduction to 252  
        13.11 Appendix: 254  
        Functions for Distance Matrices 254  
        References 256  
  Part III: Design Sensitivity 258  
     14 The Power of a Sensitivity Analysis and Its Limit 259  
        14.1 The Power of a Test in a Randomized Experiment 259  
        14.2 Power of a Sensitivity Analysis in an Observational Study 267  
        14.3 Design Sensitivity 271  
        14.4 Summary 274  
        14.5 Further Reading 274  
        Appendix: Technical Remarks and Proof of Proposition 14.1 274  
        References 276  
     15 Heterogeneity and Causality 277  
        15.1 J.S. Mill and R.A. Fisher: Reducing Heterogeneity or Introducing Random Assignment 277  
        15.2 A Larger, More Heterogeneous Study Versus a Smaller, Less Heterogeneous Study 279  
        15.3 Heterogeneity and the Sensitivity of Point Estimates 283  
        15.4 Examples of Efforts to Reduce Heterogeneity 284  
        15.5 Summary 286  
        15.6 Further Reading 286  
        References 286  
     16 Uncommon but Dramatic Responses to Treatment 288  
        16.1 Large Effects, Now and Then 288  
        16.2 Two Examples 291  
        16.3 Properties of a Paired Version of Salsburg’s Model 293  
        16.4 Design Sensitivity for Uncommon but Dramatic Effects 295  
        16.5 Summary 297  
        16.6 Further Reading 298  
        16.7 Appendix: Sketch of the Proof of Proposition 16.1 298  
        References 299  
     17 Anticipated Patterns of Response 300  
        17.1 Using Design Sensitivity to Evaluate Devices 300  
        17.2 Coherence 300  
        17.3 Doses 304  
        17.4 Example: Maimonides’ Rule 309  
        17.5 Further Reading 310  
        17.6 Appendix: Proof of Proposition 17.1 310  
        References 311  
  Part IV: Planning Analysis 313  
     18 After Matching, Before Analysis 314  
        18.1 Split Samples and Design Sensitivity 314  
        18.2 Are Analytic Adjustments Feasible? 316  
        18.3 Matching and Thick Description 321  
        18.4 Further Reading 323  
        References 323  
     19 Planning the Analysis 326  
        19.1 Plans Enable 326  
        19.2 Elaborate Theories 328  
        19.3 Three Simple Plans with Two Control Groups 329  
        19.4 Sensitivity Analysis for Two Outcomes and Coherence 338  
        19.5 Sensitivity Analysis for Tests of Equivalence 340  
        19.6 Sensitivity Analysis for Equivalence and Difference 342  
        19.7 Summary 344  
        19.8 Further Reading 344  
        19.9 Appendix: Testing Hypotheses in Order 345  
        References 349  
     Summary: Key Elements of Design 351  
     Solutions to Common Problems 353  
        References 356  
     Symbols 357  
     Acronyms 359  
     Glossary of Statistical Terms 361  
     Some Books 367  
        References 367  
     Suggested Readings for a Course 369  
        References 369  
     Index 371  


nach oben


  Mehr zum Inhalt
Kapitelübersicht
Kurzinformation
Inhaltsverzeichnis
Leseprobe
Blick ins Buch
Fragen zu eBooks?

  Navigation
Computer
Geschichte
Kultur
Medizin / Gesundheit
Philosophie / Religion
Politik
Psychologie / Pädagogik
Ratgeber
Recht
Technik / Wissen
Wirtschaft

© 2008-2024 ciando GmbH | Impressum | Kontakt | F.A.Q. | Datenschutz