Observational StudiesSpringer Science & Business Media, 29 cze 2013 - 231 An observational study is an empirical investigation of the effects of treatments, policies, or exposures. It differes from an experiment in that the investigator cannot control the assignments of treatments to subjects. Scientists across a wide range of disciplines undertake such studies, and the aim of this book is to provide a sound statistical account of the principles and methods for the design and analysis of observational studies. Readers are assumed to have a working knowledge of basic probability and statistics, but otherwise the account is reasonably self-contained. Throughout there are extended discussions of actual observational studies to illustrate the ideas discussed. These are drawn from topics as diverse as smoking and lung cancer, lead in children, nuclear weapons testing, and placement programs for students. As a result, many researchers involved in observational studes will find this an invaluable companion to their work. |
Spis treści
| 1 | |
| 3 | |
| 5 | |
| 15 | |
9 | 26 |
Randomized Trial of Coronary Bypass Surgery2 1 | 33 |
6 | 60 |
Cognitive Achievement of US HighSchool Dropouts3 1 3 | 68 |
88 | 115 |
CHAPTER 7 | 117 |
Lung Diseases of Asbestos Miners4 4 7 | 119 |
CHAPTER 5 | 136 |
Nuclear Weapons Testing and Leukemia5 1 2 | 137 |
CHAPTER 6 | 161 |
Multiple Control Groups | 174 |
Aspirin and Reyes Syndrome6 1 2 | 176 |
3 | 70 |
Trial of PACCO for Lung Cancer3 5 | 75 |
Five CaseControl Studies4 4 5 | 84 |
59 | 85 |
Allopurinol and Rash4 4 6 | 110 |
IUD and Ectopic Pregnancy7 4 1 | 183 |
CHAPTER 8 | 187 |
CHAPTER 9 | 200 |
CHAPTER 10 | 225 |
Inne wydania - Wyświetl wszystko
Kluczowe wyrazy i wyrażenia
absence of hidden allopurinol aspirin B₁ biases binary calculated Chapter chromosome compared confidence interval control groups coordinates detect hidden bias discussed disease distance Epidemiology equal example expectation and variance Exposed exposure free of hidden full matching hidden bias Hodges-Lehmann estimate Journal kmax lattice leukemia lung cancer Mantel-Haenszel matched pairs matched sets median test ment methods mortality multiple controls N-tuple null hypothesis observational studies odds ratio optimal matching partial order patients prob(Z probability problems propensity score Proposition r₁ r₂ rank sum statistic receive the treatment referent groups Reye's syndrome Rosenbaum Rubin selected sensitivity analysis sign-score statistics significance level smoking strata stratification stratum Table test statistic t(Z tion treated and control treated group treated subjects treated unit treatment assignments treatment effect uniform randomized experiment units in stratum unobserved covariate upper bound vaginal cancer variable vector z v z Z¹q