Statistical evidence in medical trials : what do the data really tell us? / Stephen D. Simon.

Format:

Book

Author/Creator:

Simon, Stephen D.

Language:

English

Subjects (All):

Clinical trials--Statistical methods.

Clinical trials.

Biomedical Research--methods.

Clinical Trials as Topic--statistics & numerical data.

Data Interpretation, Statistical.

Research Design.

Medical Subjects:

Biomedical Research--methods.

Clinical Trials as Topic--statistics & numerical data.

Data Interpretation, Statistical.

Research Design.

Physical Description:

xvii, 197 pages : illustrations ; 24 cm

Place of Publication:

Oxford ; New York : Oxford University Press, 2006.

Summary:

Statistical Evidence in Medical Trials is a lucid, well-written and entertaining text that addresses common pitfalls in evaluating medical research. Including extensive use of publications from the medical literature and a non-technical account of how to appraise the quality of evidence presented in these publications, this book is ideal for health care professionals, students in medical or nursing schools, researchers and students in statistics, and anyone needing to assess the evidence published in medical journals.

Contents:

1 Apples or Oranges? Selection of the Control Group 1

1.2 Randomly selected controls 3

1.3 Variations on randomization 8

1.4 Nonrandomized studies 11

1.5 Preventing covariate imbalance before it occurs 17

1.6 Statistical adjustments 22

1.7 Counterpoint: Randomized trials are overrated 29

1.8 Summary-Apples or oranges 30

1.9 On your own 30

2 Who Was Left Out? Exclusions, refusals, and drop-outs 37

2.2 Who was excluded at the start of the study? 39

2.3 Who refused to join the study? 43

2.4 Who stopped or switched therapies? 45

2.5 Who dropped out during the study? 47

2.6 Counterpoint: Intention to treat is overrated 49

2.7 Summary-Who was left out? 50

2.8 On your own 51

3 Mountain or Molehill? The Clinical Importance of the Results 55

3.2 Did they measure the right thing? 57

3.3 Did they measure the outcome well? 62

3.4 Were the changes clinically important? 69

3.5 Counterpoint: Blinding is overrated 75

3.6 Summary-Mountain or molehill? 76

3.7 On your own 76

4 What Do the Other Witnesses Say? Corroborating Evidence 83

4.2 Is there a strong association? 85

4.3 Is there a dose-response pattern? 86

4.4 Is the association consistent? 87

4.5 Is the association specific? 89

4.6 Is the association biologically plausible? 91

4.7 Is there a conflict of interest? 93

4.8 Is there any evidence of fraud? 94

4.9 Counterpoint: Biological plausibility is overrated 95

4.10 Summary-what do the other witnesses say? 97

4.11 On your own 98

5 Do the Pieces Fit Together? Systematic overviews and meta-analyses 101

5.2 Were apples combined with oranges? 103

5.3 Were some apples left on the tree? 110

5.4 Were all of the apples rotten? 118

5.5 Did the pile of apples amount to more than just a hill of beans? 123

5.6 Counterpoint: meta-analysis is overrated 127

5.7 Summary-Do the pieces fit together? 128

5.8 On your own 128

6 What Do All These Numbers Mean? 137

6.2 Samples and populations 138

6.3 Type I and II errors 138

6.4 Confidence interval 141

6.5 p-value 144

6.6 Odds ratio and relative risk 145

6.7 Correlation 147

6.8 Survival curves 149

6.9 Prevalence and incidence 153

6.10 On your own 156

7 Where Is the Evidence? Searching for Information 167

7.2 PICO format 168

7.3 Search high level sources first 168

7.4 Searching in PubMed 169

7.5 Searching the Internet 172

7.6 Summary-Where is the evidence? 175

7.7 On your own 176.

Notes:

Includes bibliographical references (pages [177]-192) and index.

ISBN:

019856760X

0198567618

OCLC:

61424800

Publisher Number:

9780198567608

9780198567615