Publication Bias in Meta-Analysis: Prevention, Assessment and Adjustments / Edition 1 available in Hardcover
- Pub. Date:
Publication bias is the tendency to decide to publish a study basedon the results of the study, rather than on the basis of itstheoretical or methodological quality. It can arise from selectivepublication of favorable results, or of statistically significantresults. This threatens the validity of conclusions drawn fromreviews of published scientific research.
Meta-analysis is now used in numerous scientific disciplines,summarizing quantitative evidence from multiple studies. If theliterature being synthesised has been affected by publication bias,this in turn biases the meta-analytic results, potentiallyproducing overstated conclusions. Publication Bias inMeta-Analysis examines the different types of publication bias,and presents the methods for estimating and reducing publicationbias, or eliminating it altogether.
Written by leading experts, adopting a practical andmultidisciplinary approach.
Provides comprehensive coverage of the topic including:
- Different types of publication bias,
- Mechanisms that may induce them,
- Empirical evidence for their existence,
- Statistical methods to address them,
- Ways in which they can be avoided.
- Features worked examples and common data sets throughout.
- Explains and compares all available software used for analysingand reducing publication bias.
- Accompanied by a website featuring software, data sets andfurther material.
Publication Bias in Meta-Analysis adopts aninter-disciplinary approach and will make an excellent referencevolume for any researchers and graduate students who conductsystematic reviews or meta-analyses. University and medicallibraries, as well as pharmaceutical companies and governmentregulatory agencies, will also find this invaluable.
|Product dimensions:||6.26(w) x 9.29(h) x 1.04(d)|
About the Author
Hannah Rothstein is co-chair of the Methods Group of theCampbell Collaboration, and a member of the Collaboration’sSteering Group. She is also a member of the CochraneCollaboration’s reporting bias methods group. Dr. Rothsteinhas been first author of four published meta-analyses of employmentselection methods and has written many articles on methodologicalissues in meta-analysis. She has authored a chapter onmeta-analysis that appeared in Measuring and Analyzing Behaviorin Organizations, and has completed a 25-year retrospective onthe contributions of meta-analysis to the field of industrial andorganizational psychology that appeared in ValidityGeneralization: A Critical Review. With Michael Borenstein, andothers, she is the author of computer software for meta-analysisand power analysis.
Alex Sutton has published extensively on meta-analysismethodology generally, and on publication bias specifically inrecent years, including a major systematic review on the topic ofthe methodology that has been developed for meta-analysis. Hecurrently has an active interest in the area of partially reportedstudy information, which is currently under-researched. Dr. Suttonis co-author of a textbook on metaanalysis (Methods for MetaAnalysis in Medical Research), which was published by Wiley in2000.
Michael Borenstein served as Director of Biostatistics atHillside Hospital, Long Island Jewish Medical Center from1980–2002, and as Associate Professor at Albert EinsteinCollege of Medicine from 1992–2002. He has served on variousreview groups and advisory panels for the National Institutes ofHealth and as a member of the NIMH Data Safety Monitoring Board,and is an active member of the statistical advisory groups of theCochrane and Campbell Collaborations. Since the mid-1990s, DrBorenstein has lectured widely on meta-analysis. He is the PI onseveral NIH grants to develop software for meta-analysis and is thedeveloper, with Larry Hedges, Julian Higgins, Hannah Rothstein andothers, of Comprehensive Meta Analysis, a best-sellingcomputer program for meta-analysis.
Table of Contents
Notes on Contributors.
Chapter 1: Publication Bias in Meta-Analysis (Hannah R.Rothstein, Alexander J. Sutton and Michael Borenstein).
Part A: Publication bias in context.
Chapter 2: Publication Bias: Recognizing the Problem,Understanding Its Origins and Scope, and Preventing Harm (KayDickersin).
Chapter 3: Preventing Publication Bias: Registries andProspective Meta-Analysis (Jesse A. Berlin and Davina Ghersi).
Chapter 4: Grey Literature and Systematic Reviews (SallyHopewell, Mike Clarke and Sue Mallett).
Part B: Statistical methods for assessing publicationbias.
Chapter 5: The Funnel Plot (Jonathan A.C. Sterne, Betsy JaneBecker and Matthias Egger).
Chapter 6: Regression Methods to Detect Publication and OtherBias in Meta-Analysis (Jonathan A.C. Sterne and MatthiasEgger).
Chapter 7: Failsafe N or File-Drawer Number (Betsy JaneBecker).
Chapter 8: The Trim and Fill Method (Sue Duval).
Chapter 9: Selection Method Approaches (Larry V. Hedges and JackVevea).
Chapter 10: Evidence Concerning the Consequences of Publicationand Related Biases (Alexander J. Sutton).
Chapter 11: Software for Publication Bias (MichaelBorenstein).
Part C: Advanced and emerging approaches.
Chapter 12: Bias in Meta-Analysis Induced by IncompletelyReported Studies (Alexander J. Sutton and Therese D. Pigott).
Chapter 13: Assessing the Evolution of Effect Sizes over Time(Thomas A. Trikalinos and John P.A. Ioannidis).
Chapter 14: Do Systematic Reviews Based on Individual PatientData Offer a Means of Circumventing Biases Associated with TrialPublications? (Lesley Stewart, Jayne Tierney and SarahBurdett).
Chapter 15: Differentiating Biases from Genuine Heterogeneity:Distinguishing Artifactual from Substantive Effects (John P.A.Ioannidis).
Chapter 16: Beyond Conventional Publication Bias: OtherDeterminants of Data Suppression (Scott D. Halpern and Jesse A.Berlin).
Appendix A: Data Sets.
Appendix B: Annotated Bibliography (Hannah R. Rothstein andAshley Busing).