Front page
Handbook information
Part 1: Cochrane reviews
Part 2: General methods for Cochrane reviews
    5 Defining the review question and developing criteria for including studies
    6 Searching for studies
    7 Selecting studies and collecting data
    8 Assessing risk of bias in included studies
    9 Analysing data and undertaking meta-analyses
       9.1 Introduction
       9.2 Types of data and effect measures
       9.3 Study designs and identifying the unit of analysis
       9.4 Summarizing effects across studies
          9.4.1 Meta-analysis
          9.4.2 Principles of meta-analysis
          9.4.3 A generic inverse-variance approach to meta-analysis
          9.4.4 Meta-analysis of dichotomous outcomes
             Introductory text
             9.4.4.1 Mantel-Haenszel methods
             9.4.4.2 Peto odds ratio method
             9.4.4.3 Random-effects method
             9.4.4.4 Which measure for dichotomous outcomes?
          9.4.5 Meta-analysis of continuous outcomes
          9.4.6 Combining dichotomous and continuous outcomes
          9.4.7 Meta-analysis of ordinal outcomes and measurement scales
          9.4.8 Meta-analysis of counts and rates
          9.4.9 Meta-analysis of time-to-event outcomes
          9.4.10 A summary of meta-analysis methods available in RevMan
          Table 9.4.a: Summary of meta-analysis methods available in RevMan
          9.4.11 Use of vote counting for meta-analysis
       9.5 Heterogeneity
       9.6 Investigating heterogeneity
       9.7 Sensitivity analyses
       9.8 Chapter information
       Box 9.8.a: The Cochrane Statistical Methods Group
       9.9 References
    10 Addressing reporting biases
    11 Presenting results and 'Summary of findings' tables
    12 Interpreting results and drawing conclusions
Part 3: Special topics
Additional material