Standard and Advanced Methods for Meta-Analysis with R

Novice and advanced R users from all professional groups.

• CHF 600.- for members of UZH/ETH and associated institutes
• CHF 800.- for alumni of UZH/ETH, members of other universities, the public sector and non-profit organizations
• CHF 1200.- for companies

Persons without current employment can register for the UZH/ETH fee upon request.

Meta-analysis encompasses an array of statistical methods for aggregating and comparing the results from related studies in a systematic manner. The focus of this workshop is on standard and some advanced methods for analyzing meta-analytic data. We will start by looking at methods for quantifying the results from individual studies included in a meta-analysis in terms of various effect size or outcome measures (e.g., standardized mean differences, risk/odds ratios, correlation coefficients). We will then delve into methods for combining the observed outcomes (i.e., via equal- and random-effects models) and for examining whether the outcomes depend on the characteristics of the studies from which they were derived (i.e., via meta-regression and subgrouping). A major problem that may distort the results of a meta-analysis is publication bias (i.e., when the studies included in a meta-analysis are not representative of all the relevant research that has been conducted on a particular topic). Therefore, current methods for detecting and dealing with publication bias will be discussed next. Finally, we will look at some advanced methods for meta-analysis to handle more complex data structures that frequently arise in practice, namely when studies contribute multiple effect sizes to the same analysis, leading to dependencies in the data that need to be accounted for (e.g., via multilevel/multivariate models and cluster-robust inference methods).

The workshop consists of a mixture of lectures and practical exercises. As the workshop is specifically focused on the statistical methods for conducting a meta-analysis (and doesn't cover steps such as the literature search and data extraction / coding), a basic understanding of the research synthesis process is useful. Also, while no prior experience with R is assumed, some familiarity with R would be useful.

Participants are required to bring their own laptop to the workshop with the current version of R (and RStudio for those who do not already have a different setup they are comfortable with) installed.

In this course participants will learn how to:

• compute and interpret various effect size / outcome measures
• synthesize such values via various types of models and interpret the results
• determine the presence and potential impact of publication bias
• handle dependent effect size estimates via appropriate statistical methods
• carry out the analyses using R