Course 9: Meta-Analysis in Survey Methodology

Lecturers: Dr. Bernd Weiß, Jessica Daikeler

Date: August 21-25, 2017
Time: 09:00-13:00, 14:00-16:00

Course starts Monday morning at 09:00

Short Course Description:

This course will provide an introduction to a broad range of meta-analytical techniques using the free statistical software package R. Meta-analysis can be thought of as a collection of statistical analyses used to examine
results from individual studies with the general purpose of integrating their findings. A meta-analysis is considered to be the statistical part of a so-called systematic review. While the course focuses particularly on the statistical aspects of a systematic review, we briefly introduce all parts of a research synthesis. That is, we will also discuss how to formulate a research question, search and evaluate the literature as well as how to extract and code the data. In this course we will cover the basics of meta-analysis as well as more advanced topics. Participants are not expected to have a working knowledge of R but are provided with an R introduction. Special
emphasis will be put on performing meta-analysis on experimental and intervention-based studies, in particular from survey methodology. This course is approved by the
Campbell Collaboration.

Course Prerequisites:

  • Participants are expected to have a good working knowledge of statistics at an undergraduate level, e.g. statistical inference (standard error, confidence interval), bivariate statistics (correlation coefficient, mean differences, odds ratio) as well as a basic understanding of (linear) regression analysis and ANOVA.
  • Participants are interested in any subtopic in survey methodology.
  • During the course the statistical software package R will be used, which should be installed on participants computers. A short introduction will be given in the first afternoon session.

Target Group:

Participants will find the course useful if they:

  • are interested in conducting their own research synthesis, especially using the free software package R;
  • want to gain a better understanding of the pros and cons of the method when evaluating meta-analytical results;
  • consider to prepare a Master thesis, a PhD thesis, or a scientific publication in survey methodology using quantitative research synthesis methods.

Course and Learning Objectives:

By the end of the course participants will:

  • be able to determine whether their research problem, ideally from survey methodology, can be analyzed with a meta-analysis;
  • have gained a thorough understanding of how to conduct a meta-analysis and how to present the
    results of a meta-analysis; most importantly they have learned to avoid typical pitfalls when performing a meta-analysis;
  • have learned how to conduct a basic meta-analysis using the free software package R and R’s
    metafor package (see
    www.metafor-project.org/).

Organisational Structure of the Course:

The course will consist of 4 hours of lecture in the morning. Students will spend the afternoons working on exercises designed to deepen their understanding of the material. The instructors will be available in the afternoon to answer questions.

Software and Hardware Requirements:

For performing the practical exercises, course participants will need to bring a laptop computer with both R and RStudio installed. Download R for free from http://www.r-project.org and RStudio for free from https://www.rstudio.com/products/rstudio/download/. RStudio needs a working R installation, so R needs to be installed first.