This is an old revision of the document!
The purpose of this course is to cover advanced methods for meta-analysis with particular emphasis on using the statistical software R for conducting the analyses. Therefore, course participants are expected to have an understanding of standard meta-analytic techniques and methodology (see below for course prerequisites).
We will start out by briefly reviewing standard meta-analytic models (i.e., equal-, fixed-, random-, and mixed-effects meta-regression models), focusing on how to fit these models in R. This will then be starting point to delve into more complex data structures that one may encounter in practice and to consider appropriate models for analyzing such data. Models and techniques to be discussed in this context include multilevel and multivariate models, methods for dealing with dependent/correlated outcomes, network meta-analysis or what is also known as multiple/mixed treatment comparisons (MTCs), models with crossed random effects, and phylogenetic meta-analysis. We will also examine the distinction between models that use the normal distribution as an asymptotic approximation to the sampling distribution of the observed outcomes and models that are based on alternative distributional assumptions (e.g., binomial and Poisson distributions, which then lead to random/mixed-effects (conditional) logistic and Poisson regression models).
This is a two-day course, starting at 9am and concluding around 6pm on each day.
Course participants are expected to have an understanding of standard meta-analytic methods and ideally some prior experience with analyzing meta-analytic data. Most importantly, participants should be familiar with the computation and interpretation of outcome measures commonly used in meta-analyses (e.g., risk differences, log transformed risk/odds ratios, raw or standardized mean differences, response ratios, raw or Fisher's r-to-z transformed correlations) and the interpretation and application of equal-, fixed-, random-, and mixed-effects meta-regression models. I also offer a three-day meta-analysis course that covers these (and other topics) in great detail.
The primary software package to be used during the course for the analyses will be R (see below for more details). Although all commands to be used for the examples and illustrations will be explained, this is not a comprehensive R programming course. Therefore, if you are new to R, it would be useful to familiarize yourself with R a little bit ahead of time (here are some notes on preparing to use R). You could also consider following the introduction to R course first.
Finally, further below, you will find a list of references, which describe some of the models and methods that will be discussed during the course. If you have the time, feel very ambitious, and don't already know these papers in the first place, it would be ideal to at least skim through them ahead of time in preparation for the course (and to get a better idea of the course contents). But this is not a course prerequisites per se – all of the models and methods to be discussed will be introduced step by step during the course without assuming that you have already read each and every paper listed below.
The course is very hands-on and participants will immediately put models and techniques into practice with several illustrative datasets. Therefore, please bring a laptop to the course. Moreover, you should have the current version of R installed on the laptop. More information about R can be found on the R Project Website. You can download R from the Comprehensive R Archive Network (CRAN).
If you are starting to work with R for the first time, it may be useful to also install an integrated development environment (IDE) for R. A popular recommendation these days is RStudio, which is available for Windows, MacOS, and Linux.
Once R is installed, please install the metafor package (an add-on for conducting meta-analyses with R). More details about the package can be found on the metafor package website. If you have an internet connection, you should be able to install the package by starting R and then typing
install.packages("metafor") (if you are prompted to choose a mirror, select the default option or a location that is nearby).
In addition, we are likely to make use of a number of additional packages during the course. You should be able to install all of the needed packages at once with the following command (this make take a few moments to complete):
install.packages(c("lme4", "numDeriv", "minqa", "nloptr", "dfoptim", "ucminf", "CompQuadForm", "BiasedUrn", "igraph", "multcomp", "plyr", "ape"))
Software to open/view PDF files should also be installed on the laptop (e.g., Adobe Reader or see Wikipedia for a comprehensive list of PDF software). In all likelihood, such software is already installed on your laptop anyway.
You can also pair up with another course participant for the computer exercises, so technically not everybody needs to bring a laptop. However, if at all possible, please bring your own laptop so we don't end up with the unfortunate situation that nobody brings one!
The course fee is 400 Euros and includes lunch, refreshments (e.g., coffee, tea, water) during the breaks, but not dinner or accommodations.
The course will be held at the Department of Psychiatry and Neuropsychology at Maastricht University in the Netherlands.
6226 NB Maastricht
Google Maps Link
If you arrive by car, just use the Google Maps Link to obtain directions depending on your starting point. There is a freely accessible parking lot south of the building (where the roads form a P-shape just underneath the building).
If you arrive by train, you should leave the train at the main station in Maastricht. Exit the station and take bus number 8 in the direction Valkenburg (careful, the bus only leaves once every hour at hh:52 the last time I checked). Take the bus to the Vijverdal stop (takes about 10 minutes). The building is right across the road from the bus stop.
Follow the walkway between the parking lot and the three-story building to the main entrance (the building is shown below; the walkway is to the left of the building). Inside, follow the signs for "Route 49" (at the reception, go right, then right again, follow the hallway, and then go up the stairs or take the elevator to the second floor). At the door, please ring the bell and wait for somebody to let you in.
If you need hotel accommodations, a useful website for hotel accommodations in and around Maastricht can be found here. Some possible options include the Novotel Hotel, Hotel van der Valk, and Hotel in den Hoof. All three hotels are located around 1.7km from the course location (note that Hotel in den Hoof is really on the outskirts of the city). For a map showing the course location and the location of these hotels, click here.
Begg, C. B., & Pilote, L. (1991). A model for incorporating historical controls into a meta-analysis. Biometrics, 47(3), 899–906. link
Berkey, C. S., Hoaglin, D. C., Antczak-Bouckoms, A., Mosteller, F., & Colditz, G. A. (1998). Meta-analysis of multiple outcomes by regression with random effects. Statistics in Medicine, 17(22), 2537–2550. link
Gleser, L. J., & Olkin, I. (2009). Stochastically dependent effect sizes. In H. Cooper, L. V. Hedges, & J. C. Valentine (Eds.), The handbook of research synthesis and meta-analysis (2nd ed., pp. 357–376). New York: Russell Sage Foundation.
Hasselblad, V. (1998). Meta-analysis of multitreatment studies. Medical Decision Making, 18(1), 37–43. link
Ishak, K. J., Platt, R. W., Joseph, L., Hanley, J. A., & Caro, J. J. (2007). Meta-analysis of longitudinal studies. Clinical Trials, 4(5), 525–539. link
Jackson, D., White, I. R., & Riley, R. D. (2013). A matrix-based method of moments for fitting the multivariate random effects model for meta-analysis and meta-regression. Biometrical Journal, 55(2), 231–245. link
Jackson, D., Barrett, J. K., Rice, S., White, I. R., & Higgins, J. P. (2014). A design-by-treatment interaction model for network meta-analysis with random inconsistency effects. Statistics in Medicine, 33(21), 3639–3654. link
Konstantopoulos, S. (2011). Fixed effects and variance components estimation in three-level meta-analysis. Research Synthesis Methods, 2(1), 61–76. link
Nakagawa, S., & Santos, E. S. A. (2012). Methodological issues and advances in biological meta-analysis. Evolutionary Ecology, 26(5), 1253–1274. link
Salanti, G., Higgins, J. P. T., Ades, A. E., & Ioannidis, J. P. A. (2008). Evaluation of networks of randomized trials. Statistical Methods in Medical Research, 17(3), 279–301. link
Senn, S., Gavini, F., Magrez, D., & Scheen, A. (2013). Issues in performing a network meta-analysis. Statistical Methods in Medical Research, 22(2), 169–189. link
Stijnen, T., Hamza, T. H., & Ozdemir, P. (2010). Random effects meta-analysis of event outcome in the framework of the generalized linear mixed model with applications in sparse data. Statistics in Medicine, 29(29), 3046–3067. link
Trikalinos, T. A., & Olkin, I. (2012). Meta-analysis of effect sizes reported at multiple time points: A multivariate approach. Clinical Trials, 9(5), 610–620. link
van Houwelingen, H. C., Zwinderman, K. H., & Stijnen, T. (1993). A bivariate approach to meta-analysis. Statistics in Medicine, 12(24), 2273–2284. link
van Houwelingen, H. C., Arends, L. R., & Stijnen, T. (2002). Advanced methods in meta-analysis: Multivariate approach and meta-regression. Statistics in Medicine, 21(4), 589–624. link