 Hi everyone, in this video I'll be providing a brief introduction to our hands-on guide doing meta-analysis with R. I'll be describing what it is and how to use it. As it says in the title, our guide provides a hands-on introduction to meta-analysis using R. It tries to convey a conceptual understanding of common meta-niltic methods and directly describes how to implement them using real-life examples. Importantly, the guide is specifically designed for meta-analysis and R beginners. Some background. Many would agree that R provides us with the most comprehensive toolbox for research synthesis and meta-analysis that we have to date. There is a huge and ever-increasing number of really amazing R packages out there. However, to use them, we first need a basic proficiency in R. Also, we need to know which packages are actually available for different meta-analytic research questions and how we can use them. The guide tries to bridge this gap by providing a broadly accessible introduction to the R meta-analysis ecosystem. We give a general introduction to R itself and cover both basic and somewhat more advanced meta-analytic techniques. Also, our guide is openly available online for everyone. The target audience, our students or researchers, without previous experience in meta-analysis, are or both. The guide may also be helpful for more experienced meta-analysts who want to switch to R or for those who need a quick reference tool while working on a specific meta-analysis project. Here's how you can start working with the guide. There are generally two ways to access the contents. The first option is to use the online version, which can be found openly accessible on bookdown.org. This version contains all the content and it is a living document. It is regularly updated to reflect software changes and new findings in the literature. Alternatively, you can also purchase a hard copy of the guide, which has been published with CRC Press. In this video, we'll be focusing on how to get started using the online version of the guide. This is the landing page. As you can see, it features a three-column layout. The left column contains the navigation menu displaying all the book's chapters. On the right column, you can view the contents of a specific chapter. Furthermore, the website includes a dark mode switch to cater to your preferences. The guide comes with a companion R package called Dimita. This package encompasses all the datasets that we utilize in the hands-on examples featured in the guide. Along with a few helper functions. To install the package on your computer, you can visit dimita.protectlab.org, where you'll find the code required for installation. While installing the package is recommended, it is not necessary to work with the guide. Chapter 2 also provides further information on Dimita. Here are the contents we cover. There are four sections, Getting Started, Med Analysis in ARM, Advanced Methods, and Helpful Tools. The contents are intended to be read in a linear fashion, so one chapter after another. In the first section, we start with an introduction to Med Analysis, including its historical background, common pitfalls, and importantly, the problem specification and study search. While this is not the focus of the guide, it might provide a helpful refresher on non-statistical aspects that constitute a high-quality Med Analysis. The next part is an introduction to R. Since the guide is geared towards beginners, we start with the absolute basics, so how to install R, what's the difference between R in our studio, how do I import data, and also how to manipulate data in R? We already do all of this with a direct focus on meta-analytic datasets as they commonly appear in practice. The next section covers essential or at least highly relevant aspects of every meta-analysis. We describe how to calculate effect sizes using R, for example correlations, standardized mean differences, odds ratios, risk ratios, and so on, how to pool effect sizes using an equal effect or random effects model, how to quantify and assess the between-study heterogeneity, and how to check our meta-analytic models assumption. We also provide hands-on examples on how to generate a nice-looking forest plot, run subgroup analyses and meta-regression, and how we can evaluate the impact of publication bias. In the advanced method section, we introduce more involved but still highly relevant meta-analytic methods such as three-level meta-analysis, robust variance estimation, structural equation modeling meta-analysis, network meta-analysis, and how to conduct meta-analysis within a Bayesian framework. Lastly, the helpful tool section describes how to conduct an a priori power analysis, how to produce risk of bias plots using R, and how to convert between effect sizes. The latter is often necessary because different metrics are reported in the studies that we collected. Here you can see some core packages that we introduce in the guide. The main workhorses are meta and metaphor to excellent and well-documented packages that are helpful in a variety of contexts. We also introduce packages that focus on a specific type of meta-analysis, such as GMTC and NetMeta for network meta-analysis, or Metasam for meta-analytic structural equation modeling. There are a few components which appear regularly throughout the guide. For example, text boxes displaying general notes, important information, information on the Demeter package, and ways to report results of various meta-analytic methods. The Demeter boxes appear every time a new data set is introduced in hands-on exercises. If Demeter is installed on your computer, you can directly import the example data set into your own R environment and start coding along. Reporting boxes, on the other hand, show how results of an example analysis can be displayed in scientific reports. At the end of each chapter, we also provide a set of questions which can be used to test one's knowledge. Answers are provided at the end of the book in the appendix. There you can also find a lookup table which displays formulas for common effect sizes and their standard errors, as well as functions in R which can do these calculations for us. For instructors, we provide all source files used to compile the guide on a repository on GitHub. You are free to recompile, reuse, or adapt the guide, for example, for your own teaching. To do this, you can clone the entire repository to your own computer and then use the bookdown package to render the guide locally. Feel free to contact us if you need further assistance in compiling your own adapted version of the guide. Lastly, a few limitations. The guide is intended to provide a basic conceptual introduction into meta-analysis using R. However, meta-analysis remains a complex and multifaceted topic, and continuous learning is needed to become an expert. Some parts of the advanced topic section in particular might be more difficult to understand for beginners, especially if the previous chapters are skipped. Thankfully, the guide is by no means the only resource we can recommend to novice and more experienced meta-analists. Another very helpful and practical book is meta-analysis with R by Schwarzen colleagues, which also includes a plethora of examples in R and a little more technical details than we do in our guide. Another great way to learn more about meta-analysis using R are streams offered by Wolfgang Viehbauer on Twitch. There are also great and very instructive YouTube videos on meta-analysis made by Dan Quintana. Lastly, if you're looking for an authoritative and more comprehensive resource on meta-analysis and all its intricacies, you can recommend the handbook of meta-analysis, which has also been published with CoC Press. Finally, I want to thank my co-authors, Pym Kipers, Toshi Furukawa and David Ebert for their support, and also want to thank you for your attention. I hope you find the guide helpful and informative, and I wish you all the best for your own meta-analysis project.