 Welcome to my lightning talk on myth methods, an R package for creating and handling missing data as well as evaluating missing data methods. My name is Tobias Rockl and I am the creator of the package myth methods. The package myth methods aims at making the evaluation of missing data methods easier. Therefore, it supplies functions for the three main steps in the valuation process of missing data methods. The first main step is the creation of missing data. For this step, the package supplies various delete functions. The next step is the handling of missing data, for which right now only basic imputation algorithms are implemented. However, there exists a wide variety of other great R packages for the handling of missing data. The last step is the evaluation of the missing data methods, for which the evaluate functions can be used. The names of the functions are designed to clearly indicate their purpose and to be easy-memorable. At the moment, the delete functions are the heart of the package. The functions for the two other steps are more or less work in progress. Most of the delete functions are based on the paper by Santos et al. from 2019. Nearly all possibilities of creating missing data discussed by these authors and some additional are implemented via easy-to-use functions. The vignette generating missing values explains the usage of these functions and contains a table that shows the connection between the functions from the package and the paper by Santos et al. You can see a part of this table on this slide. As you can see from this part of the table, all function names indicate the created missing data mechanism. Furthermore, different types of missing at random and missing not at random are implemented and the function names indicate the type 2. So, from the function name, you can clearly see what type of missing data you will get. A first aim of the package is to provide easy-to-use functions for the comparison of missing data methods. Until now, many authors used self-created functions which maybe are not even published to compare missing data methods. If these self-created functions would be replaced by functions from an open source package, the reproducibility of missing data method simulation would raise. Summing up, I hope that the package myth methods will simplify the design of missing data simulations and increase their reproducibility. If you are curious, you can get the released version of myth methods from Crane or the development version from GitHub the usual way. Thank you for your attention.