EP023 Reproducible Science and Synthetic Datasets Using R

FLOSS for Science

Content provided by FLOSSforScience. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by FLOSSforScience or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.

5+ y ago 55:36

MP3•Episode home

In episode 23, we interviewed Dan Quintana from the University of Oslo. We started the discussion with him by asking the link between all his subjects of interest and where R fits into his workflow. We then had an extensive discussion about R including his must have R packages and the synthpop package for generating synthetic datasets. We then widened the discussion and talked about the multiple facets of open science and reproducibility. Dan then talked about what he sees as one of the next big challenge of science. We finished the interview with our usual quick questions. 00:00:18 Introduction 00:00:39 Presentation of Dan Quintana 00:01:55 The links between his research interests 00:04:00 Where does R fits in his workflow 00:05:22 His 30 seconds elevator pitch for R 00:06:28 How difficult is it to switch from SPSS to R? 00:08:05 The best time to switch to R 00:08:40 JASP and Jamovi as a gateway to R 00:10:53 Standing on the shoulders of giants with R 00:12:15 R or Python? 00:14:00 Dan's must have R packages 00:15:59 Ressources to learn R 00:17:21 Introduction to synthetic datasets 00:21:54 Synthetic datasets for privacy and their limitations 00:24:52 How much time should be spent to publish datasets and code 00:26:58 Dan's view on open science practices 00:28:27 FLOSS and open science practices 00:30:49 The licence he uses for sharing code and data 00:32:06 Obtaining a DOI with the Open Science Framework 00:32:21 Journal of Open Source Software 00:34:15 The importance of publishing in open access journals 00:37:28 Publishig in open access journals and plan S 00:39:09 The lack of affordability for open access publishing 00:40:22 Preprints as a solution? 00:43:04 How to publish a perfectly reproducible paper 00:46:02 How to convince other scientists to share their data and code 00:46:42 The next big challenge of science 00:48:55 The most notable discovery in recent years 00:51:20 Favourite text processing tool 00:51:43 A topic in science he recently changed his mind about 00:52:49 Anything else? 00:53:34 How to contact Dan Quintana 00:53:56 Conclusion

35 episodes

#Tech #Podcasting #FLOSSforScience