> Experiencing first-hand just how unreproducible most research in our faculty was (SPSS was the norm, R was the exception, Python was unused).
How did you experience this? Did you fail to reproduce the same results when doing the research again while using R? This is how I interpret your statement, but I think it's not what you mean.
If SPSS was the norm, R or SciPy shouldn't have made a difference in reproducibility as the statistics should be more or less the same. I did social science with SPSS fine; T-Tests, MANOVA, Cronbach's alpha, Kruskall-Wallis, it's all in there. It seems you suggest that using SPSS inherently makes for bad and irreproducible science, it's similar to saying using Word instead of an open source package like LaTeX makes research unreproducible even if the data, methodology and statistics are openly accessible. This is not the case. What i mean is that while I agree there can be friction between using Word and SPSS and
Open Science and FAIR principles because of the proprietary formats, this isn't inherently a problem as people can use the dataset (csv or sqlite) and do the mentioned statistical tests outlined in the published pdf (or even an imported docx) in any statistical language.
How did you experience this? Did you fail to reproduce the same results when doing the research again while using R? This is how I interpret your statement, but I think it's not what you mean.
If SPSS was the norm, R or SciPy shouldn't have made a difference in reproducibility as the statistics should be more or less the same. I did social science with SPSS fine; T-Tests, MANOVA, Cronbach's alpha, Kruskall-Wallis, it's all in there. It seems you suggest that using SPSS inherently makes for bad and irreproducible science, it's similar to saying using Word instead of an open source package like LaTeX makes research unreproducible even if the data, methodology and statistics are openly accessible. This is not the case. What i mean is that while I agree there can be friction between using Word and SPSS and Open Science and FAIR principles because of the proprietary formats, this isn't inherently a problem as people can use the dataset (csv or sqlite) and do the mentioned statistical tests outlined in the published pdf (or even an imported docx) in any statistical language.
https://www.go-fair.org/fair-principles/
For anyone looking for an easy to use alternative to R, Jamovi is a capable and easy to use open source alternative to SPSS and RStudio. https://medium.com/@Frank.M.LoSchiavo/jamovi-a-free-alternat...