| Blog | https://fharrell.com |
| Web Site | https://hbiostat.org |
| Discussion Board | http://datamethods.org |
In this article I provide much more extensive simulations showing the near perfect agreement between the odds ratio (OR) from a proportional odds (PO) model, and the Wilcoxon two-sample test statistic. The agreement is studied by degree of violation of the PO assumption and by the sample size. A refinement in the conversion formula between the OR and the Wilcoxon statistic scaled to 0-1 (corcordance probability) is provided.
Author summary Autocorrection is a feature of modern softwares including messaging apps, word processors and spreadsheets. These are designed to avoid data entry errors but “autocorrect fails” can lead to information being distorted in undesired and sometimes humorous ways. What is not funny though is having genomics spreadsheets suffer from auto-conversion of gene names like SEPT8, DEC1 and MARCH3 into dates, a problem first characterised in 2004. A 2016 article on this topic led the Human Gene Name Consortium to change many of these gene names to be less susceptible to autocorrect. Despite this, our work here shows that gene name autocorrect errors continue to accumulate in supplementary genomics spreadsheet files at a rapid pace. To avoid this and other reproducibility problems with spreadsheets, big changes are required in the way genomics scientists analyse and share data. We provide several practical steps researchers can take to avoid gene name errors and reiterate that big genomics data analysis is better suited to Python/R notebooks rather than spreadsheets.
