Benedikt Venn

Thanks for reporting this issue. I had a look at it and indeed there is no trivial anwer to it. In general we try to add specialized functions to handle...

In the past we already had some optimizations, that we had to omit because of dependencies of the Microsoft solver foundation (see [here](https://github.com/fslaborg/FSharp.Stats/tree/8aa360c8aebbd7f819bfb04469b7761401e2fb06/src/FSharp.Stats.MSF/Optimization)). It would be great to have these...

Just listing some thoughts for remodeling: 1. The central element of the linear regression module should be multivariable polynomial regression. From here on simple linear regression as well as univariable...

> Agreed with everything here, just note that it is not absolutely necessary to update blog posts as the respective packages still work. It does not work if there is...

RMT migration to Signal is more difficult than expected: ``` - Signal - - Distribution - KernelDensity

It may be beneficial to implement a second version of the median of ratios (mor) normalization method, that works on log transformed data. When the data is already log transformed...

Additionally, it would be great to have access to the applied scaling factors to check the validity of the normalization!

Thanks for your contribution, the commit looks fine 🚀 Could you add some unit tests for the new functions? You could copy the [mean tests](https://github.com/fslaborg/FSharp.Stats/blob/3bf8e23177ad93bf19f0ed5293f83d78539dd602/tests/FSharp.Stats.Tests/Seq.fs#L44) to check the meanQuadratic for...

I have to clarify myself since I noticed there are two versions that easily get mixed up. 1. Mann–Whitney U test that tests two **independent** samples 2. Wilcoxon signed-rank test...

Wilcoxon test is implemented with documentation and unit tests. @omaus, what is the status of the Mann-Whitney U test?