Benedikt Venn

[Feature Request] Confidence bands for polynomial and nonlinear regression

1

**Is your feature request related to a problem? Please describe.** Confidence and prediction bands offer a interesting insight into regression outcomes. While the fitted function (correct model selection is assumed)...

While a weighting is possible for polynomials, a weighting for simple linear regression is missing **Describe alternatives you've considered** Using polynomial regression with order = 1 @Joott

[Feature Request] Missing medianOfRatios normalization documenation

2

A proper documentation of the medianOfRatios normalization should be added. From a mathematical perspective the calculation of the geometric mean as the nth square root of the product of all...

Update Normalization module

4

### Description The normalization module is located within the `Signal` folder but is within the `FSharp.Stats` namespace. This should be updated to `FSharp.Stats.Signal`. @HLWeil Furthermore the random matrix theory is...

### Description There are three ways to account for ties in kendalls rank correlation coefficient. It is unclear which one is used in the implemented version in Correlation.Seq.kendall. Comments, a...

[Feature Request] Dunnett's test

3

**Is your feature request related to a problem? Please describe.** Post hoc tests are used to inspect a multipe-group-comparison (e.g. ANOVA) for individual significant group mean differences. While Tukey's HSD...

[Feature Request] Wilcoxon signed ranked test

4

A Wilcoxon test compares two samples deriving from non-parametric distributions. While a test for multiple samples exists in FSharp.Stats (H-test), a test for two samples is missing. - [x] Wilcoxon...

### Description As described in Discussion #156 there is a need for OPTICS clustering (Ordering Points To Identify the Clustering Structure) as alternative for DBSCAN. ### Pointers See discussion #156...

Renew fitting module structure

4

### Description The Fitting module currently is fragmented into modules of diverse complexity. The usage of one of the most used regression types (simple linear regression) is hidden under several...

Features that are needed for 1.0.0 are tracked here. Feel free to add suggestions/issues. - [x] integration of interactive notebooks - [x] move docs to newest FSharp.Formatting for `fsdocs` -...