statistics
statistics copied to clipboard
haskell
A fast, high quality library for computing with statistics in Haskell.
This should be relatively straightforward to implement: type `permutationTest :: (v a -> v b -> Double) -> Int -> PValue`, i.e. takes in a function that takes a vector...
All API of `Statistics.Sample` works only with vectors. It would be handy to add functions for working with containers implementing `Foldable` as well. One downside is duplication of the API....
Error with a vector of two vectors, one of length 4752 and one of length 1974: `Statistics.Types.mkPValue: probability is out if [0,1] range`.
Rather than Nothing/0/NaN etc. (the first option being way better than the others), it would be great to generalize code that may throw to the MonadThrow class from `exceptions`. This...
`spearman` should return Nothing rather than NaN: `spearman $ V.fromList [(1, 3), (5, 3)]`, or any case where one of the two variables is a constant.
There is an isolated `benchmark/bench.hs` file that could be included as a `bench` stanza of the cabal file.
I extended `olsRegress` to the following settings with normally distributed errors (1) homoskedastic errors, known variance (2) homoskedastic errors, unknown variance (3) heteroskedastic errors, known variance (4) heteroskedastic errors, unknown...
I have been trying to use this package with `nonlinear-optimization` and `ad` for maximum likelihood computations, however this is highly non-practical since distributions always return `Double -> Double` and `ad`...
To calculate k-th q-quantile `weightedAvg` sorts approximately k/q smallest elements of an array. When k/q > 0.5 it's not optimal. We only need to sort upper 1-k/q elements in this...
Here is simple test case: ``` kde 32 $ U.fromList [0,0,0,1] ``` It looks like negative values are artifact of FFT.