Henry Garner

Transforming a distribution via truncation is a neat idea. I'll take a look at the chi-squared issue.

I'm going to go out on a limb: is this request driven by the recent addition of Apache Commons Math3 in `kixi.core`? If so, I support moving LOESS to a...

@gmp26 Hi Mike, apologies LOESS has been added since the latest official release. If you update the kixi/stats dependency to "0.4.4-SNAPSHOT" you'll be able to use the `locally-weighted-regression` function in...

@holtzermann17 running `lein test-cljs` shows all tests as passing after bumping the ClojureScript dependency to 1.10.597. Are you able to provide a minimal example?

@kovasap this is something which would be an excellent addition to the library. There are a handful of significance tests already in the `kixi.stats.test` namespace, but not correlation yet. I've...

> do you mean the number of data points used to compute the correlation ((count data) in your example above That's right. The number of observations is required for calculating...

That's a fair question: it would be possible to leverage the p-value calculation in order to determine significance at a given alpha. Given a test statistic, a test distribution, and...

@kovasap thanks for the excellent question. This is not something that is supported in kixi.stats currently. In my experience implementations would normally make use of matrix decomposition or numerical optimisation...