<div dir="ltr">Just out of curiosity: What is the significance of the weights?  If you are trying to represent the fact that distributional differences are more important in some regime than in another, e.g., you care more about the tails, then using weights is probably not the right approach.</div><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Apr 21, 2018 at 4:42 PM, Corin Hoad <span dir="ltr"><<a href="mailto:corinhoad@gmail.com" target="_blank">corinhoad@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Hello developers,<br><br>I recently needed an implementation of the Kolmogorov-Smirnov 2 sample test which required the incorporation of a weight associated with each element of the data.  This lead me to this stackexchange answer <a href="https://stats.stackexchange.com/questions/193439/two-sample-kolmogorov-smirnov-test-with-weights" target="_blank">https://stats.stackexchange.<wbr>com/questions/193439/two-<wbr>sample-kolmogorov-smirnov-<wbr>test-with-weights</a> where a procedure for a weighted 2-sample KS test is taken from Numerical Methods of Statistics by Monohan.<br><br>My current implementation of this can be found here:<br><br><a href="https://github.com/brunel-physics/tact/blob/2b0ee2a28a30f014b103319118b64be52070f001/tact/metrics.py#L198" target="_blank">https://github.com/brunel-<wbr>physics/tact/blob/<wbr>2b0ee2a28a30f014b103319118b64b<wbr>e52070f001/tact/metrics.py#<wbr>L198</a><br><br>Would there by any interest in incorporating this functionality into scipy?<br><br>Yours,<br><br>Corin Hoad<br><br></div>
<br>______________________________<wbr>_________________<br>
SciPy-Dev mailing list<br>
<a href="mailto:SciPy-Dev@python.org">SciPy-Dev@python.org</a><br>
<a href="https://mail.python.org/mailman/listinfo/scipy-dev" rel="noreferrer" target="_blank">https://mail.python.org/<wbr>mailman/listinfo/scipy-dev</a><br>
<br></blockquote></div><br></div>