Skip to main content
9 events
when toggle format what by license comment
Jul 4, 2023 at 14:27 comment added Dave @amitha The $\alpha$-level means what it is supposed to mean (not a given that every test has this property, but Ks behaves pretty well). Perhaps read what I posted here.
Jul 4, 2023 at 11:47 vote accept amitha
Jul 4, 2023 at 11:47
Jul 4, 2023 at 11:22 comment added amitha @Dave You are right. I meant to say that probably KS test is not what I should be targetting to show that the model fits the dataset. I am still not sure I understand what you mean here "yet it does not reject particularly often when the null is true"
Jul 3, 2023 at 16:35 history edited Gregg H CC BY-SA 4.0
edited semantics (and added clarification for original word choice)
Jul 3, 2023 at 16:31 comment added Dave @amitha Reliable in what sense? I say the KS test is extremely reliable when the sample size gets large, as its ability to detect deviations from the null hypothesis becomes spectacular, yet it does not reject particularly often when the null is true.
Jul 3, 2023 at 14:38 comment added Gregg H @amitha It is reliable for detecting distributions that are not in agreement with the test distribution...but to use the test to confirm that your distribution IS in agreement (which I believe you wish to do), you must have near perfect agreement to achieve this. (When I get a chance, I will prepare a simulation to demonstrate this and add as an edit to my answer.)
Jul 3, 2023 at 14:24 comment added amitha Is that to say KS test is not reliable for datasets of larger size? Rather than, graphical interpretation is there any metric that can be used for evaluation?
Jul 3, 2023 at 14:11 comment added whuber It's difficult to conceive of what "over-powered" might possibly mean and how that distinguishes this test from any null hypothesis test.
Jul 3, 2023 at 14:11 history answered Gregg H CC BY-SA 4.0