0
$\begingroup$

When I do a ks.test in R for a sample to check from which distribution it is, it gives me a 𝑝 value less than 0.01 for various distributions and I don't know why. It gives these small p values for normal and exponential distribution, but for Poisson distribution it asks for lambda. I don't know any parameters. Also, I have a dataset in r with two columns (samples) and the ks.test even gives an output for the whole dataset ( when I write ks.test(x = data, y = pnorm). Anyway I don't know how to correct the issue so that the test really shows from which distribution the data is drawn.

$\endgroup$
  • $\begingroup$ When you write x=data, you need to tell R which column to select, something like x=data[,1] for the first column. The rest of your post is quite confusing, especially given the lack of code and the exact output you get. $\endgroup$ – Dave May 27 at 10:38
1
$\begingroup$

KS won't tell you that. It will only tell you about whether it comes from any particular distribution. The p values are conflated with sample size.

But it's entirely possible for a sample to not come from any standard distribution.

| cite | improve this answer | |
$\endgroup$
  • $\begingroup$ What does "p values conflated with sample size mean"? After all, p-values of any test depend on the sample size, caeteris paribus. $\endgroup$ – whuber May 27 at 15:58

Not the answer you're looking for? Browse other questions tagged or ask your own question.