Skip to main content
14 events
when toggle format what by license comment
Jul 9, 2023 at 11:45 vote accept Math_Y
Jul 7, 2023 at 19:16 comment added Iosif Pinelis @MichaelHardy : In general parlance, "sample" may mean "specimen". In statistics, it usually means a sequence of sample points. I would be happy if terms like "sample" were totally banned on MO. In this case, I would use "$X_i$'s" instead of "samples". However, I understood this answer and, because it is Fedor Petrov's, I had no doubts as to whether he understands what he is talking about. :-)
Jul 7, 2023 at 19:13 comment added Fedor Petrov @MichaelHardy you are probably correct. How should I call each $X_i$ instead?
Jul 7, 2023 at 18:42 comment added Michael Hardy @IosifPinelis $\qquad\uparrow\qquad$
Jul 7, 2023 at 18:42 comment added Michael Hardy As I mentioned in comments under the question, I think you're using the word "sample" incorrectly. The whole sequence $X_1,\ldots,X_N$ is one sample, not $N$ samples. Otherwise, why would we speak of the size of a sample, or say that a bigger sample is needed, or speak of a "two-sample t-test"?
Jul 7, 2023 at 14:40 comment added Iosif Pinelis Very nice! +1 ...
Jul 7, 2023 at 14:34 comment added Fedor Petrov @IosifPinelis thank you, fixed this too
Jul 7, 2023 at 14:33 history edited Fedor Petrov CC BY-SA 4.0
added 4 characters in body
Jul 7, 2023 at 14:31 comment added Iosif Pinelis Also, I guess, instead of $N^{19/20}$, you meant $N^{-19/20}$.
Jul 7, 2023 at 14:30 comment added Iosif Pinelis The expected number of samples less than $N^{1/2}$ is $NP(X<N^{1/2})\sim N$. Or, perhaps, I misunderstood what you meant by the expected number of samples less than $N^{1/2}$.
Jul 7, 2023 at 8:50 comment added Fedor Petrov @JamesMartin thank you, fixed
Jul 7, 2023 at 8:49 history edited Fedor Petrov CC BY-SA 4.0
edited body
Jul 7, 2023 at 8:22 comment added James Martin I think the $N^{19/20}$ towards the end is meant to be $N^{19/10}$.
Jul 7, 2023 at 4:18 history answered Fedor Petrov CC BY-SA 4.0