Talk:Percentile

Replacing WP

I replaced the WP import by a new article, and added an example (test results) previously inserted by Anh Nguyen (3rd revision, 10:11, 8 November 2006). Peter Schmitt 16:03, 23 November 2009 (UTC)

Not quite so

The implication

$P(\omega =x)>0\Rightarrow P(\omega \leq x)>{k \over 100}{\textrm {\ \ and\ \ }}P(\omega \geq x)>1-{k \over 100}$

is not always true; when k is at the left endpoint of the relevant interval, the first inequality is not strict; and when k is at the right endpoint of the relevant interval, the second inequality is not strict. In addition, I did not understand from the article, is k assumed to be integral, or not? If it is then these non-strict inequalities become more rare cases, but still possible. Boris Tsirelson 19:11, 26 November 2009 (UTC)

Thank you for spotting the p's. I changed from p to k and forgot them.

Yes, I think that percentiles are used for integer k. I am no statistician, so I cannot be absolutly sure. But I have two reasons to assume that integer values are the usual case (though everybody who understands them will understand arbitrary values):

They are usually called "k-th percentile.

For general probabilities there is the quantile.

And, yes, I overlooked the special case in the inequality. It should be "or" instead of "and".

Peter Schmitt 00:57, 27 November 2009 (UTC)