Re: Distribution of a Percetile
Bob Wheeler wrote:
> You would be better advised to assume a distribution, likely
> exponential, and test estimates of the parameters. I'd use the mean. By
> testing a percentile you are throwing away information.
I was under the impression -- gained elsewhere, not in this thread --
that "85th percentile" has about the same status in traffic speed
discussions that ".05" has in hypothesis testing.
.
Relevant Pages
- Re: (hyper)sensitivity of goodness-of-fit tests
... What if I took random subsets of the observed data, ... goodness-of-fit tests using these smaller subsets and then used the ... distribution, I see an almost perfect linear relationship. ... in ALL Neyman-Pearson type of hypothesis testing -- so Kolmogorov ...
(sci.stat.math) - Re: CONFIDENCE LIMITS AROUND A PERCENTILE
... CONFIDENCE LIMITS AROUND A PERCENTILE ... Fot the normal distribution, it's based on the ... CONFIDENCE INTERVALS FOR QUANTILES ... This algorithm is based on the Normal Distribution ...
(sci.stat.math) - Re: (hyper)sensitivity of goodness-of-fit tests
... What if I took random subsets of the observed data, ... goodness-of-fit tests using these smaller subsets and then used the ... distribution, I see an almost perfect linear relationship. ... in ALL Neyman-Pearson type of hypothesis testing -- so Kolmogorov ...
(sci.stat.math) - Re: (hyper)sensitivity of goodness-of-fit tests
... Why would you go to so much trouble to numb the test so that it fails ... The data you posted indicate a strong departure from an exponential ... another distribution and move on with it? ... in ALL Neyman-Pearson type of hypothesis testing -- so Kolmogorov ...
(sci.stat.math) - Re: (hyper)sensitivity of goodness-of-fit tests
... goodness-of-fit tests using these smaller subsets and then used the ... -- Reef Fish Bob. ... distribution, I see an almost perfect linear relationship. ... in ALL Neyman-Pearson type of hypothesis testing -- so Kolmogorov ...
(sci.stat.math) |
|
