Peter Örtlund
February 1, 20110
Home › Forums › General Forums › Tools & Templates › Confidence intervals in order statistics
| Author | Posts |
|---|---|
| Author | Posts |
| February 1, 2011 at 6:44 am #168761 | |
|
Örtlund @Exiguus Reputation - 10 Rank - Aluminum
|
Hi, I’m trying to understand (with emphasis on trying) a new discipline in statistics for me, order statistics. What I’m trying to figure out is how to calculate the CI (95%) for a specific percentile. It is probably easiest described in my actual problem. The thing I am trying to achieve are how to calculate the CI for percentile P2,5 and P97,5 for a dataset of n=160 in excel. The percentile is easy using the command “PERCENTILE(array,k)” instead of going by rank and find it. However it doesn’t seems to be a function to calculate the CI level? Can anyone help me? Preferably in layman’s terms ;-) Regards |
| February 1, 2011 at 3:30 pm #168764 | |
|
Butler @Robert-Butler Reputation - 0 Rank - Aluminum
|
It’s too long to paraphrase but I can point you to a pretty good description of what you will need to do in order to build something in Excel. pp. 15 – 19 Distribution FreeConfidence Intervals for Quantiles – in Order Statistics 2nd Edition by David. My copy is old. I suspect either the most recent edition of this work or any other basic book on order statistics will have the same information. |
| February 2, 2011 at 12:08 pm #168771 | |
|
Örtlund @Exiguus Reputation - 10 Rank - Aluminum
|
ok :ohmy: not as straight forward as I hoped for then… O well, I’m always glad for new books anyway =) Thanks a lot for your answer, life is always easier with an direction ;-) Regards /peteR |
© Copyright iSixSigma 2000-2013. User Agreement. Any reproduction or other use of content without the express written consent of iSixSigma is prohibited. More »