Hi! I need to calculate estimates of the confidence intervals for extreme quantiles, say q1 and q99 (or q(0.1) and q(99.9)).
My knowledge of this type of mathematical statistics is not so great.
I know that there are options in Proc Means or Univariate, for something like this.
But I need to do these calculations in a Data-step.
If anyone has a tip of some good papers to read and implement, then I would appreciate thsi very much.
(I will use this info to try to automatically estimate the parameters LLM and ULIM in the method:
"Fast and Accurate Calculation of Descriptive Statistics of Very Large Sets of Data".
The work is paused at present. I need a break. But extended paper will appear during 2024).
Many thanks in advance!
/Br AndersS (Anders Sköllermo)
The CIPCTLDF option on the PROC UNIVARIATE statement produces distribution-free confidence intervals. The formulas are in the doc.
Hahn and Meeker are a little vague about one portion of the formula. See this discussion from someone who was trying to reproduce the formula in R and was unable to match the PROC UNIVARIATE output.
Why would you want to use a DATA step if SAS has already done the work and provided confidence intervals for percentiles in PROC UNIVARIATE (and probably elsewhere)?
Hi! 1) se my text in ( ).
2) See the answer from Rick. I want to be able to use another language than SAS.
/Br AndersS
How about Bootstrap method ?
@Rick_SAS wrote many blogs about it to get statistic confidence interval.
https://blogs.sas.com/content/iml/2018/07/23/boot-and-bootci-macros-sas.html
https://blogs.sas.com/content/iml/2016/08/10/bootstrap-confidence-interval-sas.html
The CIPCTLDF option on the PROC UNIVARIATE statement produces distribution-free confidence intervals. The formulas are in the doc.
Hahn and Meeker are a little vague about one portion of the formula. See this discussion from someone who was trying to reproduce the formula in R and was unable to match the PROC UNIVARIATE output.
Hi! The basic discussion was in 2019. Has SAS updated the software and/or the documentation?
VERY useful discussion for me! MANY thanks! /Br AndersS
> The basic discussion was in 2019. Has SAS updated the software and/or the documentation?
The software has not changed. I gave the link to the most recent documentation.
Hi! Very good. My problem has been solved. /Br AndersS
Registration is now open for SAS Innovate 2025 , our biggest and most exciting global event of the year! Join us in Orlando, FL, May 6-9.
Sign up by Dec. 31 to get the 2024 rate of just $495.
Register now!
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.