User Community
cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Show  only  | Search instead for 
Did you mean: 
  • Due to the recently reported Microsoft outage, users may be temporarily unable to access My JMP or experience a delay receiving their verification codes. If you have previously installed JMP on your computer, this outage should not impact your ability to access the software. My JMP services will be restored as soon as Microsoft resolves this issue.
  • Image to Table JMP extension imports single or batch images as data tables. Useful to extract curves from pictures or convert image data to curve data to use in analyses like Functional Data Explorer. Download and install the extension.

JMP Wish List

We want to hear your ideas for improving JMP. Share them here.
Choose Language Hide Translation Bar
0 Kudos

Confidence Intervals for Overall and Within Sigma Estimates in Process Capability

Status: New Submitted by on ‎02-26-2024 02:09 PM
Comment

What inspired this wish list request? I am trying compare the Within Sigma estimate of variation between groups, and I am unable to do so since I cannot generate confidence intervals for those estimates.

gwenhallberg_0-1708973452568.png

 

What is the improvement you would like to see?  The Capability platform now helpfully includes 95% Confidence Intervals for the various Cpx and Ppx estimates, but I can’t get the same type of information for the Within Sigma estimate.  Ultimately, I would like to be able to easily obtain confidence intervals for the Overall and Within Sigma estimates in Process Capability in all platforms where that is used.  (Distribution, Control Chart Builder, Process Capability, etc.)  It would also be beneficial to generate CIs for the Stability Index to provide a quick assessment of how this ratio compares to 1.

 

As an editorial comment, it is harder than I would like it to be to generate the confidence interval information for the Overall Sigma Std Deviation, but I can do it in the Distribution Platform using the Confidence Intervals option.  (Would like it to be an option for the summary statistics as well).  I can also get there in Fit Y by X under the Means and Std Deviations option in JMP 17, but you have to right click the table and add the columns to the report – and not a lot of people know you can even do that.

gwenhallberg_1-1708973748943.png

 

Why is this idea important? Confidence intervals are important so that we can understand the uncertainty associated with any statistical estimate.  Without this information readily available, people will often make incorrect assumptions - especially when sample sizes are small.