Calculation of Tolerance Intervals for Non-Normally Distributed DataLike in other statistical software it would be nice to be able to calculate tolerance intervals for the following non-normal distributions:
- Lognormal
- Gamma
- Exponential
- Smallest extreme value
- Largest extreme value
- Logistic
- Loglogistic
- Weibull
I know there are some workarounds and normalizing via transformation ist always a possibility, but having just to press one button would be perfect.
Best regards,
Christian
Quality and Process EngineeringRe: Calculation of Tolerance Intervals for Non-Normally Distributed DataHello @ChrisGaltress, No update unfortunately, I haven't been able to get to this. Let's try a different approach. Can you please send us an email to support@jmp.com and address it to me directly? "Hi Patrick..." Please reference this community post and give the subject line a meaningful header "Calculation of Tolerance Intervals for Non-Normally Distributed Data." I can work with you directly to demonstrate the 'alternate' approach that I am thinking for your case, and to identify its limitations (off hand, we don't support SHASH in Life Distribution which is where I think you would need to go here).
Re: Calculation of Tolerance Intervals for Non-Normally Distributed DataHi Patrick,
Any update on JMPer Article? Agree with others that this would be a welcome addition to JMP. I'm currently working on a project that requires calculating tolerance intervals from numerous (100s) of simulated non-normal sample sets. I'm working mostly w/ Weibull, Lognormal, and SHASH distributions and would like to be able to calc & export the lower bounds at 90% coverage & 95% confidence for these sample sets into table format to estimate the predicted failure rate of being below the lower bound.
Re: Calculation of Tolerance Intervals for Non-Normally Distributed DataThanks, will stay tuned. We're med dev and will have to validate the method in order to use it, so hopefully a test data set and expected results will be available with this.
Re: Calculation of Tolerance Intervals for Non-Normally Distributed DataThanks for chiming in here @Stoic. As of JMP 18.x, we do have a way of generating these but not in the "traditional sense," i.e. using the Tolerance Intervals red triangle menu option under the Distribution platform (similar how you might report/ generate these in a competitors' statistical package). I am planning to write a JMPer Cable Article that walks through that process and will try and circulate it here once I have it done.
Re: Calculation of Tolerance Intervals for Non-Normally Distributed DataPiling onto this request. New JMP user here, and I'm surprised that this feature is missing.
Re: Calculation of Tolerance Intervals for Non-Normally Distributed Data - Status changed to: AcknowledgedHi @christianguhr, thank you for your suggestion! We have captured your request and will take it under consideration.
