cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Register for our Discovery Summit 2024 conference, Oct. 21-24, where you’ll learn, connect, and be inspired.
Choose Language Hide Translation Bar
zjwright
Level II

Difference between Weibull and TH Weibull & when to use?

Title of this question pretty much says it all. I normally use Weibull curves, as this often has the lowest AIC, however for a project I am working on I am not being given the Weibull curve option, only TH Weibull. Can anyone fill me in on the difference & when it is appropriate to use each version? 

Thank you in advance for your help!

2 ACCEPTED SOLUTIONS

Accepted Solutions
David_Burnham
Super User (Alumni)

Re: Difference between Weibull and TH Weibull & when to use?

I've never needed to use TH Weibull, so I am not an expert but this is my thought/guess.

The Weibull distribution is used to model positive-valued data.  If the data are zero or negative you can't use this distribution.   In certain places in JMP e.g. the Life Distribution platform you will have the option to model TH Weibull distribution instead. This distribution has an additional parameter that has the effect of applying a shift to the distribution.

If you are dealing with Life data, then I'm not sure a negative value makes sense, and if it is because of a preponderance of zero-value data then I would usually take a closer look at distributions designed for zero-inflated distributions (e.g. ZI Weibull).

 

-Dave

View solution in original post

peng_liu
Staff

Re: Difference between Weibull and TH Weibull & when to use?

@David_Burnham has said about all.

In addition to those, TH Weibull and other TH distributions have been better fits than their regular counterparts for some data. But their usefulness usually appear when there is a positive threshold. If it is because that you data have zeros, it is worth understanding why they are zeros.

Input errors, rounding? Those are data issues.

Failure on arrival? Then consider ZI distributions as David said. Or maybe delete them, because those are likely to be a separate issue from the reliability problem, assuming you have a reliability problem.

View solution in original post

5 REPLIES 5
David_Burnham
Super User (Alumni)

Re: Difference between Weibull and TH Weibull & when to use?

I've never needed to use TH Weibull, so I am not an expert but this is my thought/guess.

The Weibull distribution is used to model positive-valued data.  If the data are zero or negative you can't use this distribution.   In certain places in JMP e.g. the Life Distribution platform you will have the option to model TH Weibull distribution instead. This distribution has an additional parameter that has the effect of applying a shift to the distribution.

If you are dealing with Life data, then I'm not sure a negative value makes sense, and if it is because of a preponderance of zero-value data then I would usually take a closer look at distributions designed for zero-inflated distributions (e.g. ZI Weibull).

 

-Dave
zjwright
Level II

Re: Difference between Weibull and TH Weibull & when to use?

Makes perfect sense, thank you!

peng_liu
Staff

Re: Difference between Weibull and TH Weibull & when to use?

@David_Burnham has said about all.

In addition to those, TH Weibull and other TH distributions have been better fits than their regular counterparts for some data. But their usefulness usually appear when there is a positive threshold. If it is because that you data have zeros, it is worth understanding why they are zeros.

Input errors, rounding? Those are data issues.

Failure on arrival? Then consider ZI distributions as David said. Or maybe delete them, because those are likely to be a separate issue from the reliability problem, assuming you have a reliability problem.

zjwright
Level II

Re: Difference between Weibull and TH Weibull & when to use?

I do have zero entries for immediate out of box failures, believe it is still relevant to the overall analysis.

How do I access the ZI Weibull option in JMP, can it be accessed through life distribution? 

Thank you for the insights on this!

peng_liu
Staff

Re: Difference between Weibull and TH Weibull & when to use?

If the setting of your machine's operating system hides scroll bar by default, it might not be obvious to you that it is available. You need to scroll the list a little bit. It is at the bottom of the list. The design was intentional.

peng_liu_0-1698151457587.png

peng_liu_1-1698151508676.png

If you still don't see it, check the preference, it might be unknowingly turned off. And you need to turn them back on, if that is the case.

peng_liu_2-1698151678004.png