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: 
Try the Materials Informatics Toolkit, which is designed to easily handle SMILES data. This and other helpful add-ins are available in the JMP® Marketplace
Choose Language Hide Translation Bar
zjuv007
zjuv007
Level III

Sample Size for Weibull Distribution - Reliability

Created: May 16, 2020 10:03 PM  |  Last Modified: May 16, 2020 7:07 PM (2324 views)

Hello,

I have prior testing of n=22 samples, with 2 failure modes/locations. The Y of interest is lbf and ALL samples are tested to failure (no censoring). I want to use this data to determine the necessary sample size I must use for the same test to ensure that at least 95% of the selected population covered at a 95% lower confidence bound (Lower Spec limit).

 

The aggregate data fits a weibull distribution with a P-value of 0.175, mean of 12.716, std dev = 0.763, shape = 25.773, and scale =13.015 for the Weibull fit.

 

How can I determine the minimum sample size I will need (based on prior testing knowledge from above) to ensure 95/95 for a lower spec limit of 5.2 lbf?

0 Kudos
1 REPLY 1
Mark_Bailey
Staff Mark_Bailey
Staff

Re: Sample Size for Weibull Distribution - Reliability

May 17, 2020 07:45 AM (2294 views)  |  Posted in reply to message from zjuv007 05-16-2020

I am not sure if this tool will do what you want, but see the Reliability Demonstration calculator under DOE > Design Diagnostics > Sample Size and Power.

 

See Help > JMP Documentation Library > Design of Experiments Guide > Reliability Demonstration Calculator section for more information and a worked example.

0 Kudos