nav[aria-label="Primary Navigation"] { padding: 0; & ul { list-style: none; width: 100%; display: flex; flex-direction: row; justify-content: start; align-items: start; gap: 30px; padding: 0; & li { margin: 0; } & ul li { list-style: none; } } }

How to calculate reliability growth parameter standard errors?

dwaterson

I am looking to know the formula to calculate the standard errors for reliability growth parameters lamda and beta.

Accepted answers

dwaterson

The covariance matrix for the parameters is estimated using the Fisher information matrix. Although, using MS Excel, I cannot get the estimates to match exactly. They look to be the same up to 2 decimal points.

All comments

dwaterson

michael_jmp

This is described in the Statistical Details section of the Reliability Growth documentation:

Statistical Details for the Reliability Growth Platform

dwaterson

Thank you, Michael. I did find the passage to which you are referring. I am actually looking for the math that is used, which is not in the provided link. Is there an article or book you can refer me to?

michael_jmp

I think this paper might help:

Crow, L. H., (1982), “Confidence Interval Procedures for the Weibull Process with Applications to Reliability Growth,” Technometrics, Feb. 1982, 24:1, 67-72.

dwaterson

Thank you, Michael. I will review this article.