Subscribe Bookmark RSS Feed

Reliability calculation with only failure

tahir

Community Trekker

Joined:

Jun 23, 2011

Hi,


I have the following test data

Nr of hours                          test results

2400                                    not failed, test stopped

2400                                    not failed, test stopped

2400                                    not failed, test stopped

2600                                    failed

I tried to use the 'life distribution' but i dont get any result as i have one failure so i want to know how to to calculate reliability at 750 hours?


BR,


/Tahir

1 REPLY
markbailey

Staff

Joined:

Jun 23, 2011

With only one observed failure, you cannot estimate two model parameters (such as alpha and beta for Weibull). You can perform a WeiBayes analysis if you only need to estimate one of these parameters. Select Weibull as the distribution model at the top in Compare Distributions. Then click the red triangle next to the Parametric Estimate - Weibull for the model results and select Fix Parameter. A new section opens where you can enter the known value and then estimate the other.

Note that you can estimate the independent parameter but you cannot evaluate goodness of fit with only a single observation.

Learn it once, use it forever!