V. Reliability Testing
C. Product Testing
Describe the purpose, advantages, and limitations of each of the following types of tests, and use common models to develop test plans, evaluate risks, and interpret test results.
1. Qualification/demonstration testing (sequential tests, fixed -length tests) (Evaluate)
In some cases we have to be ecumenical with sample size and the testing is pass/fail in nature. Then success testing is the way to go. Plus, it is a great tool to estimate sample sizes for testing.
Additional References
Sample Size – success testing (article)
Extended Bogey Testing (article)
Quick Quiz
1-134. A unit is designed to achieve 96% reliability at a 90% confidence level. Which of the following is the minimum sample testing results that reflects the requirements?
(A) 200 units to be tested with one failure reported
(B) 100 units to be tested with one failure reported
(C) 50 units to be tested with no failures reported
(D) 25 units to be tested with no failures reported
(A) 100 units to be tested with one failure reported
A quick way to solve this one is with the Beta Table based on the work of Locks. The Beta table entry is with the number of samples, n, and the number of successes, r. So, for (A) with n = 200 and r = 199 (there is one failure) and under the column with Y = 0.90 for the 90% lower confidence bound, we find a value of 0.981 or 98.1%.
Given we’re looking for the minimum testing results – or fewest samples let’s check (B). Here n = 100 and r = 99 with 90% confidence we find 96.2%, which just barely meets our requirement and uses 100 fewer samples.
For (C) we find 95.6% and for (D) find 91.5% both below the target.
Leave a Reply