One of the most important reliability parameters is the mean time to failure (MTTF). It is widely accepted that the MTTF is equal to the mean time of life ET. This article shows that this is not necessarily true. Although for the most commonly used statistical distributions (such as exponential, Gaussian, chi-square, Fisher-Tippett distributions) the values of MTTF and ET are equal, this is not the case for the log-normal distribution. Similarity, some less commonly used distributions (such as

more »

... reit-Wigner distribution) may also require calculation adjustments resulting from MTTF ≠ ET. Ignoring this discrepancy, an erroneous MTTF value can be obtained.