A common problem of high reliability computing is, on one hand, the magnitude of total testing time required,
particularly in the case of high reliability components and, on the other hand, the number of devices under test. In
both cases, the objective is to minimize the costs involved in testing without reducing the quality of the data
obtained. One solution is based on accelerated life testing techniques which permit to decrease testing time. Another
solution is to incorporate prior beliefs, engineering experience, or previous data into the testing framework. It is in
this spirit that the use of a Bayesian approach can, in many cases, significantly reduce the amount of devices required.
The accelerated life testing (ALT) of electronic components (including the semiconductor devices) under severer
than operating conditions involving high temperature, humidity, voltage, a.o. is commonly used to reduce test time
and cost. The main problem is to estimate accelerated life model parameters allowing to define the reliability
function under operating conditions from only accelerated life data. A difficulty of using the ALT, during design
stage, is due to the small sample size to test. In this context, the Bayesian approach can be used to incorporate into
the estimation process all available knowledge on accelerated life model (baseline failure rate, activation energy, a.o).
This paper presents the study of Exponential-Arrhenius model by an evaluation of parameters using maximum
likelihood and Bayesian methods. A Monte Carlo simulation has been performed to examine the asymptotic
behavior of these different estimators.