We propose a method of applying the maximum likelyhood test to the estimation of experimental inaccuracies. This method takes into consideration the fact that only the deviations between measured values and their model-aided estimations can be known. A discussion concerning the possible application of the method and the confidence we place upon it is illustrated by an empirical study of result distribution.
No takes yet. Share an insight, caveat, or question.
Péneloux et al. (1976) studied this question.