Abstract
Methods are presented for analyzing data from interlaboratory experiments, in which the main purpose is to obtain a consensus value from the overall experiment. The consensus value estimates a parameter of a certain substance or material. Statistical analysis involves computation of appropriate weights, which are derived from estimates of the within-laboratory variances and of the between-laboratory variance. Different procedures are compared via Monte Carlo simulation. The “average of squared residuals” (ASR) method is shown to be preferable in most cases.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have