We suggest in this paper a method for assessing the validity of the assumption of normal distribution of random errors in a two-factor split-plot design. The vector observation is transformed into residual vector and then the residual vector is tranformed into an adjusted residual vector from the least squares method by linear transformation. Since the components of the adjusted residual vector satisfy the conditions for a simple sample, therefore the appropriately chosen adjusted residual vector can be used for testing of normality.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.