Through the use of a “predictor-corrector” equation an experimenter may quickly determine the least squares estimates of all the coefficients in a polynomial model after the conclusion of each run, given that an initial set of orthogonal estimates of the coefficients is available. The analysis of variance may similarly be constructed at the conclusion of each added run. The predictor-corrector equation is subject to mild restrictions which are fully met in the usual application of the 2kand 2k–pfactorial designs. Adaptation of the predictor-corrector equation to the case of complimentary blocks of two runs each is described. Examples are given.