cufd22

Testing for Curvature of a 2^2 Factorial Design Analysis.

This m-file is used in experiments where there is uncertain about the assumption of linearity over the region of exploration, and when the experimenter decides to conduct a 2^2 factorial design with a single or several replicates of each factorial run, augmented with some center points. A formal analysis of variance is running in order to see if there is evidence of curvature in the response over the region of exploration. The result can gives indication of some quadratic effects (second-order model) or not (first-order model).

Inputs:
D - matrix data (=[X Y]) (last column must be the Y-dependent variable).
(X-independent variable entry for the 2^2 factorial design).
alpha - significance-value (default = 0.05).

Outputs:
A complete analysis of variance is summarized on a table.