Fixed effects balanced strip-plot designs under random blocks and non uniform dependence: robustness properties

Standard practice with factorial designs or their fractions give rise to well-known problems. The assumed independence among error terms, linked to constrained randomization of runs, may be no longer accepted, due to grouping or partial grouping of experimental units for economical reasons. This paper assumes a very general dependence structure within random components of error terms and analyses a robust behaviour of standard testing procedures on effects of two--factors strip--plot design.