Generalized aberration (GA) is one of the most frequently used criteria to quantify the suitability of an orthogonal array (OA) to be used as an experimental design. The two main motivations for GA are that it quantifies bias in a main-effects only model and that it is a good surrogate for estimation efficiencies of models with all the main effects and some two-factor interaction components. We demonstrate that these motivations are not appropriate for three-level OAs of strength 3 and we propose a direct classification with other criteria instead. To illustrate, we classified complete series of three-level strength-3 OAs with 27, 54 and 81 runs using the GA criterion, the rank of the matrix with two-factor interaction contrasts, the estimation efficiency of two-factor interactions, the projection estimation capacity, and a new model robustness criterion. For all of the series, we provide a list of admissible designs according to these criteria.

, , , ,
doi.org/10.1016/j.jspi.2011.09.014, hdl.handle.net/1765/37856
Journal of Statistical Planning and Inference
Erasmus Research Institute of Management

Sartono, B., Goos, P., & Schoen, E. (2012). Classification of three-level strength-3 arrays. Journal of Statistical Planning and Inference, 142(4), 794–809. doi:10.1016/j.jspi.2011.09.014