D-Optimal and D-Efficient Equivalent-Estimation Second-Order Split-Plot Designs

• Autores: Harrison Macharia, Peter Goos
• Localización: Journal of quality technology: A quarterly journal of methods applications and related topics, ISSN 0022-4065, Vol. 42, Nº. 4, 2010, págs. 358-372
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • Many industrial experiments use split-plot designs as a cost-efficient method of reducing the number of independent settings of hard-to-change factors. Generally, model estimation for split-plot designs requires the use of generalized least squares, but in some cases, ordinary least squares estimates work as well. These equivalent-estimation designs do not require estimation of the variance components in the split-plot model. Alternatively, D-optimal designs provide efficient estimation of the fixed effects of the statistical model. The relationship between these designs for a second-order response surface model is explored, and an algorithm is proposed for generating D-efficient equivalent-estimation split-plot designs.