Experimentally, the best design gives estimates of the desired effects and contrasts with maximum precision. Efficiency as a discriminating factor enables comparison of designs. The goal of Response Surface Methodolog...Experimentally, the best design gives estimates of the desired effects and contrasts with maximum precision. Efficiency as a discriminating factor enables comparison of designs. The goal of Response Surface Methodology (RSM) is the determination of the best settings of the in-put variables for a maximum (or a minimum) response within a region of interest, R. This calls for fitting a model that adequately represents the mean response since such a model, is then used to locate the optimum. D-, A-, E- and T-Optimal designs of a rotatable design of degree two in four dimensions constructed using balanced incomplete block designs (BIBD) when the number of replications is less than three times the number of pairs of treatments occur together in the design and their relative efficiencies to general designs are presented. D-optimal design had 88 runs after replicating the factorial part twice and the axial part thrice with an optimal variance of 0.6965612 giving an efficiency of 97.7% while for A- and T-optimal designs they are formed with 112 runs each obtained by replicating the factorial part two times and axial part six times. Their optimal variances are 0.05798174 and 1.29828 respectively, with efficiency of 71.8% for A-optimal and 87.5% for T-optimal design. E-optimal design was found to be the most efficient design with an only 32 runs comprising only of the factorial part and with an optimal variance of 0.4182000, attaining an efficiency of approximately 1%. This study proposes the adoption of the E-optimal design in estimating the parameters of a rotatable second-order degree model constructed using BIBD for less costs and time saving.展开更多
文摘Experimentally, the best design gives estimates of the desired effects and contrasts with maximum precision. Efficiency as a discriminating factor enables comparison of designs. The goal of Response Surface Methodology (RSM) is the determination of the best settings of the in-put variables for a maximum (or a minimum) response within a region of interest, R. This calls for fitting a model that adequately represents the mean response since such a model, is then used to locate the optimum. D-, A-, E- and T-Optimal designs of a rotatable design of degree two in four dimensions constructed using balanced incomplete block designs (BIBD) when the number of replications is less than three times the number of pairs of treatments occur together in the design and their relative efficiencies to general designs are presented. D-optimal design had 88 runs after replicating the factorial part twice and the axial part thrice with an optimal variance of 0.6965612 giving an efficiency of 97.7% while for A- and T-optimal designs they are formed with 112 runs each obtained by replicating the factorial part two times and axial part six times. Their optimal variances are 0.05798174 and 1.29828 respectively, with efficiency of 71.8% for A-optimal and 87.5% for T-optimal design. E-optimal design was found to be the most efficient design with an only 32 runs comprising only of the factorial part and with an optimal variance of 0.4182000, attaining an efficiency of approximately 1%. This study proposes the adoption of the E-optimal design in estimating the parameters of a rotatable second-order degree model constructed using BIBD for less costs and time saving.
