| Summary: | 碩士 === 淡江大學 === 統計學系碩士班 === 93 === The quality characteristics of some products are not easy to check, in order to reduce the cost and time effort of inspection, a modified screening procedure which selects items whose performance variable is within a one-sided specification and two-sided specification based on observing the correlated screening variables according to the individual misclassification error(IME) is proposed. The criterion of average outgoing quality(AOQ) and total inspection cost(TIC) are still used to search for the optimal allocation.
Unlike the original sequential screening procedure, the modified procedure does not need to decide the weights of every screening variable at the beginning stage. Therefore, the modified procedure is only weighting once instead of weighting twice. The generalized formulas for the single stage(SSP), double stage(DSP) and triple stage(TSP) sequential screening procedures are derived by the use of multivariate normal distribution and matrix operation. The Monte Carlo simulation method to simulate the desired probability values for any finite stage of sequential screening procedure, especially for more than three stages due to the complexity of obtaining exact results.
Several example are used to demonstrate the single stage(SSP), double stage(DSP), triple stage(TSP), quadruple stage(QSP) and the fifth stage(FSP) by the computer program via Fortran IMSL to search for the best allocation. The results show that the modified sequential screening procedure performs similar to the original one and some are even better. Therefore, the modified sequential screening procedure is recommended for practical use.
|
|---|
