论文部分内容阅读
采用Monte Carlo模拟仿真方法,分析了GJB/Z 377A-1994《感度试验用数理统计方法》中升降法标准差计算方法—传统法和修正法的估值精度,并研究了传统法和修正法相结合的方法,以提高标准差的估值精度。结果表明:任意样本量下传统法的估值精度优于修正法的估值精度;当样本量在26～59之间时,结合法的标准差估值精度最高,其他样本量下结合法与传统法具有相同的估值精度,并得到了结合法中最优a值。
Monte Carlo simulation method was used to analyze the accuracy of the standard deviation of lifting method in GJB / Z 377A-1994 “Mathematical Statistics Method of Sensitivity Test” - the accuracy of the traditional method and the correction method, and the combination of the traditional method and the correction method Method to improve the standard deviation of the valuation accuracy. The results show that the accuracy of the traditional method is better than that of the revised method for any sample size. When the sample size is between 26 and 59, the precision of the standard deviation of the binding method is the highest. The traditional method has the same evaluation precision, and obtains the optimal a value in the combination method.