摘要
在进行抽样试验时,采用传统的假设检验方法进行决策所需的样本容量通常是比较大的,而充分利用在进行抽样试验之前所能获得的关于总体分布未知参数的验前信息,在Bayes理论的基础上,采用序贯验后加权检验方法可以有效地减小试验所需的样本容量。对正态分布总体的均值与方差参数均未知时的联合序贯验后加权检验方法进行了深入分析,给出了在抽样试验之前确定假设检验问题所需样本容量和决策阈值的计算方法,并结合雷达探测距离的以往实际试验数据和结果进行了对比分析,验证了该方法在减小样本容量及提高试验效费比方面的有效性。
In the test using classic probability and statistical decision theory, the sample size is relatively large. On the basis of the Bayesian theory and by making use of the prior information of the unknown parameters effectively, the sample size can be reduced greatly by the sequential posterior odd test (SPOT) method. The SPOT method of the unknown parameters in the normal distribution is discussed in detail, and the sample size and the threshold value which are needed before a test are worked out. By analyzing the results of radar detection range test, it is proved that the SPOT method is effective to reduce the sample size and improve the test efficiency.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2004年第6期744-746,805,共4页
Systems Engineering and Electronics
关键词
贝叶斯理论
正态分布
序贯
检验
样本容量
Bayesian theory
normal distribution
sequential
test
sample size
