Specifically, we have got τ cofficient table in the condition of n equals to 20 in this paper, so that the practical extend of independence test can be enlarged.
由此将数理统计中常用的肯达尔 τ系数临界值表从 n=1 0扩展到 n为任意自然数的情形 ,并特别给出了 n=2 0情形下的 τ系数临界值表 ,扩大了 τ系数进行独立性检验的实用范
The EViews software is used for statistical analysis of the data of registered cases of bronchitis and the average temperature in Haixizhou Region,Qinghai Province,at the same time,the independence tests and forecasts for the residue series are carried out to validate the established models.
研究通过EViews软件对海西州地区支气管炎发病病例和平均气温监测登记资料的统计分析,并利用原数据建立ARCH、TARCH-M、EGARCH和EGARCH-M模型,通过对模型中的残差序列进行独立性检验和预测,确定所建立的ARCH、TARCH-M、EGARCH和EGARCH-M模型的合理性,并从中选出了最优模型TARCH(1,1)-M。
In this paper, we introduce the algorithm about constructing Bayesian network classifier for remote sensing data based on the conditional mutual information test of different bands.
本文介绍了利用贝叶斯网络的变量间独立性测试原理,构建了输入两个时相多波段遥感信息的有向无环结构,利用训练后的网络进行两个时相多波段遥感变化信息的检测,取得了较好的效果。