论文部分内容阅读
从（0,1）型的完备随机因子群与预报量之间的等概率相关出发,我们导出了偶然性相关率概率定理,即:任一含有n个（0,1）型元素的预报量序列,它与含有n个（0,1）型元素的完备随机因子群之间具有偶然性相关率m/n二的概率P_w（m/n）=C_n~m/2~n。类似于“偶然性单相关的识别与过滤”一文中的做法,引进统计量 并用其对预报因子进行显著性检验。文中给出了实际应用时应当执行的步骤。 然后本文将变量型从（0,1）型推广到K级划分的情况,于是得到K级偶然相关率概率定理,即:任一含有n个k级划分元素的预报量序列,它与包含n个k级划分元素的完备随机因子群之间具有的偶然性相关率m/n的概率P_w（m/n,k）=（k-1）~（n-m）C_n~m/K~n。
From the complete equality of (0,1) -type random equivariant groups and the predictive predictions, we derive the probabilistic theorem of chance correlation rate, that is, any forecasting sequence containing n (0,1) -type elements , And its probability P_w (m / n) = C_n ~ m / 2 ~ n, which has the chance correlation rate m / n between itself and the complete random factor group containing n (0,1) type elements. Similar to the practice in the article “Identification and Filtering of Incidental Single Correlations,” statistics were introduced and used to test the significance of the predictor. The article gives the practical steps should be implemented. Then, we generalize the variable type from (0, 1) to the K-level partition, and then we get the K-level contingency probability probability theorem, that is, any forecasting sequence with n k-level partitioning elements, The probability of accidental correlation m / n between perfect random factor groups of k-level classifying elements P_w (m / n, k) = (k-1) ~ (nm) C_n ~ m / K ~ n.