How to model the error propagation for non-normally distributed data? 如何建立非正态分布的数据的误差传播模型等等。
As the variables included continuous variables and classification variables, parameter and non-parameter method were both used to describe the samples. The comparative test and analysis was done by T-test and ANOVA, while the non-normally distributed continuous data were compared using Chi-square test. 因为变量有连续型变量和分类变量,样本的描述采用参数和非参方法,均数比较用T检验和方差分析,非正态分布且方差不齐的连续性资料的比较采用χ2检验。
That is, when population of scores has small size, and non-normally distributed, the approach may cause bias to some extent. 最后,本文分析了正态上侧百分位(NUP)排位的运用局限性,即当分数总体体量较小,且不服从正态分布时,该方法可能产生一定的偏差。