还根据所得寿命分布作出了D型V带的P-S-N曲线，并据此推断出极限应力的分布规律可以用威布尔分布或正态分布描述。
Furthermore, the P-S-N curves of D type V belt are plotted and the distribution of limit stress are deduced.
可避免的不一致性可能导致多重模态分布或非正态分布，可能会对应用程序性能造成可度量的影响。
Avoidable inconsistencies may lead to multimodal or non-normal distributions and may have a measurable impact on application performance.
由于威布尔分布或对数正态分布常用来分析寿命分布问题，故优先考虑这两种模型。
Weibull distribution or lognormal distribution is often used to analyze lifetime problem, so the two models are preferentially considered in tis paper.
归一化以后的数据服从同一正态分布，可以减少或消除不等精度的干扰，突出图象中的有用信息。
The normalized data will exhibit the same normal distribution, reduce or eliminate the interference of unequal precision, and highlight the useful information in images.
抗差估计等价权函数一般由正态分布统计量构造，其临界值（或称准则）一般由实际经验确定。
The equivalent weight function in robust estimation is usually constructed by the statistics of normal distribution. The critical values are often fixed by experience.
线性回归模型的误差项不服从正态分布或存在多个离群点时，可以将残差秩次的某些函数作为权重引入估计模型来减少离群点的不良影响。
When multiple outliers occur in linear regression model or the distribution of residuals is not normal, we can use residuals rank as weight function to get some resist estimator.
在冷形变量大于或等于70 %时，其再结晶晶粒尺寸分布符合对数正态分布。
If the cold deformation rate is higher than 70 %, the recrystallized grain size distribution agrees with lognormal distribution.
结果正态性检验和频率分布曲线分析显示，所获数据符合或基本符合正态分布。
A normal distribution of our data was shown using the normality test and distribution curve.
传统回归分析只适用于来自正态分布的完全数据，对于截尾数据或威布尔分布数据则无能为力，目前工程上只能采用成组试验方法，结果导致试验量很大。
The traditional regression analysis is only suitable to complete data from normal distribution. In engineering, censored data is analyzed by group test method that requires a large number of samples.
传统回归分析只适用于来自正态分布的完全数据，对于截尾数据或威布尔分布数据则无能为力，目前工程上只能采用成组试验方法，结果导致试验量很大。
The traditional regression analysis is only suitable to complete data from normal distribution. In engineering, censored data is analyzed by group test method that requires a large number of samples.
应用推荐