栖息谷-管理人的网上家园

[求助]explain it to me ??

[复制链接] 4
回复
1016
查看
打印 上一主题 下一主题
楼主
跳转到指定楼层
分享到:
发表于 2004-4-1 19:46:26 | 只看该作者 回帖奖励 |倒序浏览 |阅读模式

MINITAB操作

Stat > Basic Statistics > 2 Variances

Stat > ANOVA > Test for Equal Variances

我的问题是,这两种方法都是检验两个样本的方差是否相等,或者说是方差的置信区间的范围的操作,它们有什么不同吗?/分别用在什么场合下呢??

沙发
发表于 2004-4-2 16:59:24 | 只看该作者
Stat > Basic Statistics > 2 Variances

You can use the variance test to perform hypothesis tests for equality, or homogeneity, of variance among two populations using an F-test and Levene’s test. Many statistical procedures, including the two sample t-procedures, assume that the two samples are from populations with equal variance. The variance test procedure will test the validity of this assumption.

Stat > ANOVA > Test for Equal Variances

Use variance test to perform hypothesis tests for equality or homogeneity of variance using Bartlett’s and Levene’s tests. An F Test replaces Bartlett’s test when you have just two levels.

Many statistical procedures, including analysis of variance, assume that although different samples may come from populations with different means, they have the same variance. The effect of unequal variances upon inferences depends in part upon whether your model includes fixed or random effects, disparities in sample sizes, and the choice of multiple comparison procedure. The ANOVA F-test is only slightly affected by inequality of variance if the model contains fixed factors only and has equal or nearly equal sample sizes. F-tests involving random effects may be substantially affected, however [18]. Use the variance test procedure to test the validity of the equal variance assumption.

板凳
 楼主| 发表于 2004-4-2 21:37:06 | 只看该作者
谢谢回复,但是我就是因为看不懂英文的意思,所以才问的呀,可以用汉语解释吗??
4
 楼主| 发表于 2004-4-4 17:58:24 | 只看该作者
还是没有答案吗??
5
 楼主| 发表于 2004-4-6 20:47:39 | 只看该作者
答案呀,HELP!!

使用高级回帖 (可批量传图、插入视频等)快速回复

您需要登录后才可以回帖 登录 | 加入

本版积分规则   Ctrl + Enter 快速发布  

发帖时请遵守我国法律,网站会将有关你发帖内容、时间以及发帖IP地址等记录保留,只要接到合法请求,即会将信息提供给有关政府机构。
快速回复 返回顶部 返回列表