找回密码
 注册
搜索
查看: 669|回复: 4

[灌水] 统计分析

[复制链接]
发表于 2010-5-2 09:29 AM | 显示全部楼层 |阅读模式


本帖最后由 zhufufu 于 2010-5-2 10:31 编辑

1,样本大小
2,相关性, 相关系数
3,Univariate and multivariate one-factor analyses of variance

这几点没弄明白来算probability就是个joke. 用5个样本来算出80%的可能, 相关性是扯蛋。忽视了变量间的关系来说相关是无知, 例如黄金和指数有正副相关,但原因是受其他因素的影响,断不可仅仅考虑两者
发表于 2010-5-2 10:06 AM | 显示全部楼层
Thanks, can you give an example of a correct analysis, at least you think it is correct.

Thanks a lot!
回复 鲜花 鸡蛋

使用道具 举报

发表于 2010-5-2 10:20 AM | 显示全部楼层
TA is not science.
回复 鲜花 鸡蛋

使用道具 举报

发表于 2010-5-2 04:17 PM | 显示全部楼层
回复 1# zhufufu


    Agree totally. but sometimes it's hard to judge whether the sample is big enough or two stocks are related or not. Samples in different market conditions may be more important than actual sample size. As to related or not, in some markets, oil is related to airline sometimes they are not. How to solve these problems?  Hopefully big cow in this forum can shed some light
回复 鲜花 鸡蛋

使用道具 举报

发表于 2010-5-2 05:35 PM | 显示全部楼层
回复 1# zhufufu


   
回复 鲜花 鸡蛋

使用道具 举报

您需要登录后才可以回帖 登录 | 注册

本版积分规则

手机版|小黑屋|www.hutong9.net

GMT-5, 2025-6-24 05:24 AM , Processed in 0.073716 second(s), 15 queries .

Powered by Discuz! X3.5

© 2001-2024 Discuz! Team.

快速回复 返回顶部 返回列表