作者Eviette (快点开学吧)
看板Statistics
标题[问题] Robustness 稳健性
时间Wed Jan 30 03:27:40 2008
想请问一下大家robustness是什麽东西呢
我在看关於Monday effect的论文
看到了一篇关於这个东西的
(finds that sample size and/or
error term adjustments render U.S. day-of-the-week effects statistically
insignificant. In
contrast, day-of-the-week effects in seven European countries and in Canada
and Hong
Kong are robust to individual sample size or error term adjustments, and
day-of-the-week
effects in five European countries survive the simultaneous imposition of
both types of
adjustments.)
因为robust这个东西搞不清楚 搞的我整篇论文不知道他在干麻
查了课本网路还是找不到关於这个东西的解释
所以想请问大家
感谢!!!!
--
※ 发信站: 批踢踢实业坊(ptt.cc)
◆ From: 129.234.226.20
1F：推 jack317:不会因为违反基本假设或误差而影响结果 01/30 10:02
2F：→ Eviette:谢谢你!可以再请问一下如果regression errors 不普通(not 01/30 21:02
3F：→ Eviette:normal)且heteroskedastic ,然後autocorrelation存在,是否 01/30 21:03
4F：→ Eviette:就表示有robustness呢?谢谢~ 01/30 21:04
5F：推 ShibaInu:not normal...意思应该是非常态分配吧! 01/30 21:33
6F：→ Eviette:对吼...哈哈..那请问上面那样是否就表示有稳健性呢? 01/30 21:48