w********u 发帖数: 328 | 1 three curves:
1 & 2 has the coefficient of determination, R square, =0.7
1 & 3 has the coefficient of determination, R square, =0.8
Actually, there is no correlation between 1 & 2, for example, sunshine and
the light, they both light up the room but there is no actual relationship
between them. But 1 & 3 indeed has statistical correlation.
Now, how to prove that 1&3 has statistical correlation but 1&2 does not?
Any idea is welcome, especially with some particular formula.
Thank you.! | w********u 发帖数: 328 | 2 there is no exact data but only three curves, sorry. | g******c 发帖数: 116 | 3 取样的问题了。做个SIMULATION就知道,X,Y没有关联,但是就是有可能某组样本,X
,Y之间的相关系数会比较高还有统计意义。你拿到这数据算出R,与其指望某种统计方
法能证明它们之间其实没有关联,还不如重新取样做个VALIDATION来得实际可信。 | w********u 发帖数: 328 | 4 thank you for your quick response.
would you please explain more clearly? how to do the simulation and how to
do the validation? thank you so much!! | w********u 发帖数: 328 | 5 thank you for your quick response.
would you please explain more clearly? how to do the simulation and how to
do the validation? thank you so much!! | w********u 发帖数: 328 | 6 thank you for your quick response.
would you please explain more clearly? how to do the simulation and how to
do the validation? thank you so much!! | w********u 发帖数: 328 | | D******n 发帖数: 2836 | 8 u misunderstand correlation.
if R=0.7, it does have a "correlation", it does have a relationship ,statist
ically.
I guess u probably want to say there is no causality relationship between 1
& 2.
but thats not something that can be checked by just looking at ur data. u ne
ed to conduct some control experiments...
【在 w********u 的大作中提到】 : three curves: : 1 & 2 has the coefficient of determination, R square, =0.7 : 1 & 3 has the coefficient of determination, R square, =0.8 : Actually, there is no correlation between 1 & 2, for example, sunshine and : the light, they both light up the room but there is no actual relationship : between them. But 1 & 3 indeed has statistical correlation. : Now, how to prove that 1&3 has statistical correlation but 1&2 does not? : Any idea is welcome, especially with some particular formula. : Thank you.!
|
| w********u 发帖数: 328 | 9 would you please say a little bit more about how to conduct some control
experiments? thank you! | D*******a 发帖数: 207 | 10
Between sunshine and the light, there is actual relationship. When sunshine
comes, you turn off the light. When night comes, you turn the light on. So
there is not only relationship, there is causal relationship.
【在 w********u 的大作中提到】 : three curves: : 1 & 2 has the coefficient of determination, R square, =0.7 : 1 & 3 has the coefficient of determination, R square, =0.8 : Actually, there is no correlation between 1 & 2, for example, sunshine and : the light, they both light up the room but there is no actual relationship : between them. But 1 & 3 indeed has statistical correlation. : Now, how to prove that 1&3 has statistical correlation but 1&2 does not? : Any idea is welcome, especially with some particular formula. : Thank you.!
| w********u 发帖数: 328 | 11 i still have no idea..ding~~ | b*****n 发帖数: 685 | 12 First of all,
correlation != linear correlation
【在 w********u 的大作中提到】 : three curves: : 1 & 2 has the coefficient of determination, R square, =0.7 : 1 & 3 has the coefficient of determination, R square, =0.8 : Actually, there is no correlation between 1 & 2, for example, sunshine and : the light, they both light up the room but there is no actual relationship : between them. But 1 & 3 indeed has statistical correlation. : Now, how to prove that 1&3 has statistical correlation but 1&2 does not? : Any idea is welcome, especially with some particular formula. : Thank you.!
| l***a 发帖数: 12410 | 13 by default?
【在 b*****n 的大作中提到】 : First of all, : correlation != linear correlation
| c*******o 发帖数: 8869 | 14 GOOGLE correlation vs causation....
【在 w********u 的大作中提到】 : three curves: : 1 & 2 has the coefficient of determination, R square, =0.7 : 1 & 3 has the coefficient of determination, R square, =0.8 : Actually, there is no correlation between 1 & 2, for example, sunshine and : the light, they both light up the room but there is no actual relationship : between them. But 1 & 3 indeed has statistical correlation. : Now, how to prove that 1&3 has statistical correlation but 1&2 does not? : Any idea is welcome, especially with some particular formula. : Thank you.!
|
|