l******o
发帖数: 162 | 1 Ran a regression to test the relation between Z and A (after control some
other variables); Z is dependent variable,and A is indep.;
A coefficient is positive and significant;
Then ran another regression to test the relation between Z and B (after
control some other variables); still Z is dep. and A is indep.
B coefficient is negative and significant.
==========================================
Based on the above results, can we safely conclude the relatinship between A
and B??? If we can, the re |
d*******o
发帖数: 493 | 2 This is a multiple regression with 2 predictors and such things happen often
.
You can follow three steps to resolve such a multiple regression by partial
regressions.
1)regress Z on A, by which you have Z-hat expression
2)regress B on A, by which you have B-hat expression
3)regress Z minus Z-hat on B minus B-hat. Plug in 1) and 2) then you have
the same result from the first multiple regression. |
T*******I
发帖数: 5138 | 3 其实，这个问题很简单。在你仅仅完成了Z-A和Z-B的相关性分析后，你是不知道A-
B之间的关系的。你不能简单地根据前两者之间的关系推定第三者关系。在随机世界里
没有确定性，只有非确定性。其实，A-B之间的关系只能有三种可能性：1）正相关、2
）负相关、3）不相关。在你不知道的情况下，你只能用统计的方法去建立和验证，而
不是用某种确定性思维去推定。这就是统计思维与数学思维的差别，或者说是非确定性
系统与确定性系统之间的差别。
【在 l******o 的大作中提到】
: Ran a regression to test the relation between Z and A (after control some
: other variables); Z is dependent variable,and A is indep.;
: A coefficient is positive and significant;
: Then ran another regression to test the relation between Z and B (after
: control some other variables); still Z is dep. and A is indep.
: B coefficient is negative and significant.
: ==========================================
: Based on the above results, can we safely conclude the relatinship between A
: and B??? If we can, the re
|
D******n
发帖数: 2836 | 4 relationship is complicated. no matter in a statistical sense or in romance.
A
【在 l******o 的大作中提到】
: Ran a regression to test the relation between Z and A (after control some
: other variables); Z is dependent variable,and A is indep.;
: A coefficient is positive and significant;
: Then ran another regression to test the relation between Z and B (after
: control some other variables); still Z is dep. and A is indep.
: B coefficient is negative and significant.
: ==========================================
: Based on the above results, can we safely conclude the relatinship between A
: and B??? If we can, the re
|
s*r
发帖数: 2757 | 5 especially there are 3 variables
romance.
【在 D******n 的大作中提到】
: relationship is complicated. no matter in a statistical sense or in romance.
:
: A
|
