各位兄弟姐妹们,考虑的是利率波动对投资的影响,加入时间和行业固定效应,但是结果却把利率波动删了,提示说和固定效应存在共线性,这是咋回事呀<br><br>
下面是运行结果<br>
xtset id year
Panel variable: id (unbalanced)<br>
Time variable: year, 2009 to 2018, but with gaps<br>
Delta: 1 unit
. reghdfe Inveffi RateV $controls,abs(Ind year)<br>
note: RateV is probably collinear with the fixed effects (all partialled-out values are close to zero; tol = 1.0e-<br>
&gt; 09)<br>
(MWFE estimator converged in 5 iterations)<br>
note: RateV omitted because of collinearity
HDFE Linear regression Number of obs = 18,459<br>
Absorbing 2 HDFE groups F( 6, 18368) = 28.60<br>
Prob &gt; F = 0.0000<br>
R-squared = 0.0453<br>
Adj R-squared = 0.0406<br>
Within R-sq. = 0.0093<br>
Root MSE = 0.0557
------------------------------------------------------------------------------<br>
Inveffi | Coefficient Std. err. t P&gt;|t| [95% conf. interval]<br>
-------------+----------------------------------------------------------------<br>
RateV | 0 (omitted)<br>
Age | -.00046 .000087 -5.28 0.000 -.0006306 -.0002894<br>
Size | -.0010301 .0003906 -2.64 0.008 -.0017958 -.0002645<br>
TBQ | -.000227 .0001596 -1.42 0.155 -.0005399 .000086<br>
ROA | .0160552 .0031219 5.14 0.000 .009936 .0221744<br>
DAR | -.0006601 .0013712 -0.48 0.630 -.0033477 .0020275<br>
ATO | -.0081886 .0008245 -9.93 0.000 -.0098046 -.0065725<br>
_cons | .0702545 .0039283 17.88 0.000 .0625547 .0779544<br>
------------------------------------------------------------------------------
Absorbed degrees of freedom:<br>
-----------------------------------------------------+<br>
Absorbed FE | Categories - Redundant = Num. Coefs |<br>
-------------+---------------------------------------|<br>
Ind | 76 0 76 |<br>
year | 10 1 9 |<br>
-----------------------------------------------------+
.