作者pigwitch (witch)
看板Statistics
标题[问题] 跑sas时出现的问题
时间Sat Jun 28 21:20:27 2008
我在跑二阶段最小平方法(2sls)时，语法如下：
proc syslin data=K.HSIN 2sls ;
endogenous csr1 q_ave ;
instruments rd_ave csr2 csr3 csr4 size D1 D2 D3 D4 D5 D7 D8 ;
reg1: model csr1=rd_ave q_ave size D1 D2 D3 D4 D5 D7 D8 ;
reg2: model q_ave=csr1 csr2 csr3 csr4 rd_ave size D1 D2 D3 D4 D5 D7 D8;
RUN ;
reg1可以跑得出来
但reg2跑出来的结果显示
WARNING: The model is not of full rank. Least Squares solutions for the
parameters are not unique. Certain statistics will be misleading. A reported
degree of freedom of 0 or B means the estimate is biased.
The following parameters have been set to zero. These variables are a
linear combination of other variables as shown.
CSR1 = -0.0381*Intercept +0.2148* CSR2 +0.2200*CSR3 +0.2593*CSR4
+0.004380*SIZE -0.002569*D1 -0.0122*D2 -0.004962*D3 -0.0505*D4
+0.0819*D5 +0.007241*D7 -0.0219*D8
请问是那边出了问题呢？谢谢
--
※ 发信站: 批踢踢实业坊(ptt.cc)
◆ From: 140.119.149.150
1F：推 tew:可能是虚拟变数的问题 06/28 21:34
2F：推 bugle:The model is not of full rank. 06/28 21:40