随机效应回归后，还应该有一个xttset0和xttset1检验。

xttset1进行检验，结果中p值全为0，一方面肯定了随机效应模型的有效，同时也说明存在序列相关——这个理解是对的吧？
原假设：
1) LM test for random effects, assuming no serialcorrelation;

2) Adjusted LM test for random effects, which works evenunder serial correlation;

3) One-sided version of the LM test for random effects;

4) One-sided version of the adjusted LM test for randomeffects;

5) LM joint test for random effects and serial correlation;

6) LM test for first-order serial correlation, assuming norandom effects;

7) Adjusted test for first-order serial correlation, whichworks even under random effects.

如果存在自相关，是否需要进一步用xtgls修正？

修正命令中ar项等数字需要如何决定呢？


另外STATA13的xttset1检验的结果似乎是“简洁”版了.....只有四个P值了.....