这个论断应该是有前提的吧。
经查，发现楼主有点断章取义：Bernard, A., J. Jensen, 2004, Why some firms export, Review of Economics and Statistics, 86 (2): 561-569. 的原文如下：
There are several potential estimation strategies for this dynamic binary
choice framework with unobserved heterogeneity, including probit with random
or fixed effects, conditional logit, and linear probability models with
fixed or random effects. A starting point in choosing among the available
specifications is the decision whether unobserved plant heterogeneity is better
modelled as fixed or random effects. The use of random effects requires
that the plant effects be uncorrelated with the regressors. Most fixed effects
models, on the other hand, produce biased and inconsistent parameter
estimates, especially for the coefficient on the lagged dependent variable.
他们谈论的是动态 logit 或 probit 模型的估计方法，FE当然是有偏的。
扫码加好友，拉您进群
全部版块
我的主页
收藏
下次再认真些。。。
