Skip to main content
12 events
when toggle format what by license comment
Feb 26, 2017 at 22:03 vote accept Dole
Feb 26, 2017 at 5:39 answer added anuragsodhi timeline score: 2
Feb 26, 2016 at 10:41 comment added Dole @mpktas Indeed, these are the modified assumptions (two different ways of presenting them). The $cov(x_i,e_i)=0$ relaxes the stochasticity assumption just the same. What I want to know is whether the assumption $E(e_i|x_i)$ can relax the autocorrelation assumption as well (as it seems to me it's included in the assumption).
Feb 26, 2016 at 9:38 comment added mpiktas Note that in the classical Gauss-Markov theorem (en.wikipedia.org/wiki/Gauss%E2%80%93Markov_theorem) the $x_i$ are not stochastic. So $E(e_i|x_i)=E(e_i)$. If we move to stochastic $x_i$, then $E(e_i|x_i)=0$ is essential, because it guarantees unbiasedness of the OLS estimate, and the Gauss-Markov theorem states that OLS is BLUE, i.e. it is efficient among unbiased estimators. The autocorrelation in this case is irrelevant, as there is a variant of Gauss-Markov theorem in the general case when covariance matrix of regression disturbances is any positive-definite matrix.
Feb 26, 2016 at 8:30 history edited mpiktas CC BY-SA 3.0
edited title
Feb 26, 2016 at 5:46 history edited Dole CC BY-SA 3.0
added 293 characters in body
Feb 26, 2016 at 5:21 comment added Christoph Hanck Related: stats.stackexchange.com/questions/190703/non-linear-endogeneity/…
Feb 26, 2016 at 5:20 history edited Dole CC BY-SA 3.0
added 4 characters in body; edited title
Feb 26, 2016 at 5:04 history edited Dole CC BY-SA 3.0
added 696 characters in body
Feb 26, 2016 at 4:56 history edited Dole CC BY-SA 3.0
added 696 characters in body
Feb 26, 2016 at 4:41 history edited Dole CC BY-SA 3.0
deleted 40 characters in body; edited title
Feb 26, 2016 at 4:22 history asked Dole CC BY-SA 3.0