6
votes
Repeated measurements on the right hand side of the regression equation
The cluster sandwich covariance estimator works quite well in situations like this. As a test, you can just duplicate each row of data in a standard study and you’ll find the cluster covariance ...
- 98.4k
4
votes
Accepted
Repeated measurements on the right hand side of the regression equation
What about the following joint-modeling perspective:
There is a latent quantity (you might think of it as the true underlying health state of the patient). Let's call that $x_i$ for subject $i$.
The ...
- 35.2k
2
votes
Accepted
Regression lines adjusted for region vs region-specific regression lines
The "region-adjusted slopes" are almost as useless here as the unadjusted slope:
The region-adjusted slope comes from estimating separate regression of damage on elevation for the Southern ...
- 101k
2
votes
in ensemble the resulting model is nonlinear even if the base model is linear?
It depends crucially on how your "ensembling" works.
For instance, suppose you have two linear models, $y=a_1+b_1x$ and $y=a_2+b_2x$, and the ensembling picks one of the two models depending ...
- 131k
1
vote
Accepted
$\text{E}[\mathbf{\varepsilon}\mathbf{\varepsilon}'\mid\mathbf{X}]=\sigma^2\mathbf{I}\implies\text{Var}[\mathbf{\varepsilon}]=\sigma^2\mathbf{I}$?
Presumably it was assumed that $\operatorname E(\varepsilon\mid \mathbf X) = 0$ regardless of the value of $\mathbf X.$ Consequently the variance of that expression is $0$ and so the entire second ...
- 11k
Only top scored, non community-wiki answers of a minimum length are eligible