Contents
How do you prove consistency of an estimator?
The third way of proving consistency is by breaking the estimator into smaller components, finding the limits of the components, and then piecing the limits together. This is described in the following theorem and example. i →p E (X2) and by adding the above theorem we have ¯X2 →p E (X)2.
What can you conclude about consistency of OLS estimator?
The OLS estimator is consistent when the regressors are exogenous, and—by the Gauss–Markov theorem—optimal in the class of linear unbiased estimators when the errors are homoscedastic and serially uncorrelated.
What does it mean for an OLS estimator to be consistent?
An estimator is consistent if ˆβ→pβ Or limn→∞Pr(|ˆβ−β|<ϵ)=1 for all positive real ϵ. Consistency in the literal sense means that sampling the world will get us what we want.
What causes OLS to be inconsistent?
The presence of omitted-variable bias violates this particular assumption. The violation causes the OLS estimator to be biased and inconsistent. The direction of the bias depends on the estimators as well as the covariance between the regressors and the omitted variables.
Why do we estimate OLS in the first place?
This is why we estimate it in the first place. When you estimate this model and if OLS is BLUE, then plimˆβOLS = β This means, as your sample size becomes larger and larger, your estimate ˆβ converges to the true value β. In this case you are “consistently” estimating this parameter.
Is the OLS estimator biased or biased?
This doesn’t mean that every estimator fulfills these requirements. If Cov(X, u) ≠ 0, OLS is biased (but it may still be “best”, i.e. it has the smallest variance, and it will be “linear”).
When does OLS always estimate the best linear predictor?
If we have random sample X, Y and X ′ X is invertible, then we can always define Best Linear Predictor of y given x. And then OLS always consistently estimates coefficients of Best Linear Predictor (because in BLP we have Cov(u, x) = 0 from the definition).
What do you consistently estimate with OLS WRT # 2?
That is what you consistently estimate with OLS, the more that n increases. WRT #2 Linear regression is a projection. The predictors we obtain from projecting the observed responses into the fitted space necessarily generates it’s additive orthogonal error component.