applied econometric

Question

.A. Suppose that x is a regressor in a model to be estimated by ordinary least squares (OLS). If cov(𝑥, 𝑒) ≠ 0, what kind of problem are we faced with when we estimate this model?

Answer 1

When regressor x is correlated with error e (e.g. due to omitted variable bias) this is called endogeneity which my lead to biased estimates as it violates the exogeneity assumption in the OLS (the Gauss-Markov theorem).