In the case of the simple regression model Y_i = β₀ + β₁X_i + u_i, i = 1, …, n, when X and u are correlated, then A)the OLS estimator is biased in small samples only. B)OLS and TSLS produce the same estimate. C)X is exogenous. D)the OLS estimator is inconsistent.

Question

Quizplus · Accepted Answer

When X and u are correlated, OLS estimates become biased and inconsistent. Therefore, the OLS estimator is inconsistent in this case. TSLS is preferred to address the problem of endogeneity. Option A is incorrect since the OLS estimator is consistently biased (not only in small samples). Option B is incorrect because OLS and TSLS produce different estimates when X and u are correlated. Option C is incorrect because X is endogenous in this case.

In the Case of the Simple Regression Model Yi =

In the Case of the Simple Regression Model Y_i =