Suppose that in the linear model Y, = #3:: + lXi + u,- the error has zero mean, E (11,-) = 0, that it has a nonzero conditional mean, E (uXm-JI 9E 0, that observations (H, X;) are independent and identically distributed and that the fourth moments of Y5 and X; are nite. Is the OLS estimator 31 biased? Is it consistent? [11 case it is biased and there is positive correlation between the regresm and the error, does 31 tend to overestimate or underestimate the true value of 31'? Discuss briey