Assume the correct model is: y = \beta_0 \beta_1 x_1 \beta_2 x_2 \beta_3 x_3 \mu . Your estimated coefficient of interest is \beta_2 (you are interested in the effect of x_2 on y), but you are not able to observe x_3 . Under which two conditions, the estimated coefficient \beta_2 will be biased? a. cov(x_1, x_3) eq 0 and \beta_3 eq 0 b. cov(x_2, x_3) eq 0 and \beta_3 eq 0 c. cov(x_2, x_3) eq 0 and \beta_2 eq 0 d. cov(x_1, x_3) eq 0 and \beta_1 eq 0