plz solve it asap in 15 to 20 minutes

Q#1: Answer the following questions (6*2=12) a) If the residuals from a regression estimated using a small sample of data are not normally distributed, what are the consequences that may arise? b) Define a parsimonious model. c) Is serial correlation the same as autocorrelation? d) Suppose the model of interest is y = Bo + BIX1 + 82X2 + #, where E(u/X)=0 and E(u2/X) = o'and X1 and X2 are uncorrelated in your sample. Will the bivariate regression of Y on Xi have the same coefficient estimate and standard error for B, as the multivariate regression of Y on X, and X2? e) What are the cases where it is expectable to obtain heteroscedasticity? f) List the assumptions that are required to show the consistency, unbiasedness and efficiency of the OLS estimator