Sir i am stuck for this question

1.4 Part d: variance In this part, we assume that X has only one feature p = 1 and that we do not include the intercept so that , B, and x are univariate. Note that X is an n-by-1 vector. First, use the fact that if e; ~ N(0, o?) then Et_, are; has the N(0, |all302) distribution to show that for OLS, we have Var (BIX) = 02. Next, show that for any > > 0, Var(BA[X) = 1 02 1 + 1problem 1.4 has a mistake: the variance should have the expression sigma^2 / sum_i X_i^2 instead of just sigma ^2 for both betahat and betahat lambda