I am very confused on all of this problem, don't know where to start.

1. Consider a large population which has true mean / and true standard deviation o. We take a sample of size 3 from this population, thinking of the sample as the RVs X1, X2, X3 where Xi can be considered iid (independent identically distributed). We are interested in estimating M. (a) Consider the estimator Ml = X1 + X2 - X3. Is this estimator biased? Show your work (b) Find the variance of /1. (c) Consider the estimator (2 = 1+42+43. Is this estimator biased? Show your work (d) Find the variance of /2. (e) Now, consider the estimator (3 = 41+242+3X3. Is this estimator biased? Show your work (f) Find the variance of /3. (g) Which of these three estimators is preferable? Why? (h) Now let u = 100 and o = 10. Define the estimator (4 = 142+3 + EX1. Compute the MSE for /4. (i) Is 4 ever a better estimator than Ml? (j) Extra Credit. If the answer to the preceding question is yes, find the range of values of e for which this is the case. Assume that e is small, so you can drop all terms with an e in them