Solution

ID: past-exam-of-the-mathematics-course-of-the-university-of-cambridge/2019/ii/paper-1/29j/e/solution

Using the estimator from part (b) and the spectral decomposition of ,
Thus
Under the stated separation of scales, the shrinkage factor is approximately one for and approximately zero for . The principal-component shrinkage by ridge regression formula therefore reduces approximately to
the orthogonal projection of onto the span of the normalized sample principal components with greatest variance.

New to topics? Read the docs here!