In Example 1, suppose it is desired to estimate 8 under squared-error loss, but that an approximate r-minimax estimator is desired for robustness reasons. Suppose r is the e-contamination class, with...

In Example 1, suppose it is desired to estimate 8 under squared-error loss, but that an approximate r-minimax estimator is desired for robustness reasons. Suppose r is the e-contamination class, with 21 = {all distributions}, e =0.1, and 170 being the K(100, 225) distribution. Find the appropriate estimator and give its r-minimax risk. Compare the estimate for x = 115 with the conjugate prior Bayes estimate and that from Exercise 105.