9.3 Suppose ECM is used to find the ML estimate of y in Example 8.6. Are the iterates likely to converge more quickly or more slowly than EM? Further suppose that SEM is applied to the sequence of ECM iterates, assuming they were EM iterates. Would the resulting asymptotic covariance matrix more likely be an over or underestimate, and explain your reasoning. What about the asymmetry of the calculated matrix? (See Van Dyk, Meng and Rubin, 1995, for details).