Hw7 - is somewhat messy.) Extra Problems: Figure out the...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
Reading: All of Ch. 7 except 7.2.4 (EM algorithm) Background reading: Section 5.3, pages 218--220 and Section 5.5, pages 232--236 and Section 10.1, pages 467-468 Exercises in Chapter 7: 1, 4, 6--13, 19--24 37, 38, 40, 42, 46, 47, 49, 50, 52, 57, 59, 60 Comments and Additional Parts for the Chapter 7 Exercises: 22 and 24: Add another part to these two problems: Show that when the sample size n is large the Bayesian (reporting the posterior mean and variance) will be essentially in agreement with the non-Bayesian (reporting the MLE and its estimated variance). 50: In part (b) use the result of problem 42. 38(a): Also, compute the CR bound explicitly. (The computation of the CR bound in (b)
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: is somewhat messy.) Extra Problems: Figure out the MOM estimates of the parameters alpha, beta of a Gamma distribution based upon a random sample of size n. Do this for: (1) alpha (when beta is known), (2) beta (when alpha is known), and (3) alpha and beta (both are unknown). You should be able to compute Fisher Information and CR bounds for the common families of distributions. Find the Fisher information matrix for a k-parameter exponential family with the natural parameter w(theta)=theta. http://www.stat.fsu.edu/~huffer/mordor/5327/test2_material/ch7_hw_pro. .. 1 of 1 08/08/2009 7:09 PM...
View Full Document

This note was uploaded on 12/15/2011 for the course STAT 5326 taught by Professor Frade during the Fall '10 term at FSU.

Ask a homework question - tutors are online