MATH 6262 Statistical Estimation

Fall 2001

Professor Spruill

Course Outline, Grading, References

• Standard probability distributions

• The spreadsheet, including formulas, for our sample proportion estimation example is available here if you have a spreadsheet program that reads SYLK files.

• Plot of a normal gamma prior.

• If you have Maple you can look at a 3-d plots, rotate them, and see different normal gamma priors.

• If you have a spreadsheet that reads SYLK files you can play with the parameters and simulate Bayesian prediction in a dynamic linear model.

• You can also see a real-time simulation of Bayesian prediction in a dynamic linear model. Compare with best mean square prediction in an autoregressive model.

• You can also simulate 200 observations of a dynamic linear model with the optimal (Bayes) predictor in red.

• A simulation of 200 observations of the autoregressive process of your choice can also be done with the optimal predictor in blue.

• You can run a Monte Carlo estimate of a Poisson parameter. It is the Bayes estimate of the mean q of a Poisson distribution assuming squared error loss and a heirarchical prior of gamma distributions. See the Poisson gamma heirarchy in Lehmann and Casella, Theory of Point Estimation, for details.

• Geometric solution to an odd-even with lying problem.