A. Caticha and A. Giffin, "Updating Probabilities", Bayesian Inference and Maximum Entropy Methods in Science and Engineering, ed. by Ali Mohammad-Djafari, AIP Conf. Proc. 872, 31 (2006).

In this paper we show how Bayes Rule is a special case of Maximum Entropy and therefore combine the methods. This is a key result that I have implemented in several papers.

C. Cafaro, S. A. Ali, A. Giffin, "An Application of Reversible Entropic Dynamics on Curved Statistical Manifolds", Bayesian Inference and Maximum Entropy Methods in Science and Engineering, ed. by Ali Mohammad-Djafari, AIP Conf. Proc. 872, 243 (2006).

In this paper we apply Entropic Dynamics to a few example problems.

A. Giffin, "The Error in the Two Envelope Paradox",(2006) (Not refereed).

This is a little paper that I wrote that has probably been read more than most. If you Google it you will find it used as a reference on many web sites.

"Finding a Correction Factor to Compare Flexural Strength and Modulus of Large Deflection Urethane Based Polymers”, BASF, 2003 (Internal paper).

This is an internal paper that came out of a study that I did. The idea was to submit it to an industrial journal but I had left BASF before that could happen. The link is to the paper itself. There are a lot of supporting documents (graphs, pictures, etc.) that are not attached.

A. Giffin and A. Caticha, "Updating Probabilities with Data and Moment Constraints ", to be presented at the 27th International Workshop on Bayesian Inference and Maximum Entropy Methods in Science and Engineering, Saratoga Springs, NY, July 8-13, 2007.

In this paper we give a general and explicitly worked example of how one would use data (Bayes) and a constraint (ME) together.

A. Giffin, "Updating Probabilities with Data and Moment Constraints: An Econometric Example"

In this paper I will solve a current econometric problem (large deviations) using the method that I show in the previous paper. The problem is as follows:

A factory makes four different kinds of bouncy balls. For reference, they assign each different kind with a number 1, 2, 3 or 4. They ship boxes of them out to stores. Unfortunately, there is no mechanism that regulates how many of each ball goes in the boxes. What is the probability of getting a particular kind of ball? To help you, I tell you that while I do not know the amount of each kind of ball in the box, I do know that if you add up all of the numbers for the balls in each box, the average is 2.5. Using maximum entropy, you would arrive at the conclusion that all of the probabilities are the same, 1/4. However, that is certainly not the only solution. So to help you out a little more, I let you pull out 13 balls to examine. Now that you have this additional information, would your assignment of the probabilities change and what would they now be?

Additionally I will use some different sampling methods to solve large dimensional problems.

A. Giffin, "Updating Probabilities In Ecology".

In this paper I hope to do something similar to the previous paper, only in ecology. The problem is as follows:

One may count a few bees in a forest and try to use this sample to estimate all of the bees in the forest. One may also do this with flowers. Additionally, one may know that for every bee, one needs two flowers. How do you use this constraint that correlates the two species?

A. Giffin, "Irreversible Chaos: The Path to Complexity and Randomness".

This paper is a departure from the last two. This paper follows a similar route to a paper that my colleague Carlo Cafaro wrote and to one we co-wrote 2006 (above). The difference is that I introduce the notion of irreversibility in this one.