This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: September 10, 2007 STA 282 INSTRUCTOR: WILLIAM M BRIGGS 1. Week 1 1.1. Logic. We start with logic, and thinking straight. Here is a classical logical argument, slightly reworked: All statistics classes are boring. STA 282 is a statistics class. Therefore, STA 282 is boring. The structure of this argument can be broken down: the two statements before the horizontal line are called premises, the one after is called the conclusion. An- other way to say it is that the premises are our evidence for the conclusion. In any case, we want to know: what is the probability that the conclusion is true? Given the evidence listed, it is 1 (probability is a number between, and including, 0 and 1), the conclusion is certainly true. You are no doubt tempted to say that it is not 1, that is, that the conclusion is not certain, because statistics is nothing if not fun. But that would be missing the point. You are not free to change out the evidence given and insert, say, Statistics is nothing if not fun. You must assess the proba- bility given only the evidence presented. And the conlcusion here is entailed by the premises given. Here is another argument, due (in form, at least) to David Hume All the reality TV shows I have ob- served before have been ridiculous. This is a (new) reality show before me. Therefore, this reality show will be ridiculous. The conclusion here does not follow from the premises; that is, the conclusion is not certainly true. You may be surprised to learn this, but the universe is not set up to guarantee that all reality TV shows will be ridiculous. It may be that, for whatever unknown reason, that this show will not be ridiculous. The conclu- sion, then, is contingent on certain facts (about network executives, uncontrollable weeping, viewers habits, etc.) of the universe being true, and any conclusion that is contingent (on certain conditions about the universe holding) is never certainly 1 2 INSTRUCTOR: WILLIAM M BRIGGS true or certainly false. But how about the probability that the conclusion is true? Pretty high, naturally, but not 1. One last argument I will roll a die, which has six sides, only one of which will show. Just 1 side of the six is labeled 6.. Therefore, the side that shows will be a 6. The conclusion here is also not certain, as will be plainly obvious to any of us. And given just the evidence in the premises, the probability that the conclusion is true is 1 in 6, or about 0.17. For us, then, probability is a measure of the logical relation between a list of premises (or observation statements) and some conclusion. This is not the only interpretation of probability. There are many more, but only two of them have large followings. The largest is called frequentism , the second largest is called Bayesian , which itself is divided in two, a subjective and the logical or objective Bayesian . The differences between the two flavors of Bayesianism are slight, and have to do with how much probabilities are a matter of human beliefs;...
View Full Document
This note was uploaded on 04/08/2008 for the course STA 282 taught by Professor Briggs during the Fall '08 term at Central Mich..
- Fall '08