Vinteren i Nerja

1. Wed Feb 20 we discussed some basics regarding Bayesian formalism for determining Pr(model | data). This leads via further approximations to the BIC. We continue next week with more from Ch 3 and also Section 4.2; the other Ch 4 sections are "cursory curriculum" only.

2. General message A: We've been through a perhaps challenging phase regarding R programming of logL functions, how to work one's way through several competing models, Jhat and Khat matrices, etc. There may be further things to learn in the weeks ahead, but we've more or less reached the "right level of expertise". In yet other words, it should be easier sailing from now on. General message B: By necessity some of our efforts so far in the course have been associated with "getting things done", fitting models to real data with new twists & turns, etc. But this ought not to create an impression that getting one's R programmes to work, cranking out numbers and figures and tables etc., is the "main part", or somehow sufficient for the exam project down the road, etc. A good exam project (also) requires thinking and maturity and presentational skills and good writing (!).

3. Exercises for Wed Feb 27: First, the rest of the details regarding the 189 mothers & babies, finding estimates of the focus parameters for the two mothers we're zooming in on (age 33, weight 66, smoker vs non-smoker). Also, in addition to the eight "traditional" linear regression models, try one more, namely the "skewed extension of the normal" described in the book's Section 6.6.3. Does it pay off to include the extra lambda parameter? You may start off from com10a, which I've uploaded to the site. Second, continue and finish the work I started on the blackboard, regarding blood groups A, B, AB, 0 (Example 3.6). Compute the exact Pr(M1 | data), Pr(M2 | data), with flat priors on the two parameter spaces involved.