Bayes-päättely, kevät 2013

Johdatus todennäköisyyslaskentaan tai vastaavat tiedot todennäköisyyslaskennan peruskäsitteistä, kuten satunnaismuuttujista ja niiden jakaumista (esim. binomijakauma, normaalijakauma, yms) on hyvä olla jossain määrin tuttua sillä Bayes-päättely nojautuu todennäköisyyksien laskentaan. Myös johdatus tilastolliseen päättelyyn ja kiinnostus empiiristen aineistojen tilastolliseen mallintamiseen on hyödyksi.

20

21

Introduction to probability theory or equivalent course is prerequisite, so that you should be familiar with concepts such as random variables and their typical distributions (e.g. binomial, normal etc) because Bayes inference is heavily based on probability calculations. Also previous exposure to statistical inference and interest in empirical data analysis is useful.

=== Luentoajat ===

Viikot 3-8 ti 16-18, to 16-18 B120, lisäksi laskuharjoituksia 2 viikkotuntia.

=== Kokeet ===

Changed exam date: Friday (% style="color: rgb(0,0,255);" %)**1.3.**(%%) at 9~-~-12 in CK112. (as written in the Moodle pages, which you hopefully have been following).

30

31

If this is not possible to attend, or if you need 2nd exam, another one would be 21.3. (general examination day - yleistentti). **Register at the dept. office latest 19.3.**

=== Kirjallisuus ===

Materials are in English, but lectures in Finnish. Materials are based on those of previous courses, and excerpts from books such as "Bayesian ideas and data analysis: an introduction for scientists and statisticians" (Chapman & Hall /CRC 2011). This time the plan is to introduce WinBUGS/OpenBUGS a bit earlier than previously so that we could (hopefully) move smoothly between theory and practical calculations with BUGS, to get working experience with the calculations. We start with one parameter inference, using examples that have analytical solutions by paper and pencil, and then move to cases which are simulated using BUGS software (and/or a little bit with R). In the end, the goal is that you should understand the basic philosophical principle of Bayesian inference, its fundamental elements, and how they are put together and computed, and to distinguish between (classical) cases which have analytical solution and those more general ones which require simulation, and how to construct a Baysian model for simple probabilistic data analysis purposes using BUGS.

36

37

Materials, exercises, etc. in Moodle: [[https:~~/~~/moodle.helsinki.fi/course/view.php?id=8905>>url:https://moodle.helsinki.fi/course/view.php?id=8905||shape="rect"]]

38

39

(% style="color: rgb(255,0,0);" %)**Exercise group on Thu would start at 18:00 for the rest of the weeks, (we try to finish lecture at 17:45 before that). **(%%)

40

41

42

=== [[Ilmoittaudu>>url:https://oodi-www.it.helsinki.fi/hy/opintjakstied.jsp?html=1&Tunniste=57753||shape="rect"]] ===

43

44

Unohditko ilmoittautua? [[Mitä tehdä>>doc:mathstatOpiskelu.Kysymys4]].

45

46

=== Laskuharjoitukset (Starting 21.1.) ===

47

48