Statistical Data Analysis (code: 401029; credits: 6)


Fall 2011

Please register for this course in VUnet; if this gives problems and you meet the entry requirements (see below), then please register via blackboard.

Docent
Mathisca de Gunst (e-mail: degunst"at"cs.vu.nl), room R3.20.
Assistents
Geert Geeven, e-mail: geert"at"few.vu.nl, room S2.22;
Beata Ros, e-mail: b.p.ros"at"vu.nl, room S2.30.

Entry requirements
Algemene Statistiek (W/Ectrie) or Algemene Statistiek voor BWI.
Students who wish to particpate in the course but have not followed one of these two courses,
are requested to contact the docent, Mathisca de Gunst, before the start of the course.

Content
Aim: The course introduces the students to several widely used statistical models and methods, and the students are taught how to apply these tools to real data.
Covered topics: summarizing data, investigating the distribution of data, Q-Q plots, robust methods, non-parametric methods, bootstrap, two-sample problems, contingency tables, multiple linear regression.

Form of tuition
Lectures, exercises with computer, discussion of exercises.

Literature
Lecture notes (in English) will be provided.

R
The weekly exercises are made with the computer package R. R is installed on the faculty's computer systems, but can als be downloaded for free from here.
Via the same website an introductory manual can be downloaded: below the heading `Documentation' click on `Manuals' and choose "An Introduction to R".
A beginners' manual for R in Dutch can be found here.

Exercises
Weekly homework assignments are made in groups of two people. During the first lecture, the groups will be formed. For the exercises the computerpackage R is used (see above). The homework needs to be neatly made, with in an Appendix all R-code that was used to make the exercises, and handed in in time. It will be graded and discussed in the exercise class one week later. Participation in the exercise classes is compulsory. Too late handing in of the home work as well as absence in an exercise class without proper excuse yields an insufficient score (5) for the homework. A student who repeatedly hands in homework too late and/or repeatedly is absent in the exercise classes without proper excuse, will be expelled from the course.

Assessment
Via weekly homework assignments and written exam.
Both the average score of the homework assignments and the exam score should at least be 5.5. One can take part in the written exam only if the average score of the homework is at least 5.5. The obtained scores for the weekly exercises are valid for one course-year. The final score is the average of the average score of the homework assignments and the exam score.
  
In case the average score of the homework is less than 5.5, at the end of the course a "re-examination" opportunity is given by means of an assignment consisting of exercises similar to the ones in the weekly home work assignments, but more of them and ranging over all topics. The maximum possible score for this "re-examination" homework assignment is 5.5. The written exam has the usual re-examination opportunity.



Information course year 2011-2012

Please enroll in blackbooard!

Exercise Class groups
Please find your Exercise Class group and home work assistant here.
Note: Presence at the exercise classes is compulsory. If there are very pressing circumstances
that prevent you from attending the class, you should notify the docent beforehand.

Schedule
Start Lectures: Tuesday Sept 6.
On Sept 6 presence compulsory both during lecture and computer classes.
Note: Rooms, exam dates, etc. can change any time. Check here for the most recent information.

Reader
The complete Reader.
Data sets of examples in the Reader.

Topics of the week
The part of the Reader to be studied per week plus lecture notes (if any) are given here. (Homework assignments see below.)
06 Sep: Chapters 1 and 2; handout lecture 1
13 Sep: Chapter 3, Sections 3.1-3.5.1; handout lecture 2
20 Sep: Chapter 3, Sections 3.5.2, 3.5.3, Chapter 4, Sections 4.1, 4.2; handout lecture 3
27 Sep: Chapter 4, Sections 4.3, 4.4, 4.5; handout lecture 4
04 Oct: Chapter 5; handout lecture 5
11 Oct: Chapter 6, Sections 6.1 and 6.2; handout lecture 6
01 Nov: Chapter 6, Sections 6.3 and 6.4; handout lecture 7
08 Nov: Chapter 7 plus Fisher's exact test; handout lecture 8
22 Nov: Chapter 8 up to 8.2.3 (not including this section); handout lecture 9
29 Nov: No lectures due to circumstances

Tentative schedule
13 Dec: Question hour Example exam. Exercise class: Ass9

Introduction R
Exercises R, lepton, sample1
A beginners' manual for R in Dutch can be found here.

Homework assignments
The assignments below should be made in English and a printed version should be handed in.
Note: The date indicates the deadline for handing in the assignment; the printed assignment should be handed in
in the mailbox of your exercise class docent (staff room S3.22) no later than 15.30h on the indicated deadline.
15 Sep: Assignment1, light, supermarket
22 Sep: Assignment2, functions Ch3, handy scheme, sample5, sun, lengths
29 Sep: Assignment3, functions Ch4, sample3, expdata1, expdata2, birthweight
6 Oct: Assignment4, climate
13 Oct: Assignment5, functions Ch5, lepton
20 Oct: Assignment6, functions Ch6, statgrades, temp
10 Nov: Assignment7, wereldwinkel, expensescrime
22 Nov (note: this is on a Tuesday): Assignment8, functions Ch7, dna, nausea, austen
There will be only one assignment about Ch8
8 Dec: Assignment9, functions Ch8, life, mortality

Example-exam plus answers
Example-exam
Answers Example-exam

Previous exams
Dec 15 2009
Feb 02 2010
Dec 23 2010
Feb 10 2011
Dec 22 2011