Odota...
Wait...
Korppi-järjestelmän toimintoja Korppi
Huhtikuu 2014
  Ma Ti Ke To Pe La Su
14:   1 2 3 4 5 6
15: 7 8 9 10 11 12 13
16: 14 15 16 17 18 20
17: 21 22 23 24 25 26 27
18: 28 29 30
 

10.62.0

Kirjaudu sisään järjestelmään!
19.4.2014 22:33

IHMJ215 Handling Missing Data, 3 - 5 op

Ihmistieteiden metodikeskus

Tiedotus:
Kurssille ei voida ilmoittautua, koska se on jo vanhennettu.
Kurssin ilmoittautumisaika päättyi 6.4.11 klo 09:00.
Tiedotus:
Kurssille ilmoittautuneet järjestetään ilmoittautumisjärjestyksen mukaan. Lisätietoja jonotuksesta.

Yleisiä tietoja

Alkaa - päättyy: 6.4.11 - 8.4.11
Ilmoittautumisaika: 1.2.11 klo 9:00 - 6.4.11 klo 9:00
Ilmoittautuminen voidaan perua 6.4.2011 klo 09:00 mennessä.
Opettaja(t): -
Laajuus: 3 - 5 op
Kielet: opetuskielet: English; suorituskielet: English
Ilmoittautuneita: 33
Maksimi osallistujamäärä: 30 (Jonotuskäytännöstä johtuen kurssille voidaan ilmoittautua, vaikka maksimi osallistujamäärä ylittyisikin.);
Organisaatiot:Ihmistieteiden metodikeskus (IHM)
Ajankohtaista:

Responsible teacher: Mervi Eerola (IHME)

Teachers: Prof. Susanne Rässler (Universität Bamberg), Dr. Jonathan Bartlett (London School of Hygiene and Tropical Medicine)

Sisältö:

The introductory course and the research seminar following it deal with the meaning of missing data and its mending possibilities. It is targeted for both doctoral students and senior researchers and research groups.

COURSE ON HANDLING MISSING DATA, 6-7 April 2011

Teacher: Dr Jonathan Bartlett (London School of Hygiene and Tropical Medicine)

Summary of the course: This course aims to

-provide an introduction to the issues raised by missing data, and the associated statistical jargon
-illustrate the shortcomings of ad-hoc methods for handling missing data
-introduce multiple imputation for statistical analysis with missing data
-discuss the issues involved in analysing longitudinal studies with missing data, including use of multiple imputation and linear mixed models

Course content: The course will consist of 4 sessions, each of which comprises a 1hr lecture followed by a 1.5hr computer practical using R:

Wednesday, April 6

9-12 Session I: Introduction, issues raised by missing data, and towards a systematic approach
13-16 Session II: Shortcomings of ad-hoc methods; introduction to multiple imputation (MI)

Thursday, April 7

9-12 Session III: More on multipIe imputation (joint model approach, chained equations)
13-15 Session IV: Missing data in longitudinal and multi-level studies (concepts, MI, linear mixed models)

Course Materials: Participants will receive written course notes, computer practicals and solution sheets.

RESEARCH SEMINAR ON MISSING DATA IN SURVEYS 7-8 April 2011

Lecturer: Professor Susanne Rässler

Seminar content

The seminar will consist of 3 lectures, the first starting on Thursday afternoon after the course and the second and third on Friday. The seminar will end with a session of examples from the local research projects and discussion. Lunch break 12-13 and coffee breaks as needed.

Thursday, April 7

15.15-17 Session I: Special missing data problems in surveys (item nonresponse, unit nonresponse, combining data from different sources, split questionnaire survey designs, censored data, confidentiality and synthetic data, Rubin causal model and potential outcomes) and a quick introduction to Bayesian statistics

Friday, April 8
9-10.30 Session II: Some illustrative theory on Multiple Imputation (combining rules, analyst model vs. imputer model, correct modelling and creation of imputations, why does single imputation not work for inference

11.00-12.30 Session III: Common multiple imputation models for complex surveys (chained equations, Gibbs sampling, data augmentation)

13.30-16.00 Examples and discussion: practical problems and solutions

Prof. Dr. Susanne Rässler holds the Chair of Statistics and Econometrics at the Otto-Friedrich-University of Bamberg, Germany, and is speaker of the methods group of the National Educational Panel Study. Her research interest involves methods for handling missing data in complex surveys, multiple imputation, Bayesian and computational statistics as well as matching techniques for causal analysis and marketing research. She is closely working together with Prof. Donald B. Rubin, Harvard University, USA, the founder of multiple imputation.

Dr Jonathan Bartlett is Research Fellow in the Department of Medical Statistics at the London School of Hygiene & Tropical Medicine (University of London). His research involves investigating methods for dealing with coarsened data, including methods to deal with covariate measurement error, in particular in life-course studies, and missing data. He has co-led a number of missing data courses across Europe. More information about his work and courses on page www.missingdata.org.uk

Esitiedot:

Target Audience: Epidemiologists, biostatisticians and researchers from the social sciences, psychology, health science, economics, and educational research. Participants should have some experience in statistical analyses, including fitting regression models. R will be used for the computer practicals, and so familiarity with the package is highly desirable, although full R code and solutions will be provided.

Ilmoittautuminen:

The students of the University of Jyväskylä register for the courses in Korppi study system. The students of the University of Tampere and Tampere University of Technology: get registered by sending email to tiina.m.hokkanen@jyu.fi .

[Tiivistä opetusryhmien aika- ja paikkatiedot]

Luento [ryhmien tarkat tiedot ja ilmoittautuminen]

Luento [ryhmätiedot ja ilmoittautuminen]; ilmoittautuneita 33, maksimi 30
ilm.aika: 1.2.2011 09:00 - 6.4.2011 09:00
 PaikkaViikkoPäiväPvmKloOhjaajaLisätietojaURITapahtuman tiedot
1MaC 10214ke6.4.201109:15-16:00-Tapahtuman tiedot
Luento [ryhmätiedot ja ilmoittautuminen]; ilmoittautuneita 33, maksimi 30
ilm.aika: 1.2.2011 09:00 - 6.4.2011 09:00
 PaikkaViikkoPäiväPvmKloOhjaajaLisätietojaURITapahtuman tiedot
1MaB 10214to7.4.201109:15-16:00-Tapahtuman tiedot
2MaC 10214pe8.4.201109:15-16:00-Tapahtuman tiedot

Demo [ryhmien tarkat tiedot ja ilmoittautuminen]

Demo 1 [ryhmätiedot ja ilmoittautuminen]; ilmoittautuneita 20, maksimi 30
ilm.aika: 1.2.2011 09:00 - 6.4.2011 09:00
 PaikkaViikkoPäiväPvmKloOhjaajaLisätietojaURITapahtuman tiedot
1MaD 20614ke6.4.201109:00-17:00-Tapahtuman tiedot
2Ag B111.1 (Asia)14to7.4.201113:00-17:00-Tapahtuman tiedot
3Ag B112.1 (Africa)14to7.4.201113:00-17:00-Tapahtuman tiedot
4MaD 20614pe8.4.201109:15-12:00-Tapahtuman tiedot
Demo 1 [ryhmätiedot ja ilmoittautuminen]; ilmoittautuneita 12, maksimi 30
ilm.aika: 1.2.2011 09:00 - 6.4.2011 09:00
 PaikkaViikkoPäiväPvmKloOhjaajaLisätietojaURITapahtuman tiedot
1MaD 20614to7.4.201109:00-12:00-Tapahtuman tiedot