spring 2015

HEL-8009 Analysis of Incomplete Data and Methods for Imputation - 2 stp

Sist endret: 30.06.2015

The course is administrated by

Faculty of Health Sciences

Studiested

Tromsø |

Application deadline

24.02.2015

Type of course

PhD Course. This course is available as a singular course.

Admission requirements

To take PhD courses you need at a minimum a master's degree or equivalent, or admission to a Medical Student Research Program.

For information about how to apply for admission, go to http://uit.no/helsefak/forskning/phd/emner

Course contents

Missing data are ubiquitous in medical research, leading to a loss of statistical power and potentially biased estimates. The aim of this course is to familiarize participants with these issues, and statistical methods for handling missing data.

Specifically the course will:

1. Introduce the issues missing data, review common jargon and argue for a principled, systematic approach
2. Briefly discuss the problems with ad-hoc approaches.  
3. Introduce multiple imputation methods for handling missing data in realistically complex datasets
4. Introduce inverse probability weighting and for missing data and contrast it with imputation
5. Illustrate simple approaches for conducting sensitivity analyses for missing data. Computer practicals will use Stata.

Objective of the course

The participants will:

  • have knowledge about the common terminology regarding incomplete data.
  • have knowledge of the available methods for imputation of missing data.
  • be able to apply the methods on new data.

Language of instruction

English

Teaching methods

A mixture of lectures and computer practicals will be given.

Assessment

The exam will be a take home test evaluated as passed or failed.

The course will be arranged irregularly and no continuation exams will be given.

Schedule



Kontakt
Ansatt---Bjørn-Straume-ii

Bjørn Straume


Førsteamanuensis
Telefon: +4777644837 bst002@post.uit.no