Module 13: Propensity Score Methods
Type of Course - Dates - Venue - Description - Target audience - Exam - IMPORTANT: Incorporation in DTP and reimbursement by DS
Course prerequisites - Teacher - Course material - Fees - Enrol
Type of course
Taking into account the current status of the corona epidemic the course will be most likely be taught online.
Dates
Wednesday June 2 and Thursday June 3, 2021, from 9 am to 4 pm and Friday June 4, 2021, from 9 am to 12 pm. (Dates subject to change)
Please note: The deadline for UGent PhD students who want a refund to open a dossier on the DS website (Application for Recognition) is April 30, 2021.
Venue
Most likely online. (If on campus: Faculty of Science, Site Sterre, Krijgslaan 281, building S9, Ghent, lecture room 3.1 (V2), third floor + pc class 3.1 (=Konrad Zuse).
Description
The course will consist of the following parts:
Part 1: Introduction. We discuss the basic principles of causal inference; the formulation of a causal question for a well-defined population of interest, an outcome that corresponds to the scientific question under study and a treatment/exposure with relevant levels. We also discuss the problem of confounding by indication and the traditional methods to deal with confounding such as stratification and regression methods.
Part 2: Building a propensity score. The general principle of a propensity score as a balancing score is considered. Methods to build a propensity score, which variables to include. We discuss how to assess if a propensity score is adequate, the assumption of non-positivity and how it can be checked using a propensity score.
Part 3: Propensity based analysis. Different propensity score methods are discussed: matching, stratification, adjustment in a regression model and inverse probability weighting. Each of the methods is discussed in detail with specific focus on the decisions which have to be made when applying a method to real life data. Several case studies will be discussed.
Part 4. Comparison of the different propensity methods and other methods to deal with confounding, discussion of the advantages and disadvantages, and discussion of the causal estimand which is estimated by each of the methods.
The course will be a mixture of theory, case studies and computer exercises using R or Stata.
Target audience
This course will benefit professionals and investigators who are involved in the comparison of interventions using observational data.
Exam
Participants can, if they wish, take part in an exam. Upon succeeding in this test a certificate from Ghent University will be issued.
Please note: For UGent PhD students it is no longer necessary to participate/succeed in this exam to be able to incorporate the course in the DTP.
Incorporation in DTP and reimbursement from DS for UGent PhD students
As a UGent PhD student, to be able to incorporate this 'specialist course' in your Doctoral Training Program (DTP) and get a reimbursement of the registration fee from your Doctoral School (DS) you need to follow strict rules: please take the necessary action in time. The deadline to open a dossier on the DS website (Application for Recognition) for this course is April 30, 2021. Please note that opening a dossier does not mean that you are enrolled. You still need to enrol via the registration form on this site.
Course prerequisites
Participants are expected to have an active knowledge of regression models, in particular logistic regression, and have some experience in working with R or Stata.
Teacher
Course material
The presentations and exercises will be available online.
Fees
A different price applies, depending on your main type of employment.
Employment | Module 13 |
---|---|
Industry/Private sector1 | 925 |
Non-profit, government, university outside AUGent2 | 785 |
(Doctoral)student outside AUGent2 | 355 |
1 If three or more employees from the same company enrol simultaneously for this course a reduction of 10% on the module price is taken into account.
2 AUGent-staff and AUGent doctoral students who pay through use of an SAP internal order/invoice can participate at these special rates.