This course is not running in 2015.
Health economic evaluations often make use of observational data. A major concern is that cost-effectiveness results may be subject to selection bias. While sophisticated methods for addressing selection bias are routinely used in other literatures, their uptake in health economic evaluation has been limited.
This course offers an in depth description of 'cutting edge' methods for addressing treatment selection bias in economic evaluation, developed as part of an ESRC grant (for more details visit http://www.lshtm.ac.uk/php/hsrp/reducing-selection-bias/index.html). These methods include regression, propensity score matching, an approach that extends propensity score matching (Genetic Matching) and ‘combination’ methods such as regression-adjusted matching. In addition, this year the course will include approaches for handling aspects of unobserved confounding including difference-in differences estimation, and the synthetic control method .
The course will highlight underlying assumptions and the pros and cons of each method. Articles on the development of these methods have recently been accepted for publication in leading health economics and statistical journals (Sekhon and Grieve, Health Econ, 2011; Kreif et al, Med Decis Making, 2012; Radice et al, Int J Biostats , 2012; Kreif et al, Stats Methods in Medical Research, 2014).
The course places a strong emphasis on applying the methods in practice, with practical sessions illustrating how to implement each technique with readily available software (STATA and R).
The course will feature a guest lecture by Dr Ian White (MRC Biostatistics Unit, Cambridge). Ian’s talk will focus on new methods for handling treatment switching in RCTs.
Who should apply?
The course is aimed at health economists, or statisticians with an interest in health economic evaluation. It is envisaged that participants will be interested in undertaking or interpreting cost-effectiveness analyses that use observational data.
This is an advanced course focusing on statistical methods for economic evaluation. Participants would be expected have some familiarity with STATA, and relevant statistical concepts such as OLS regression.
By the end of the course participants will:
- have a clear conceptual understanding of the key underlying assumptions underpinning the relevant approaches for address selection bias
- be able to adjust for observed confounders with regression and propensity score matching approaches
- be able to apply a computationally intensive matching method, Genetic Matching, that matches on individual confounders
- be able to implement matching methods in both STATA and R.
Teaching Methods and Course Materials
The course consists of lectures and computer practical sessions. Comprehensive course notes will be provided at the start of the course. Computer practicals will use STATA and the R package, which is freely available with documentation at http://cran.r-project.org/. The course is limited to 15 participants.
Richard Grieve, Zia Sadique and Noemi Kreif
Methods of Assessment
There is no formal assessment but a certificate of attendance will be provided.
Commercial sector: N/A
Public/academic sector: N/A
If the course fee is to be paid on the applicant's behalf, please send a letter from the sponsor to confirm this as soon as possible. Otherwise, the applicant will be held personally responsible for payment. Fess are payable in full by 18 August 2014.
How to Apply
We are currently not accepting applications.
The London School of Hygiene & Tropical Medicine is committed to improving global health through its programme of short and full-time postgraduate study.
- If you have been offered a place on the course you will not be able to register without bringing formal ID (Passport) and without having obtained the correct visa.
- It is essential that you read the current visa requirements for short course students. To view this information please click here.
- The School may cancel courses two weeks before the first day of the course if numbers prove insufficient. In those circumstances, course fees will be refunded.
- The School cannot accept responsibility for accommodation, travel and other losses incurred as a result of the course being cancelled.