Two-day short course: Methods for addressing missing data in health economic evaluation

Course dates: 21-22 September 2017

Venue: University College London (further details to follow soon.)

Course overview

Missing data are ubiquitous in health economic evaluation. The major concern that arises with missing data is that individuals with missing information tend to be systematically different from those with complete data. As a result, cost-effectiveness inferences based on complete cases are often misleading. These concerns face health economic evaluation based on a single study, and studies that synthesise data from several sources in decision models. While accessible, appropriate methods for addressing the missing data are available in most software packages, their uptake in health economic evaluation has been limited.

Taught by academics with extensive expertise in missing data methodology, this course offers an in-depth description of both introductory and advanced methods for addressing missing data in health economic evaluation. The course will combine a mixture of lectures and computer-based exercises, where participant will learn about the relevant statistical concepts and the application of the methods in practice. Participants will engage in practical sessions illustrating how to implement each technique with user-friendly software (Stata®). We welcome participants bringing their own data and problems, and one session is dedicated to discussion of participants' case-studies.

Objectives

By the end of the course the participants will be able to:

· Recognise the key statistical concepts, underlying assumptions and the relative merits of different statistical methods for dealing with missing data

· Perform a descriptive analysis of incomplete cost-effectiveness data

· Apply multiple imputation to address missing data in economic evaluation studies

· Conduct sensitivity analyses to assess whether cost-effectiveness inferences are robust to alternative missing data assumptions

· Consider Bayesian methods for addressing the missing data and bringing in additional evidence to inform the missing data assumptions

· Report and interpret cost-effectiveness results in light of contextually plausible missing data assumptions

Target audience

· Health economists, statisticians, policy advisors, or other analysts with an interest in health economic evaluation.

· Participants will be interested in undertaking or interpreting cost-effectiveness analyses that use patient-level data, either from clinical trials or observational data.

· Should be familiar with running Stata from the command line

· No prior knowledge of methods for handling missing data is assumed

Programme

Day 1   

  • Overview of missing data issues in cost-effectiveness analysis
  • Descriptive analysis of the missing cost-effectiveness data.
  • Alternative statistical approaches for dealing with missing data
  • Practical guidance on the use of multiple imputation in Stata
  • Applying multiple imputation in cost-effectiveness analysis

Day 2

  • Addressing missing data in hierarchical studies
  • Implementing multilevel multiple imputation in Stata
  • Sensitivity analysis approaches to assess departures from MAR assumption
  • Combining multiple imputation with pattern mixture models
  • Bayesian approaches for addressing missing data in economic evaluation

Faculty

· Manuel Gomes, UCL

· Gianluca Baio, UCL

· Ian White, MRC Clinical Trials Unit at UCL

· James Carpenter, LSHTM and MRC Clinical Trials Unit at UCL

· Baptiste Leurent, LSHTM

Register

To register for the course please complete the Registration Form. For more information, contact m.gomes@ucl.ac.uk, or call 0207 3108 3080.

Fees

The course fees include tuition, course materials, lunches and tea/coffee breaks. Delegates are advised to arrange their own travel and accommodation.

Students/UCL Staff £200

Public Sector £450

Commercial/Industry £600

Cancellations and alterations

A full refund of course fees will be made for cancellations prior to the 8th September 2017. Substitutes can be made but please email new delegate's details to m.gomes@ucl.ac.uk. Cancellations made after the 8th September 2017 are non-refundable. In the unlikely event that, due to unforeseen circumstances, the course has to be cancelled by the University College of London, our liability is limited to refund of course fees. We recommend delegates have adequate insurance cover to claim any travel or personal expenses.