EMU – Stata command

Background

Quality Adjusted Life Years (QALYs) are used in many assessments of the cost effectiveness of health interventions. However, there is often an evidence gap between clinical measures of effect that are available and the detailed preference-based information needed to construct QALY measures.

The QALY attaches a value of 1 to each year in full health and a value of 0 to death. These two values serve as anchor points for any other health state.

Instruments like the EQ-5D-3L (EQ-5D) have preference-based scoring systems and are favoured by organisations such as the National Institute for Health and Care Excellence (NICE) to use in the estimation of QALYs.

The EQ-5D questionnaire asks individuals to describe their health using five different dimensions: mobility, self-care, usual activities, pain/discomfort, anxiety/depression. Each dimension has three levels: no problems, some problems, extreme problems. There are 243 theoretically possible health states described by this instrument which have each been assigned a value based on general public preferences.

Frequently, EQ-5D is absent from clinical studies of treatment effect which prevents the direct calculation of QALYs. Often this gap is bridged by “mapping” – estimating a relationship between observed clinical outcomes and preference based measures, using data from another dataset containing both types of information. However, the distribution of EQ-5D exhibits characteristics which make standard models inappropriate.

The adjusted limited dependent variable mixture model variable was first proposed by Hernández-Alava et al. (2012) to deal with the distributional features presented by EQ-5D. The command described here estimates the variant of the model presented in Hernández-Alava et al. (2013) and Hernández-Alava et al. (2014).

MRC / DSU publication

M Hernández Alava, A Wailoo (2015) ALDVMM: A command for fitting Adjusted Limited Dependent Variable Mixture Models to EQ-5D (PDF, 312KB). The Stata Journal. In press. Available online.

This publication was part-funded by the NICE DSU and the MRC.

References

M Hernández-Alava, A Wailoo and R Ara (2012) Tails from the peak district: Adjusted Limited Dependent Variable Mixture Models of EQ-5D Health State Utility Values. Value in Health 15(3): 550-561 (May 2012)

M Hernández-Alava, A Wailoo, F Wolfe and K Michaud (2013) The relationship between between EQ-5D, HAQ and pain in patients with rheumatoid arthritis. Rheumatology 52(5): 944-950 (January 2013)

M Hernández-Alava, A Wailoo, F Wolfe and K Michaud (2014) A comparison of direct and indirect methods for the estimation of health utilities from clinical outcomes. Medical Decision Making 34: 919-930 (October 2014)