Jan J Barendregt1. 1. School of Population Health, University of Queensland, Herston, QLD, Australia. j.barendregt@sph.uq.edu.au
Abstract
OBJECTIVE: In model-based health economic evaluation, uncertainty analysis is often done using parametric bootstrapping. This requires specifying probability distributions for the model variables that are uncertain. METHODS: The effect size of the intervention is often expressed as a relative risk, and the standard assumption for a relative risk is that it has a lognormal distribution with the natural log of the relative risk and its standard error as parameters. The problem with this assumption is that the mean of the bootstrap draws from the lognormal distribution is always higher than the relative risk. RESULTS: This article looks at two ways to correct for this effect and discusses their advantages and drawbacks. Both methods return a bootstrap mean equal to the relative risk, but the first returns an uncertainty interval that is narrower than the corresponding confidence interval, although the second method retains the corresponding width. CONCLUSIONS: The article concludes that the second correction method is preferred.
OBJECTIVE: In model-based health economic evaluation, uncertainty analysis is often done using parametric bootstrapping. This requires specifying probability distributions for the model variables that are uncertain. METHODS: The effect size of the intervention is often expressed as a relative risk, and the standard assumption for a relative risk is that it has a lognormal distribution with the natural log of the relative risk and its standard error as parameters. The problem with this assumption is that the mean of the bootstrap draws from the lognormal distribution is always higher than the relative risk. RESULTS: This article looks at two ways to correct for this effect and discusses their advantages and drawbacks. Both methods return a bootstrap mean equal to the relative risk, but the first returns an uncertainty interval that is narrower than the corresponding confidence interval, although the second method retains the corresponding width. CONCLUSIONS: The article concludes that the second correction method is preferred.
Authors: Rosana Norman; Michelle Schneider; Debbie Bradshaw; Rachel Jewkes; Naeemah Abrahams; Richard Matzopoulos; Theo Vos Journal: Popul Health Metr Date: 2010-12-01
Authors: Joel W Hotchkiss; Carolyn A Davies; Ruth Dundas; Nathaniel Hawkins; Pardeep S Jhund; Shaun Scholes; Madhavi Bajekal; Martin O'Flaherty; Julia Critchley; Alastair H Leyland; Simon Capewell Journal: BMJ Date: 2014-02-06
Authors: Albert Marni Joensen; Torben Joergensen; Søren Lundbye-Christensen; Martin Berg Johansen; Maria Guzman-Castillo; Piotr Bandosz; Jesper Hallas; Eva Irene Bossano Prescott; Simon Capewell; Martin O'Flaherty Journal: PLoS One Date: 2018-04-19 Impact factor: 3.240
Authors: Shaun Scholes; Madhavi Bajekal; Paul Norman; Martin O'Flaherty; Nathaniel Hawkins; Mika Kivimäki; Simon Capewell; Rosalind Raine Journal: PLoS One Date: 2013-07-25 Impact factor: 3.240
Authors: Belen Zapata-Diomedi; Luke D Knibbs; Robert S Ware; Kristiann C Heesch; Marko Tainio; James Woodcock; J Lennert Veerman Journal: PLoS One Date: 2017-10-11 Impact factor: 3.240