作者: M Hernández Alava , AJ Wailoo , R Ara , None
DOI:
关键词: EQ-5D 、 Function (mathematics) 、 Censored regression model 、 Engineering 、 Set (abstract data type) 、 Tobit model 、 Econometrics 、 Linear regression 、 Bounded function 、 Mixture model 、 Statistics
摘要: Health state utility data generated using the EQ-5D instrument are typically right bounded at one with a substantial gap to next set of observations, left by some negative value, and multi modal. These features present challenges estimation e¤ect clinical socioeconomic characteristics on health utilities. We an adjusted censored model then use this in flexible, mixture modelling framework address these issues. demonstrate superior performance compared linear regression Tobit dataset from repeated observations patients rheumatoid arthritis. �nd that three latent classes appropriate estimating function, pain sociodemographic factors. Analysis should apply methods recognise distributional data.