St Joseph’s Healthcare Hamilton, Hamilton, Ontario, Canada (EMP)
University of Toronto, Toronto, Ontario, Canada (HSW)
Med Decis Making. 2013 Feb;33(2):244-51. doi: 10.1177/0272989X12465354. Epub 2012 Nov 6.
Measured utility data have a discrete distribution, and the discreteness is particularly pronounced for EQ-5D utilities. Given the discreteness of the data, modeling the distribution parametrically is likely to be difficult. Moreover, since the distribution is bounded, the linearity assumptions made by many models are questionable. This article suggests using semi-parametric models and illustrates the use of generalized additive models (GAMs) for handling nonlinear associations.
A simulation study is used to explore whether bias arises when applying parametric models to discrete utility data. A further simulation investigates the bias in semi-parametric linear and quasi-beta regression models when the assumed linearity does not hold and also investigates the use of GAMs. The use of GAMs in practice is shown through a recent study of health utilities among patients with diabetes.
Using parametric beta models to analyze discrete EQ-5D utility data led to substantial bias. Both semi-parametric linear regression and quasi-beta regression led to biased estimates of marginal and incremental effects when the mean model was misspecified. The use of GAMs reduced these biases.
Parametric models for EQ-5D utility data should be used with caution. Semi-parametric modeling of utility data should check for nonlinearity. GAMs can help in diagnosing and accommodating nonlinearity.
测量效用数据具有离散分布，对于 EQ-5D 效用数据，离散性尤为明显。鉴于数据的离散性，参数化建模可能很困难。此外，由于分布是有界的，许多模型所做的线性假设值得怀疑。本文建议使用半参数模型，并说明如何使用广义加性模型（GAMs）来处理非线性关联。
使用模拟研究来探讨在将参数模型应用于离散效用数据时是否会出现偏差。进一步的模拟研究了当假设的线性关系不成立时，半参数线性和拟贝塔回归模型中的偏差，以及 GAMs 的使用。通过最近对糖尿病患者健康效用的研究，展示了 GAMs 的实际应用。
使用参数 beta 模型分析离散 EQ-5D 效用数据会导致很大的偏差。当均值模型指定不正确时，半参数线性回归和拟贝塔回归都会导致边际和增量效应的有偏估计。使用 GAMs 可以减少这些偏差。
对于 EQ-5D 效用数据，参数模型的使用应谨慎。效用数据的半参数建模应检查非线性。GAMs 有助于诊断和适应非线性。
