Non-Parametric Heteroscedastic Transformation Regression Models for Skewed Data With an Application to Health Care Costs
- 16 September 2008
- journal article
- Published by Oxford University Press (OUP) in Journal of the Royal Statistical Society Series B: Statistical Methodology
- Vol. 70 (5) , 1029-1047
- https://doi.org/10.1111/j.1467-9868.2008.00669.x
Abstract
Summary: We develop a new non-parametric heteroscedastic transformation regression model for predicting the expected value of the outcome of a patient with given patient's covariates when the distribution of the outcome is highly skewed with a heteroscedastic variance. In our model, we allow both the transformation function and the error distribution function to be unknown. We show that under some regularity conditions the estimators for regression parameters, the expected value of the original outcome and the transformation function converge to their true values at the rate n−1/2. In our simulation studies, we demonstrate that our proposed non-parametric method is robust with little loss of efficiency. Finally, we apply our model to a study on health care costs.Funding Information
- Healthcare Research and Quality (R01HS013105)
- US Department of Veterans Affairs (ECI-03-206)
- Veterans Affairs Health Administration
- Health Services Research & Development
- Fund of National Natural Science (10771148)
This publication has 19 references indexed in Scilit:
- Estimating marginal and incremental effects on health outcomes using flexible link and variance function modelsBiostatistics, 2004
- Too much ado about two-part models and transformation?Journal of Health Economics, 2004
- Modeling risk using generalized linear modelsJournal of Health Economics, 1999
- Quasi-Likelihood Regression with Unknown Link and Variance FunctionsJournal of the American Statistical Association, 1998
- Estimating Outcome Distributions for Compliers in Instrumental Variables ModelsThe Review of Economic Studies, 1997
- Generalized Partially Linear Single-Index ModelsJournal of the American Statistical Association, 1997
- Semiparametric Estimation of a Regression Model with an Unknown Transformation of the Dependent VariableEconometrica, 1996
- Transformation and Weighting in RegressionPublished by Springer Nature ,1988
- Non-parametric analysis of a generalized regression modelJournal of Econometrics, 1987
- Smearing Estimate: A Nonparametric Retransformation MethodJournal of the American Statistical Association, 1983