Abstract
The problem of analyzing a continuous variable with a discrete component is addressed within the framework of the mixture model proposed by Moulton and Halsey (Biometrics 1995; 51:1570-1578). The model can be generalized by the introduction of the log-skew-normal distribution for the continuous component, and the fit can be significantly improved by its use, while retaining the interpretation of regression parameter estimates. Simulation studies and application to a real data set are used for demonstration.
Original language | English (US) |
---|---|
Pages (from-to) | 3643-3655 |
Number of pages | 13 |
Journal | Statistics in Medicine |
Volume | 27 |
Issue number | 18 |
DOIs | |
State | Published - Aug 15 2008 |
Keywords
- Censoring
- Skew-normal distribution
- Two-part model
ASJC Scopus subject areas
- Epidemiology
- Statistics and Probability