Abstract Details
Activity Number:
|
70
|
Type:
|
Contributed
|
Date/Time:
|
Sunday, August 3, 2014 : 4:00 PM to 5:50 PM
|
Sponsor:
|
Biometrics Section
|
Abstract #312291
|
|
Title:
|
Degradation Data Analysis Using Nonlinear Mixed-Effects Models and Shape-Restricted Splines
|
Author(s):
|
Zhibing Xu*+
|
Companies:
|
Virginia Tech
|
Keywords:
|
Degradation Data ;
Nonlinear ;
Shape-restricted Splines ;
Random Effects
|
Abstract:
|
Comparing to the traditional life time data, degradation data not only can provide enough information in a short time, but also give a better estimation and prediction of the life time of the highly reliable products. With the improvement of technology, life-affecting environmental variables are recorded as well as the degradation measure over time. For example, the large amount of ultraviolet exposure will accelerate the degradation of the polymer coating. Thus, it is important to incorporate the environmental variables, also called dynamic covariates, into the degradation path model. Existing research suggests a linear mixed-effects model with splines to incorporate the dynamic covariates. However, the linear model may not widely used in practice, especially in the pharmacokinetic research. In this paper, we propose a nonlinear mixed-effects model incorporating with dynamic covariates to model the degradation data. Shape restricted splines are used in the proposed model and a modified alternating algorithm is developed. The performance of the algorithm is evaluated by simulations. An outdoor weathering dataset is used for illustration of the proposed method.
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.