|
Activity Number:
|
523
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #304245 |
|
Title:
|
Recent History Functional Linear Model for Sparse Longitudinal Data
|
|
Author(s):
|
Kion Kim*+ and Senturk Damla
|
|
Companies:
|
Penn State University and Penn State University
|
|
Address:
|
331B, Thomas Bldg., University Park, 16801,
|
|
Keywords:
|
Covariance Function ; Functional Linear Models ; Regression Spline ; Sparse Longitudinal Data ; Varying Coeffficient Models
|
|
Abstract:
|
We propose a variant of historical functional linear models for cases where the current response is affected by the predictor process in a window into the past. We expand the functional regression surface using regression splines and utilize connections to varying coefficient models. The algorithm proposed is geared towards sparse longitudinal data where the observations are irregular and total number of measurements per subject is small. The algorithm is fast and easy to implement involving one dimensional basis expansions. Simulations are used to demonstrate the efficacy of the proposed method.
|
