Skip to Main Content
 

Global Search Box

 
 
 
 

Files

File List


print_version.pdf (698.79 KB)

ETD Abstract Container

Abstract Header

Tree-based Models for Longitudinal Data

Liu, Dan
http://rave.ohiolink.edu/etdc/view?acc_num=bgsu1399972118

Abstract Details

2014, Master of Science (MS), Bowling Green State University, Applied Statistics (Math).
Classification and regression trees (CART) have been broadly applied due to their simplicity of explanation, automatic variable selection, visualization and interpretation. Previous algorithms for constructing regression and classification tree models for longitudinal data suffer from the computational difficulties in the estimation of covariance matrix at each node. In this paper, we proposed regression and classification trees for longitudinal data, utilizing the quadratic inference functions (QIF). Following the CART approach and taking the correlation of longitudinal data into consideration, we developed a new criterion, named RSSQ, to select the best splits. The proposed approach could incorporate the correlation between the repeated measurements on the same subject without the estimation of correlation parameters. Therefore, the efficiency of the partition results and prediction accuracy could be improved. Simulation studies and real data examples are provided to illustrate the promise of the proposed approach.
Peng Wang (Advisor)
Hanfeng Chen (Committee Member)
Junfeng Shang (Committee Member)
42 p.
Statistics
Longitudinal data; Classification and regression trees; Quadratic inference functions

Recommended Citations

Citations

  • Liu, D. (2014). Tree-based Models for Longitudinal Data [Master's thesis, Bowling Green State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=bgsu1399972118

    APA Style (7th edition)

  • Liu, Dan. Tree-based Models for Longitudinal Data. 2014. Bowling Green State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=bgsu1399972118.

    MLA Style (8th edition)

  • Liu, Dan. "Tree-based Models for Longitudinal Data." Master's thesis, Bowling Green State University, 2014. http://rave.ohiolink.edu/etdc/view?acc_num=bgsu1399972118

    Chicago Manual of Style (17th edition)

bgsu1399972118
2,419
© 2014, all rights reserved.
This open access ETD is published by Bowling Green State University and OhioLINK.