Additive Models for Longitudinal Data with Application to KLIPS

Additive model;Smooth backfitting;Kernel smoothing;Longitudinal data;KLIPS.;519

자연과학대학 통계학과 ;

University:서울대학교 대학원

关键词: Additive model;    Smooth backfitting;    Kernel smoothing;    Longitudinal data;    KLIPS.;    519;   

Others  :  http://s-space.snu.ac.kr/bitstream/10371/131276/1/000000017421.pdf

美国|英语

来源: Seoul National University Open Repository

【 摘 要 】

Many studies have taken to construct models between time-varying variables for longitudinal data. These longitudinal models are widely used in physics, biology and social sciences. In this paper, we introduce a time-varying additive model with smooth backfitting to overcome the limitations of parametric model. This modeling strategy allows us to provide dimension reduction and simultaneously retain flexibility of regression function. Furthermore, an application to Korean Labor and Income Panel Study (KLIPS) data is presented to illustrate the proposed methodologies. This model might be quite useful to fit a data and gives a good explanation on social phenomenon.