Functional variance estimation using penalized splines with principal component analysis

被引:0
作者
Göran Kauermann
Michael Wegener
机构
[1] University of Bielefeld,Centre for Statistics, Department of Economics
[2] DEKA Investment GmbH,undefined
来源
Statistics and Computing | 2011年 / 21卷
关键词
Functional data analysis; Principal components; Penalized splines; Mixed models;
D O I
暂无
中图分类号
学科分类号
摘要
In many fields of empirical research one is faced with observations arising from a functional process. If so, classical multivariate methods are often not feasible or appropriate to explore the data at hand and functional data analysis is prevailing. In this paper we present a method for joint modeling of mean and variance in longitudinal data using penalized splines. Unlike previous approaches we model both components simultaneously via rich spline bases. Estimation as well as smoothing parameter selection is carried out using a mixed model framework. The resulting smooth covariance structures are then used to perform principal component analysis. We illustrate our approach by several simulations and an application to financial interest data.
引用
收藏
页码:159 / 171
页数:12
相关论文
共 58 条
  • [1] Besse P.(1986)Principal components analysis of sampled functions Psychometrika 51 285-311
  • [2] Ramsay J.O.(1995)Bias correction in generalized linear mixed models with a single component of dispersion Biometrika 82 81-91
  • [3] Breslow N.E.(1998)Smoothing spline models for the analysis of nested and crossed samples of curves (c/r: P976-994) J. Am. Stat. Assoc. 93 961-976
  • [4] Lin X.(2007)Conditional functional principal components analysis Scand. J. Stat. 34 317-335
  • [5] Brumback B.A.(2003)A functional multiplicative effects model for longitudinal data, with application to reproductive histories of female medflies Stat. Sin. 13 1119-1133
  • [6] Rice J.A.(2006)Forecasting the term structure of government bond yields J. Econom. 130 337-364
  • [7] Cardot H.(1996)A yield-factor model of interest rates Math. Finance 6 379-406
  • [8] Chiou J.(1996)Flexible smoothing with B splines and penalties Stat. Sci. 11 89-121
  • [9] Müller H.(2000)Two-step estimation of functional linear models with applications to longitudinal data J. R. Stat. Soc., Ser. B 62 303-322
  • [10] Wang J.(1993)Varying-coefficient models J. R. Stat. Soc., Ser. B 55 757-796