Three-way component analysis with smoothness constraints

被引:24
作者
Timmerman, ME [1 ]
Kiers, HAL [1 ]
机构
[1] Univ Groningen, DPMG, Heymans Inst Psychol, NL-9712 TS Groningen, Netherlands
关键词
three-way data; longitudinal data; splines; smoother;
D O I
10.1016/S0167-9473(02)00059-2
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Tucker3 Analysis and CANDECOMP/PARAFAC (CP) are closely related methods for three-way component analysis. Imposing constraints on the Tucker3 or CP solutions can be useful to improve estimation of the model parameters. In the present paper, a method is proposed for applying smoothness constraints on Tucker3 or CP solutions, which is particularly useful in analysing functional three-way data. The usefulness of smoothness constraints on Tucker3 and CP solutions is examined by means of a simulation experiment. Generally, the results of the experiments indicate better estimations of the model parameters. An empirical example illustrates the use of smoothness constraints. The constrained model is more stable and easier to interpret than the unconstrained model. (C) 2002 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:447 / 470
页数:24
相关论文
共 34 条
[1]   COMPRESSION OF NTH-ORDER DATA ARRAYS BY B-SPLINES .1. THEORY [J].
ALSBERG, BK ;
KVALHEIM, OM .
JOURNAL OF CHEMOMETRICS, 1993, 7 (01) :61-73
[2]   Improving the speed of multi-way algorithms: Part I. Tucker3 [J].
Andersson, CA ;
Bro, R .
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1998, 42 (1-2) :93-103
[3]  
Bro R., 1998, Multi-way Analysis in the Food Industry
[4]  
BRO R, 2001, UNPUB CENTERING SCAL
[5]   ALTERNATIVE WAYS OF ASSESSING MODEL FIT [J].
BROWNE, MW ;
CUDECK, R .
SOCIOLOGICAL METHODS & RESEARCH, 1992, 21 (02) :230-258
[6]  
BUS AG, 1982, SOL8208 U GRON DEP E
[7]  
CARROLL JD, 1980, PSYCHOMETRIKA, V45, P3
[8]   ANALYSIS OF INDIVIDUAL DIFFERENCES IN MULTIDIMENSIONAL SCALING VIA AN N-WAY GENERALIZATION OF ECKART-YOUNG DECOMPOSITION [J].
CARROLL, JD ;
CHANG, JJ .
PSYCHOMETRIKA, 1970, 35 (03) :283-&
[9]  
de Boor C., 1978, PRACTICAL GUIDE SPLI
[10]  
Golub G. H., 2013, Matrix Computations