Analysis of growth curve data by using cubic smoothing splines. (English) Zbl 1147.62051

Summary: Longitudinal data frequently arise in various fields of applied sciences where individuals are measured according to some ordered variable, e.g., time. A common approach used to model such data is based on the mixed models for repeated measures. This model provides an eminently flexible approach to modeling of a wide range of mean and covariance structures. However, such models are forced into a rigidly defined class of mathematical formulas which may not be well supported by the data within the whole sequence of observations.
A possible nonparametric alternative is a cubic smoothing spline, which is highly flexible and has useful smoothing properties. It can be shown that under normality assumptions, the solution of the penalized log-likelihood equation is the cubic smoothing spline, and this solution can be further expressed as a solution of a linear mixed model. It is shown here how cubic smoothing splines can be easily used in the analysis of complete and balanced data. The analysis can be greatly simplified by using the unweighted estimator studied in the paper. It is shown that if the covariance structure of the random errors belongs to a certain class of matrices, the unweighted estimator is the solution to the penalized log-likelihood function. This result is new in a smoothing spline context and it is not only confined to growth curve settings. The connection to mixed models is used in developing a rough testing of group profiles. Numerical examples are presented to illustrate the techniques proposed.


62H12 Estimation in multivariate analysis
62G05 Nonparametric estimation
65C60 Computational problems in statistics (MSC2010)
62H15 Hypothesis testing in multivariate analysis
Full Text: DOI


[1] Green P. J., Nonparametric Regression and Generalized Linear Models (1994) · Zbl 0832.62032
[2] Harville D. A., Matrix Algebra From A Statistician’s Perspective (1997) · Zbl 0881.15001
[3] Hastie T., The Elements of Statistical Learning (2001) · Zbl 0973.62007
[4] DOI: 10.2307/2529876 · Zbl 0512.62107
[5] DOI: 10.1016/0378-3758(94)00127-H · Zbl 0832.62067
[6] DOI: 10.1080/00949650310001623416 · Zbl 1153.62320
[7] DOI: 10.1007/s001840000063 · Zbl 1093.62545
[8] Nummi, T. and Möttönen, J. Prediction of stem characteristics for a forest harvester, in. Proceedings of Woodfor Africa 2002 Forest Engineering Conferenc, pp.133–140. Corvallis): Oregon State University.
[9] DOI: 10.1080/0266476032000148975 · Zbl 1046.62121
[10] Pan J., Growth Curve Models and Statistical Diagnostics (2002) · Zbl 1024.62025
[11] Potthoff R. F., Biometrika 5 pp 313– (1964) · Zbl 0138.14306
[12] DOI: 10.2307/2685062
[13] DOI: 10.1007/BF02162161 · Zbl 0161.36203
[14] Silverman B. W., J. R. Stat. Soc. B 47 pp 1– (1985)
[15] Speed T. P., Statis. Sci. 6 pp 44– (1991)
[16] Stone M., J. R. Stat. Soc. B 36 pp 111– (1974)
[17] Verbyla A. P., Applied Statistics 48 pp 269– (1999)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.