FPCA-based method to select optimal sampling schedules that capture between-subject variability in longitudinal studies. (English) Zbl 1415.62143

Summary: A critical component of longitudinal study design involves determining the sampling schedule. Criteria for optimal design often focus on accurate estimation of the mean profile, although capturing the between-subject variance of the longitudinal process is also important since variance patterns may be associated with covariates of interest or predict future outcomes. Existing design approaches have limited applicability when one wishes to optimize sampling schedules to capture between-individual variability. We propose an approach to derive optimal sampling schedules based on functional principal component analysis (FPCA), which separately characterizes the mean and the variability of longitudinal profiles and leads to a parsimonious representation of the temporal pattern of the variability. Simulation studies show that the new design approach performs equally well compared to an existing approach based on parametric mixed model (PMM) when a PMM is adequate for the data, and outperforms the PMM-based approach otherwise. We use the methods to design studies aiming to characterize daily salivary cortisol profiles and identify the optimal days within the menstrual cycle when urinary progesterone should be measured.


62P10 Applications of statistics to biology and medical sciences; meta analysis
62K05 Optimal statistical designs
62D05 Sampling theory, sample surveys
62H11 Directional data; spatial statistics


optitxs; fda (R); nlme
Full Text: DOI Link


[1] Adam, E. K. and Kumari, M. (2009). Assessing salivary cortisol in large‐scale, epidemiological research. {\it Psychoneuroendocrinology}34, 1423-1436.
[2] Atkinson, A. C., Donev, A. N., and Tobias, R. (2007). {\it Optimum Experimental Designs, with SAS}. Oxford, UK: Oxford University Press. · Zbl 1183.62129
[3] Basagaña, X. and Spiegelman, D. (2010). Power and sample size calculations for longitudinal studies comparing rates of change with a time‐varying exposure. {\it Statistics in Medicine}29, 181-192.
[4] Bazzoli, C., Retout, S., and Mentré, F. (2009). Fisher information matrix for nonlinear mixed effects multiple response models: Evaluation of the appropriateness of the first order linearization using a pharmacokinetic/pharmacodynamic model. {\it Statistics in Medicine}28, 1940-1956.
[5] Brumback, B. A. and Rice, J. A. (1998). Smoothing spline models for the analysis of nested and crossed samples of curves. {\it Journal of the American Statistical Association}93, 961-976. · Zbl 1064.62515
[6] Carroll, R. J. (2003). Variances are not always nuisance parameters. {\it Biometrics}59, 211-220. · Zbl 1210.62147
[7] Davidian, M., Carroll, R. J., and Smith, W. (1988). Variance functions and the minimum detectable concentration in assays. {\it Biometrika}75, 549-556. · Zbl 0651.62100
[8] De Souza, M., Toombs, R., Scheid, J., O’Donnell, E., West, S., and Williams, N. (2010). High prevalence of subtle and severe menstrual disturbances in exercising women: Confirmation using daily hormone measures. {\it Human Reproduction}25, 491-503.
[9] Elliott, M. R. (2007). Identifying latent clusters of variability in longitudinal data. {\it Biostatistics}8, 756-771. · Zbl 1267.62058
[10] Fedorov, V. V. and Hackl, P. (1997). {\it Model‐Oriented Design of Experiments}. New York: Springer. · Zbl 0878.62052
[11] Hajat, A., Diez‐Roux, A., Franklin, T. G., Seeman, T., Shrager, S., Ranjit, N., et al. (2010). Socioeconomic and race/ethnic differences in daily salivary cortisol profiles: The multi‐ethnic study of atherosclerosis. {\it Psychoneuroendocrinology}35, 932-943.
[12] Hastings, W. K. (1970). Monte Carlo sampling methods using Markov chains and their applications. {\it Biometrika}57, 97-109. · Zbl 0219.65008
[13] James, G. M., Hastie, T. J., and Sugar, C. A. (2000). Principal component models for sparse functional data. {\it Biometrika}87, 587-602. · Zbl 0962.62056
[14] Ji, H. and Müller, H. G. (2017). Optimal designs for longitudinal and functional data. {\it Journal of the Royal Statistical Society, Series B}79, 859-876. · Zbl 1411.62231
[15] Johnson, R. A. and Wichern, D. W. (2007). {\it Applied Multivariate Statistical Analysis}. NJ: Pearson Prentice Hall. · Zbl 1269.62044
[16] Mentré, F. M. and Baccar, D. (1997). Optimal design in random‐effects regression models. {\it Biometrika}84, 429-442. · Zbl 0882.62069
[17] Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H., and Teller, E. (1953). Equation of state calculations by fast computing machines. {\it The Journal of Chemical Physics}21, 1087-1092.
[18] Ogungbenro, K., Graham, G., Gueorguieva, I., and Aarons, L. (2005). The use of a modified Fedorov exchange algorithm to optimise sampling times for population pharmacokinetic experiments. {\it Computer Methods and Programs in Biomedicine}80, 115-125.
[19] Pinheiro, J., Bates, D., DebRoy, S., Sarkar, D., and R Core Team (2015). {\it nlme: Linear and Nonlinear Mixed Effects Models}. R package version 3.1.
[20] Ramsay, J. and Silverman, B. (2005). {\it Functional Data Analysis}, 2nd edition, New York: Springer. · Zbl 1079.62006
[21] Raudenbush, S. W. and Liu, X. (2000). Statistical power and optimal design for multisite randomized trials. {\it Psychological Methods}5, 199-213.
[22] Retout, S., Mentré, F., and Bruno, R. (2002). Fisher information matrix for non‐linear mixed‐effects models: evaluation and application for optimal design of enoxaparin population pharmacokinetics. {\it Statistics in Medicine}21, 2623-2639.
[23] Retout, S., Comets, E., Samson, A., and Mentré, F. (2007). Design in nonlinear mixed effects models: Optimization using the Fedorov‐Wynn algorithm and power of the Wald test for binary covariates. {\it Statistics in Medicine}26, 5162-5179.
[24] Stroud, J. R., Müller, P., and Rosner, G. L. (2001). Optimal sampling times in population pharmacokinetic studies. {\it Journal of the Royal Statistical Society, Series C}50, 345-359. · Zbl 1112.62310
[25] Stroud, L. R., Papandonatos, G. D., Williamson, D. E., and Dahl, R. E. (2004). Applying a nonlinear regression model to characterize cortisol responses to corticotropin‐releasing hormone challenge. {\it Annals of the New York Academy of Sciences}1032, 264-266.
[26] Waller, K., Swan, S. H., Windham, G. C., Fenster, L., Elkin, E. P., and Lasley, B. L. (1998). Use of urine biomarkers to evaluate menstrual function in healthy premenopausal women. {\it American Journal of Epidemiology}147, 1071-1080.
[27] Zhou, L., Huang, J. Z., and Carroll, R. J. (2008). Joint modelling of paired sparse functional data using principal components. {\it Biometrika}95, 601-619. · Zbl 1437.62676
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.