{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T18:01:30Z","timestamp":1791396090929,"version":"4.3.3"},"reference-count":44,"publisher":"Institute of Mathematical Statistics","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ann. Appl. Stat."],"published-print":{"date-parts":[[2024,6,1]]},"abstract":"The adrenocorticotropic hormone and cortisol play critical roles in stress regulation and the sleep-wake cycle. Most research has been focused on how the two hormones regulate each other in terms of short-term pulses. Few studies have been conducted on the circadian relationship between the two hormones and how it differs between normal and abnormal groups. The circadian patterns are difficult to model as parametric functions. Directly extending univariate functional mixed effects models would result in a large dimensional problem and a challenging nonparametric inference. In this article we propose a semiparametric bivariate hierarchical state space model in which each hormone profile is modeled by a hierarchical state space model with nonparametric population-average and subject-specific components. The bivariate relationship is constructed by concatenating two latent independent subject-specific random functions specified by a design matrix, leading to a parametric inference on the correlation. We propose a computationally efficient state-space EM algorithm for estimation and inference. We apply the proposed method to a study of chronic fatigue syndrome and fibromyalgia and discover an erratic regulation pattern in the patient group in contrast to a circadian regulation pattern conforming to the day\u2013night cycle in the control group.<\/jats:p>","DOI":"10.1214\/23-aoas1834","type":"journal-article","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T12:39:51Z","timestamp":1712320791000},"page":"1275-1293","source":"Crossref","is-referenced-by-count":0,"title":["Semiparametric bivariate hierarchical state space model with application to hormone circadian relationship"],"prefix":"10.1214","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4510-5637","authenticated-orcid":false,"given":"Mengying","family":"You","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8892-4309","authenticated-orcid":false,"given":"Wensheng","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"108","reference":[{"key":"33","doi-asserted-by":"publisher","unstructured":"Morris, J. S.<\/small> and Carroll, R. J.<\/small> (2006). Wavelet-based functional mixed models. J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> 68<\/b> 179\u2013199.","DOI":"10.1111\/j.1467-9868.2006.00539.x"},{"key":"19","doi-asserted-by":"publisher","unstructured":"Gu, C.<\/small> (2013). Smoothing Spline ANOVA Models<\/i>, 2nd ed. Springer Series in Statistics<\/i> 297<\/b>. Springer, New York.","DOI":"10.1007\/978-1-4614-5369-7"},{"key":"20","doi-asserted-by":"publisher","unstructured":"Guo, W.<\/small> (2002). Functional mixed effects models. Biometrics<\/i> 58<\/b> 121\u2013128.","DOI":"10.1111\/j.0006-341X.2002.00121.x"},{"key":"36","doi-asserted-by":"publisher","unstructured":"RICE, J. A.<\/small> and WU, C. O.<\/small> (2001). Nonparametric mixed effects models for unequally sampled noisy curves. Biometrics<\/i> 57<\/b> 253\u2013259.","DOI":"10.1111\/j.0006-341X.2001.00253.x"},{"key":"21","doi-asserted-by":"publisher","unstructured":"HAPP, C.<\/small> and GREVEN, S.<\/small> (2018). Multivariate functional principal component analysis for data observed on different (dimensional) domains. J. Amer. Statist. Assoc.<\/i> 113<\/b> 649\u2013659.","DOI":"10.1080\/01621459.2016.1273115"},{"key":"18","doi-asserted-by":"publisher","unstructured":"GOLDSMITH, J.<\/small> and KITAGO, T.<\/small> (2016). Assessing systematic effects of stroke on motor control by using hierarchical function-on-scalar regression. J. R. Stat. Soc. Ser. C. Appl. Stat.<\/i> 65<\/b> 215\u2013236.","DOI":"10.1111\/rssc.12115"},{"key":"32","doi-asserted-by":"crossref","unstructured":"MORRIS, J. S.<\/small> (2015). Functional regression. Annu. Rev. Stat. Appl.<\/i> 2<\/b> 321\u2013359.","DOI":"10.1146\/annurev-statistics-010814-020413"},{"key":"24","doi-asserted-by":"publisher","unstructured":"JAMES, G. M.<\/small>, HASTIE, T. J.<\/small> and SUGAR, C. A.<\/small> (2000). Principal component models for sparse functional data. Biometrika<\/i> 87<\/b> 587\u2013602.","DOI":"10.1093\/biomet\/87.3.587"},{"key":"43","doi-asserted-by":"publisher","unstructured":"ZHOU, L.<\/small>, HUANG, J. Z.<\/small> and CARROLL, R. J.<\/small> (2008). Joint modelling of paired sparse functional data using principal components. Biometrika<\/i> 95<\/b> 601\u2013619.","DOI":"10.1093\/biomet\/asn035"},{"key":"5","doi-asserted-by":"crossref","unstructured":"CHIOU, J.-M.<\/small>, CHEN, Y.-T.<\/small> and YANG, Y.-F.<\/small> (2014). Multivariate functional principal component analysis: A normalization approach. Statist. Sinica<\/i> 24<\/b> 1571\u20131596.","DOI":"10.5705\/ss.2013.305"},{"key":"13","doi-asserted-by":"publisher","unstructured":"DI, C.-Z.<\/small>, CRAINICEANU, C. M.<\/small>, CAFFO, B. S.<\/small> and PUNJABI, N. M.<\/small> (2009). Multilevel functional principal component analysis. Ann. Appl. Stat.<\/i> 3<\/b> 458\u2013488.","DOI":"10.1214\/08-AOAS206"},{"key":"28","doi-asserted-by":"crossref","unstructured":"LI, C.<\/small>, XIAO, L.<\/small> and LUO, S.<\/small> (2020). Fast covariance estimation for multivariate sparse functional data. Stat<\/i> 9<\/b> e245.","DOI":"10.1002\/sta4.245"},{"key":"1","doi-asserted-by":"publisher","unstructured":"ANSLEY, C. F.<\/small>, KOHN, R.<\/small> and WONG, C.-M.<\/small> (1993). Nonparametric spline regression with prior information. Biometrika<\/i> 80<\/b> 75\u201388.","DOI":"10.1093\/biomet\/80.1.75"},{"key":"2","doi-asserted-by":"publisher","unstructured":"ANTONIADIS, A.<\/small> and SAPATINAS, T.<\/small> (2007). Estimation and inference in functional mixed-effects models. Comput. Statist. Data Anal.<\/i> 51<\/b> 4793\u20134813.","DOI":"10.1016\/j.csda.2006.09.038"},{"key":"3","doi-asserted-by":"crossref","unstructured":"BOONEN, E.<\/small>, MEERSSEMAN, P.<\/small>, VERVENNE, H.<\/small>, MEYFROIDT, G.<\/small>, GU\u00cfZA, F.<\/small> and WOUTERS, P. J.<\/small> (2014). Reduced nocturnal ACTH-driven cortisol secretion during critical illness. Amer. J. Physiol<\/i>: Endocrinol. Metab.<\/i> 306<\/b> E883\u2013E892.","DOI":"10.1152\/ajpendo.00009.2014"},{"key":"4","doi-asserted-by":"publisher","unstructured":"CARROLL, C.<\/small>, M\u00dcLLER, H.-G.<\/small> and KNEIP, A.<\/small> (2021). Cross-component registration for multivariate functional data, with application to growth curves. Biometrics<\/i> 77<\/b> 839\u2013851.","DOI":"10.1111\/biom.13340"},{"key":"6","doi-asserted-by":"publisher","unstructured":"CHIOU, J.-M.<\/small> and M\u00dcLLER, H.-G.<\/small> (2016). A pairwise interaction model for multivariate functional and longitudinal data. Biometrika<\/i> 103<\/b> 377\u2013396.","DOI":"10.1093\/biomet\/asw007"},{"key":"7","doi-asserted-by":"publisher","unstructured":"CRAINICEANU, C. M.<\/small>, STAICU, A.-M.<\/small>, RAY, S.<\/small> and PUNJABI, N.<\/small> (2012). Bootstrap-based inference on the difference in the means of two correlated functional processes. Stat. Med.<\/i> 31<\/b> 3223\u20133240.","DOI":"10.1002\/sim.5439"},{"key":"8","unstructured":"CROFFORD, L. J.<\/small> (2015). Chronic pain: Where the body meets the brain. Trans. Amer. Clin. Climatol. Assoc.<\/i> 126<\/b> 167\u2013183."},{"key":"9","doi-asserted-by":"publisher","unstructured":"CROFFORD, L. J.<\/small>, YOUNG, E. A.<\/small>, ENGLEBERG, N. C.<\/small>, KORSZUN, A.<\/small>, BRUCKSCH, C. B.<\/small>, MCCLURE, L. A.<\/small>, BROWN, M. B.<\/small> and DEMITRACK, M. A.<\/small> (2004). Basal circadian and pulsatile ACTH and cortisol secretion in patients with fibromyalgia and\/or chronic fatigue syndrome. Brain Behav. Immun.<\/i> 18<\/b> 314\u2013325.","DOI":"10.1016\/j.bbi.2003.12.011"},{"key":"10","doi-asserted-by":"crossref","unstructured":"CZEISLER, C. A.<\/small> and WATERHOUSE, J. M.<\/small> (1995). The effect of light on the human circadian pacemaker. Circadian Clocks and Their Adjust.<\/i> 183<\/b> 254\u2013290.","DOI":"10.1002\/9780470514597.ch14"},{"key":"11","unstructured":"DALLMAN, M. F.<\/small>, STRACK, A. M.<\/small>, AKANA, S. F.<\/small>, BRADBURY, M. J.<\/small>, HANSON, E. S.<\/small>, SCRIBNER, K. A.<\/small> and SMITH, M.<\/small> (1993). Feast and famine: Critical role of glucocorticoids with insulin in daily energy flow. Front. Neuroendocrinol.<\/i> 14<\/b> 303\u2013347."},{"key":"12","doi-asserted-by":"crossref","unstructured":"DE JONG, P.<\/small> (1989). Smoothing and interpolation with the state-space model. J. Amer. Statist. Assoc.<\/i> 84<\/b> 1085\u20131088.","DOI":"10.1080\/01621459.1989.10478876"},{"key":"14","doi-asserted-by":"publisher","unstructured":"DUBIN, J. A.<\/small> and M\u00dcLLER, H.-G.<\/small> (2005). Dynamical correlation for multivariate longitudinal data. J. Amer. Statist. Assoc.<\/i> 100<\/b> 872\u2013881.","DOI":"10.1198\/016214504000001989"},{"key":"15","doi-asserted-by":"publisher","unstructured":"DUMBELL, R.<\/small>, MATVEEVA, O.<\/small> and OSTER, H.<\/small> (2016). Circadian clocks, stress, and immunity. Front. Endocrinol.<\/i> 7<\/b> 37.","DOI":"10.3389\/fendo.2016.00037"},{"key":"16","doi-asserted-by":"crossref","unstructured":"ENGLER, D.<\/small>, PHAM, T.<\/small>, LIU, J.-P.<\/small>, FULLERTON, M. J.<\/small>, CLARKE, I. J.<\/small> and FUNDER, J. W.<\/small> (1990). Studies of the regulation of the hypothalamic-pituitary-adrenal axis in sheep with hypothalamic-pituitary disconnection. II. Evidence for in vivo ultradian hypersecretion of proopiomelanocortin peptides by the isolated anterior and intermediate pituitary. Endocrinology<\/i> 127<\/b> 1956\u20131966.","DOI":"10.1210\/endo-127-4-1956"},{"key":"17","doi-asserted-by":"crossref","unstructured":"FOCKE, C. M. B.<\/small> and IREMONGER, K. J.<\/small> (2020). Rhythmicity matters: Circadian and ultradian patterns of HPA axis activity. Mol. Cell. Endocrinol.<\/i> 501<\/b> 110652.","DOI":"10.1016\/j.mce.2019.110652"},{"key":"22","doi-asserted-by":"publisher","unstructured":"HE, G.<\/small>, M\u00dcLLER, H.-G.<\/small> and WANG, J.-L.<\/small> (2003). Functional canonical analysis for square integrable stochastic processes. J. Multivariate Anal.<\/i> 85<\/b> 54\u201377.","DOI":"10.1016\/S0047-259X(02)00056-8"},{"key":"23","unstructured":"HE, J.<\/small> (2014). Functional correlations to quantify functional connectivity in brain imaging. ProQuest LLC, Ann Arbor, MI. Thesis (Ph.D.)\u2014Univ. California, Davis."},{"key":"25","doi-asserted-by":"publisher","unstructured":"KOOPMAN, S. J.<\/small> and DURBIN, J.<\/small> (2000). Fast filtering and smoothing for multivariate state space models. J. Time Series Anal.<\/i> 21<\/b> 281\u2013296.","DOI":"10.1111\/1467-9892.00186"},{"key":"26","doi-asserted-by":"publisher","unstructured":"LAI, T.<\/small>, ZHANG, Z.<\/small>, WANG, Y.<\/small> and KONG, L.<\/small> (2021). Testing independence of functional variables by angle covariance. J. Multivariate Anal.<\/i> 182<\/b> Paper No. 104711.","DOI":"10.1016\/j.jmva.2020.104711"},{"key":"27","doi-asserted-by":"crossref","unstructured":"LEURGANS, S. E.<\/small>, MOYEED, R. A.<\/small> and SILVERMAN, B. W.<\/small> (1993). Canonical correlation analysis when the data are curves. J. Roy. Statist. Soc. Ser. B<\/i> 55<\/b> 725\u2013740.","DOI":"10.1111\/j.2517-6161.1993.tb01936.x"},{"key":"29","doi-asserted-by":"crossref","unstructured":"LIGHTMAN, S. L.<\/small>, BIRNIE, M. T.<\/small> and CONWAY-CAMPBELL, B. L.<\/small> (2020). Dynamics of ACTH and cortisol secretion and implications for disease. Endocr. Rev.<\/i> 41<\/b> 470\u2013490.","DOI":"10.1210\/endrev\/bnaa002"},{"key":"30","doi-asserted-by":"publisher","unstructured":"LIU, Z.<\/small>, CAPPOLA, A. R.<\/small>, CROFFORD, L. J.<\/small> and GUO, W.<\/small> (2014). Modeling bivariate longitudinal hormone profiles by hierarchical state space models. J. Amer. Statist. Assoc.<\/i> 109<\/b> 108\u2013118.","DOI":"10.1080\/01621459.2013.830071"},{"key":"31","doi-asserted-by":"crossref","unstructured":"LIU, Z.<\/small> and GUO, W.<\/small> (2012). Functional mixed effects models. Wiley Interdiscip. Rev<\/i>.: Comput. Stat.<\/i> 4<\/b> 527\u2013534.","DOI":"10.1002\/wics.1226"},{"key":"34","unstructured":"QIN, L.<\/small> (2004). Functional models using smoothing splines, a state space approach. Dissertation, Univ. Pennsylvania."},{"key":"35","doi-asserted-by":"crossref","unstructured":"QIN, L.<\/small> and GUO, W.<\/small> (2006). Functional mixed-effects model for periodic data. Biostatistics<\/i> 7<\/b> 225\u2013234.","DOI":"10.1093\/biostatistics\/kxj003"},{"key":"37","doi-asserted-by":"publisher","unstructured":"SANG, P.<\/small>, WANG, L.<\/small> and CAO, J.<\/small> (2019). Weighted empirical likelihood inference for dynamical correlations. Comput. Statist. Data Anal.<\/i> 131<\/b> 194\u2013206.","DOI":"10.1016\/j.csda.2018.07.003"},{"key":"38","doi-asserted-by":"publisher","unstructured":"SHUMWAY, R. H.<\/small> and STOFFER, D. S.<\/small> (1982). An approach to time series smoothing and forecasting using the EM algorithm. Journal of time series analysis<\/i>. 3<\/b> 253\u2013264.","DOI":"10.1111\/j.1467-9892.1982.tb00349.x"},{"key":"39","doi-asserted-by":"crossref","unstructured":"VELDHUIS, J. D.<\/small>, IRANMANESH, A.<\/small>, NAFTOLOWITZ, D.<\/small>, TATHAM, N.<\/small>, CASSIDY, F.<\/small> and CARROLL, B. J.<\/small> (2001). Corticotropin secretory dynamics in humans under low glucocorticoid feedback. J. Clin. Endocrinol. Metab.<\/i> 86<\/b> 5554\u20135563.","DOI":"10.1210\/jcem.86.11.8046"},{"key":"40","doi-asserted-by":"publisher","unstructured":"VOLKMANN, A.<\/small>, ST\u00d6CKER, A.<\/small>, SCHEIPL, F.<\/small> and GREVEN, S.<\/small> (2021). Multivariate functional additive mixed models. Stat. Model.<\/i> 23<\/b> 303\u2013326.","DOI":"10.1177\/1471082X211056158"},{"key":"41","doi-asserted-by":"crossref","unstructured":"YOU, M.<\/small> and GUO, W.<\/small> (2024). Supplement to \u201cSemiparametric bivariate hierarchical state space model with application to hormone circadian relationship.\u201d https:\/\/doi.org\/10.1214\/23-AOAS1834SUPP<\/a>","DOI":"10.1214\/23-AOAS1834SUPP"},{"key":"42","doi-asserted-by":"crossref","unstructured":"YOUNG, E. A.<\/small>, CARLSON, N. E.<\/small> and BROWN, M. B.<\/small> (2001). Twenty-four-hour ACTH and cortisol pulsatility in depressed women. Neuropsychopharmacology<\/i> 25<\/b> 267\u2013276.","DOI":"10.1016\/S0893-133X(00)00236-0"},{"key":"44","doi-asserted-by":"publisher","unstructured":"ZHOU, Y.<\/small>, LIN, S.-C.<\/small> and WANG, J.-L.<\/small> (2018). Local and global temporal correlations for longitudinal data. J. Multivariate Anal.<\/i> 167<\/b> 1\u201314.","DOI":"10.1016\/j.jmva.2018.03.015"}],"container-title":["The Annals of Applied Statistics"],"original-title":[],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T17:38:36Z","timestamp":1791394716000},"score":1,"resource":{"primary":{"URL":"https:\/\/projecteuclid.org\/journals\/annals-of-applied-statistics\/volume-18\/issue-2\/Semiparametric-bivariate-hierarchical-state-space-model-with-application-to-hormone\/10.1214\/23-AOAS1834.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,1]]},"references-count":44,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1214\/23-aoas1834","relation":{},"ISSN":["1932-6157","1941-7330"],"issn-type":[{"value":"1932-6157","type":"print"},{"value":"1941-7330","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,1]]}}}