Simple State space models in a mixed model framework

State-space models play a central role in time series analysis. Biological time series, which present trend, seasonal, and cyclic fluctuations, can be well described by such models. In addition, biological experiments and surveys often have a relatively complex design structure calling for special a...

Full description

Bibliographic Details
Main Authors: Piepho, Hans-Peter, Ogutu, Joseph O.
Format: Journal Article
Language:Inglés
Published: Informa UK Limited 2007
Subjects:
Online Access:https://hdl.handle.net/10568/1291
_version_ 1855526669114146816
author Piepho, Hans-Peter
Ogutu, Joseph O.
author_browse Ogutu, Joseph O.
Piepho, Hans-Peter
author_facet Piepho, Hans-Peter
Ogutu, Joseph O.
author_sort Piepho, Hans-Peter
collection Repository of Agricultural Research Outputs (CGSpace)
description State-space models play a central role in time series analysis. Biological time series, which present trend, seasonal, and cyclic fluctuations, can be well described by such models. In addition, biological experiments and surveys often have a relatively complex design structure calling for special attention. It is straightforward to account for design effects in a mixed linear model framework. This article shows how simple state-space models can be cast as a standard mixed model, provided the transition matrix of the state equation has a simple form. This opens up the opportunity for refined modeling of time series data involving complex blocking and treatment structures. Conversely, the state-space model gives rise to a special class of variance-covariance structures. Thus, integrating state-space components into a mixed model broadens the class of variance-covariance structures that may be employed to model serial correlation in longitudinal data. The approach is illustrated using several biological examples.
format Journal Article
id CGSpace1291
institution CGIAR Consortium
language Inglés
publishDate 2007
publishDateRange 2007
publishDateSort 2007
publisher Informa UK Limited
publisherStr Informa UK Limited
record_format dspace
spelling CGSpace12912024-04-25T06:01:03Z Simple State space models in a mixed model framework Piepho, Hans-Peter Ogutu, Joseph O. models State-space models play a central role in time series analysis. Biological time series, which present trend, seasonal, and cyclic fluctuations, can be well described by such models. In addition, biological experiments and surveys often have a relatively complex design structure calling for special attention. It is straightforward to account for design effects in a mixed linear model framework. This article shows how simple state-space models can be cast as a standard mixed model, provided the transition matrix of the state equation has a simple form. This opens up the opportunity for refined modeling of time series data involving complex blocking and treatment structures. Conversely, the state-space model gives rise to a special class of variance-covariance structures. Thus, integrating state-space components into a mixed model broadens the class of variance-covariance structures that may be employed to model serial correlation in longitudinal data. The approach is illustrated using several biological examples. 2007-08 2010-04-21T10:56:51Z 2010-04-21T10:56:51Z Journal Article https://hdl.handle.net/10568/1291 en Limited Access Informa UK Limited Piepho, H.P.; Ogutu, J.O. 2007. Simple State space models in a mixed model framework. The American Statistician 61(3): 224-232
spellingShingle models
Piepho, Hans-Peter
Ogutu, Joseph O.
Simple State space models in a mixed model framework
title Simple State space models in a mixed model framework
title_full Simple State space models in a mixed model framework
title_fullStr Simple State space models in a mixed model framework
title_full_unstemmed Simple State space models in a mixed model framework
title_short Simple State space models in a mixed model framework
title_sort simple state space models in a mixed model framework
topic models
url https://hdl.handle.net/10568/1291
work_keys_str_mv AT piephohanspeter simplestatespacemodelsinamixedmodelframework
AT ogutujosepho simplestatespacemodelsinamixedmodelframework