Formulating state space models in R with focus on longitudinal regression models

Research output: Book/ReportReportResearch

749 Downloads (Pure)

Abstract

  We provide a language for formulating a range of state space models. The described methodology is implemented in the R -package sspir available from cran.r-project.org . A state space model is specified similarly to a generalized linear model in R , by marking the time-varying terms in the formula. However, the model definition and the model fit are separated in different calls. The model definition creates an object with a number of associated functions. The model object may be edited to incorporate extra features before it is fitted to data. The formulation of models does not depend on the implemented method of inference. The package is demonstrated on three datasets.
Original languageEnglish
Place of PublicationDept. of Mathematical Sciences
PublisherAalborg Universitetsforlag
Number of pages12
Publication statusPublished - 2005
SeriesResearch Report Series
NumberR-2005-21
ISSN1399-2503

Keywords

  • Dynamic models
  • Exponential family
  • Iterated extended Kalman smoothing
  • Kalman filtering

Fingerprint

Dive into the research topics of 'Formulating state space models in R with focus on longitudinal regression models'. Together they form a unique fingerprint.

Cite this