Non-linear state-space methods for Bayesian time series modelling
State-space methods are used in many fields of science to solve so called filtering, smoothing, prediction and parameter inference problems using multivariate
time series data. Analytical solutions to these inference problems exist mainly for linear Gaussian state-space models and discrete state-space models. Outside
these special cases, the inference is typically based on approximate methods, or simulation-based methods such as particle filters. This thesis develops new methods for Bayesian inference of general state-
space models and applies existing methods in challenging non-linear problems involving multivariate time series data. The new methods presented in this thesis are conditional particle filters that are relevant for the inference of models that involve uninformative initial state distributions and models that have slowly-mixing state dynamics and/or weakly informative observation processes. The
applied problems develop new non-linear state-space models in order to solve a prediction problem related to childhood acute lymphoblastic leukaemia and a filtering problem related to the identification of wolf territories based on presence-only citizen science data.
...
Publisher
Jyväskylän yliopistoISBN
978-951-39-9226-2ISSN Search the Publication Forum
2489-9003Contains publications
- Artikkeli I: Karppinen, S., Lohi, O., & Vihola, M. (2019). Prediction of leukocyte counts during paediatric acute lymphoblastic leukaemia maintenance therapy. Scientific Reports, 9, Article 18076. DOI: 10.1038/s41598-019-54492-5
- Artikkeli II: Karppinen, S., & Vihola, M. (2021). Conditional particle filters with diffuse initial distributions. Statistics and Computing, 31(3), Article 24. DOI: 10.1007/s11222-020-09975-1
- Artikkeli III: Karppinen, S., Rajala, T., Mäntyniemi, S., Kojola, I., & Vihola, M. (2022). Identifying territories using presence-only citizen science data : An application to the Finnish wolf population. Ecological Modelling, 472, Article 110101. DOI: 10.1016/j.ecolmodel.2022.110101
- Artikkeli IV: Karppinen, S., Singh, S.S., and Vihola, M. (2022). Conditional particle filters with bridge backward sampling. Preprint
Metadata
Show full item recordCollections
- JYU Dissertations [775]
- Väitöskirjat [3435]
License
Related items
Showing items with similar title or keywords.
-
Superconductive and insulating inclusions for linear and non-linear conductivity equations
Brander, Tommi; Ilmavirta, Joonas; Kar, Manas (American Institute of Mathematical Sciences, 2018)We detect an inclusion with infinite conductivity from boundary measurements represented by the Dirichlet-to-Neumann map for the conductivity equation. We use both the enclosure method and the probe method. We use the ... -
Linear and non-linear flow mode in Pb–Pb collisions at √sNN = 2.76 TeV
ALICE Collaboration (Elsevier B.V., 2017)The second and the third order anisotropic flow, V2 and V3, are mostly determined by the corresponding initial spatial anisotropy coefficients, ε2 and ε3, in the initial density distribution. In addition to their dependence ... -
Motor skill competence and moderate- and vigorous-intensity physical activity : a linear and non-linear cross-sectional analysis of eight pooled trials
Barnett, L. M.; Verswijveren, S. J. J. M.; Colvin, B.; Lubans, D. R.; Telford, R. M.; Lander, N. J.; Schott, N.; Tietjens, M.; Hesket, K. D.; Morgan, P. J.; Hinkley, T.; Downing, K. L.; Telford, R. D.; Cohen, K. E.; Ridgers, N. D.; Abbott, G. (Biomed Central, 2024)Background Few studies have examined the relationship between motor skill competence and device-measured physical activity in large samples and none have used non-linear modelling. This study assessed the linear and ... -
Efficient Bayesian generalized linear models with time-varying coefficients : The walker package in R
Helske, Jouni (Elsevier BV, 2022)The R package walker extends standard Bayesian general linear models to the case where the effects of the explanatory variables can vary in time. This allows, for example, to model the effects of interventions such as ... -
A linear approach for the nonlinear distributed parameter identification problem
Tai, Xue-Cheng; Neittaanmäki, Pekka (Birkhäuser, 1991)In identifying the nonlinear distributed parameters we propose an approach, which enables us to identify the nonlinear distributed parameters by just solving linear problems. In this approach we just need to identify linear ...