Bayesian model selection with fractional Brownian motion

Jens F. C. Krog, Lars Hervig Jacobsen, Frederik Wendelboe Lund, Daniel Wüstner, Michael Andersen Lomholt

Research output: Contribution to journalJournal articleResearchpeer-review

111 Downloads (Pure)

Abstract

We implement Bayesian model selection and parameter estimation for the case of fractional Brownian motion with measurement noise and a constant drift. The approach is tested on artificial trajectories and shown to make estimates that match well with the underlying true parameters, while for model selection the approach has a preference for simple models when the trajectories are finite. The approach is applied to observed trajectories of vesicles diffusing in Chinese hamster ovary cells. Here it is supplemented with a goodness-of-fit test, which is able to reveal statistical discrepancies between the observed trajectories and model predictions.
Original languageEnglish
Article number093501
JournalJournal of Statistical Mechanics: Theory and Experiment
Volume2018
Issue number9
Number of pages23
ISSN1742-5468
DOIs
Publication statusPublished - 18. Sep 2018

Fingerprint

Bayesian Model Selection
Fractional Brownian Motion
trajectories
Trajectory
goodness of fit
ovaries
Ovary
hamsters
Vesicles
Goodness of Fit Test
noise measurement
Model Selection
Prediction Model
Discrepancy
Parameter Estimation
Fractional Brownian motion
Model selection
Bayesian model
Cell
estimates

Keywords

  • Brownian motion
  • statistical inference in biological systems
  • stochastic processes

Cite this

@article{391279a027cc4e919e0d996454913351,
title = "Bayesian model selection with fractional Brownian motion",
abstract = "We implement Bayesian model selection and parameter estimation for the case of fractional Brownian motion with measurement noise and a constant drift. The approach is tested on artificial trajectories and shown to make estimates that match well with the underlying true parameters, while for model selection the approach has a preference for simple models when the trajectories are finite. The approach is applied to observed trajectories of vesicles diffusing in Chinese hamster ovary cells. Here it is supplemented with a goodness-of-fit test, which is able to reveal statistical discrepancies between the observed trajectories and model predictions.",
keywords = "Brownian motion, statistical inference in biological systems, stochastic processes",
author = "Krog, {Jens F. C.} and {Hervig Jacobsen}, Lars and Lund, {Frederik Wendelboe} and Daniel W{\"u}stner and Lomholt, {Michael Andersen}",
year = "2018",
month = "9",
day = "18",
doi = "10.1088/1742-5468/aadb0e",
language = "English",
volume = "2018",
journal = "Journal of Statistical Mechanics: Theory and Experiment",
issn = "1742-5468",
publisher = "IOP Publishing",
number = "9",

}

Bayesian model selection with fractional Brownian motion. / Krog, Jens F. C. ; Hervig Jacobsen, Lars; Lund, Frederik Wendelboe; Wüstner, Daniel; Lomholt, Michael Andersen.

In: Journal of Statistical Mechanics: Theory and Experiment, Vol. 2018, No. 9, 093501, 18.09.2018.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Bayesian model selection with fractional Brownian motion

AU - Krog, Jens F. C.

AU - Hervig Jacobsen, Lars

AU - Lund, Frederik Wendelboe

AU - Wüstner, Daniel

AU - Lomholt, Michael Andersen

PY - 2018/9/18

Y1 - 2018/9/18

N2 - We implement Bayesian model selection and parameter estimation for the case of fractional Brownian motion with measurement noise and a constant drift. The approach is tested on artificial trajectories and shown to make estimates that match well with the underlying true parameters, while for model selection the approach has a preference for simple models when the trajectories are finite. The approach is applied to observed trajectories of vesicles diffusing in Chinese hamster ovary cells. Here it is supplemented with a goodness-of-fit test, which is able to reveal statistical discrepancies between the observed trajectories and model predictions.

AB - We implement Bayesian model selection and parameter estimation for the case of fractional Brownian motion with measurement noise and a constant drift. The approach is tested on artificial trajectories and shown to make estimates that match well with the underlying true parameters, while for model selection the approach has a preference for simple models when the trajectories are finite. The approach is applied to observed trajectories of vesicles diffusing in Chinese hamster ovary cells. Here it is supplemented with a goodness-of-fit test, which is able to reveal statistical discrepancies between the observed trajectories and model predictions.

KW - Brownian motion

KW - statistical inference in biological systems

KW - stochastic processes

U2 - 10.1088/1742-5468/aadb0e

DO - 10.1088/1742-5468/aadb0e

M3 - Journal article

VL - 2018

JO - Journal of Statistical Mechanics: Theory and Experiment

JF - Journal of Statistical Mechanics: Theory and Experiment

SN - 1742-5468

IS - 9

M1 - 093501

ER -