Description Details Note Author(s) References
Bayesian Spectrum Analysis of time series data
Package: | BaSAR |
Type: | Package |
Version: | 1.1 |
Date: | 2012-01-09 |
Repository: | CRAN |
License: | GPL (>= 2) |
LazyLoad: | yes |
The key function is BaSAR.post
. It computes the normalized posterior probability distribution over a predefined range.
Model comparison can be done for time series with trends.
BaSAR.modelratio
computes the model ratio between two models, and when the ratio is above 1 the simpler model is preferred. The procedure of adding additional background functions to the model until this ratio is above 1 is automated in BaSAR.auto
.
When there are multiple frequencies present in the data, the nested sampling routine, BaSAR.nest
, should be preferred over the functions BaSAR.modelratio
and BaSAR.auto
to compare models. Plot log of posterior probability distribution and visually inspect if there are additional frequencies present.
BaSAR.nest
calculates the evidence for a given model, and a model with a higher evidence should be preferred.
The functions output the posterior over omega (angular frequency). If the user wants to plot over period instead, the function BaSAR.plotperiod
will produce the posterior over period.
Requires the R libraries polynom and orthopolynom, which will be loaded automatically.
Emma Granqvist, Matthew Hartley and Richard J Morris.
Maintainer: Matthew Hartley list("matthew.hartley@jic.ac.uk")
Bretthorst, G. L. (1988) Bayesian spectrum analysis and parameter estimation. Lecture notes in statistics. New York: Springer-Verlag.
Granqvist, E., Oldroyd, G. E. and Morris, R. J. (2011) Automated Bayesian model development for frequency detection in biological time series. BMC Syst Biol 5, 97.
http://dx.doi.org/10.1186/1752-0509-5-97
Sivia, D. S. and Skilling, J. (2006) Data analysis: a Bayesian tutorial. 2nd Edition. Oxford: Oxford science publications. Oxford University Press.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.