BaSAR.auto: BSA automatic model comparison

In JIC-CSB/BaSAR: Bayesian Spectrum Analysis in R

Description

Function for automated model comparison which stops adding background functions when model ratio > 1.

Usage

BaSAR.auto(data, start, stop, nsamples, nbackg, tpoints)

Arguments

data	data as a 1-dimensional vector
start	lower limit of period of interest, in seconds
stop	upper limit of period of interest, in seconds
nsamples	number of samples within the interval start-stop
nbackg	number of background functions to be added to the model
tpoints	vector of time points, in seconds

Details

This is a wrapper function that uses BaSAR.modelratio, and automatically adds more background functions until the model ratio is > 1, or the maximum number of background functions (nbackg) has been reached. It will warn if the max was reached first, instead of the modelratio goal.

Plot log of posterior probability distribution and visually inspect if there are additional frequencies present. If there are, BaSAR.nest should be used instead for model comparison.

Value

A list containing:

normp	1D normalized posterior distribution over omega
omega	1D vector of the omega sampled
stats	list of statistics from the probability distribution
modelratio	final model ratio
model	no of background functions added to the model

Author(s)

Emma Granqvist, Matthew Hartley and Richard J Morris.

References

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

Bretthorst, G. L. (1988) Bayesian spectrum analysis and parameter estimation. Lecture notes in statistics. New York: Springer-Verlag.

See Also

BaSAR.modelratio, BaSAR.post

Examples

require(polynom)
require(orthopolynom)
# Create time series with omega = 0.5 and a background trend
tpoints = seq(from=1, to=200, length=200)
dpoints = sin(0.5 * tpoints) - tpoints ^ 2 * 0.005 + 0.1 * rnorm(200, 0, 1)
# Plot time series
plot(dpoints, type="l", col="blue", xlab="t", ylab="d(t)")
# Run BaSAR with automated model selection for background trends
# up to a max of 4 background functions in this example
r = BaSAR.auto(dpoints, 6, 600, 100, 4, tpoints)
# Plot the resulting posterior density function, and check which model was selected
plot(r$omega, r$normp, xlim=c(0:1), type="h", col="red", ylab="PDF",
xlab=expression(omega))

JIC-CSB/BaSAR documentation built on May 21, 2019, 1:41 p.m.