Gaussbound

This is a simple function that computes bounds for a credible interval
according to Gauss's inequality. If a random variable has a Lebesgue density
with a single mode (<code>mode</code>) and a finite expected squared
deviation (<code>tau</code>^2) from this mode,
then Gauss's inequality tells us that at least a
given proportion (<code>prob</code>) of the distribution's mass lies within a
finite symmetric interval centred on the mode.

Computes linear Bayesian spectral estimates from multirate	data for second-order stationary time series. Provides credible intervals and methods for plotting various spectral estimates. Please see the paper `Should we sample a time series more frequently?' (doi below) for a full description of and motivation for the methodology.

Ben Powell

regspec

Non-Parametric Bayesian Spectrum Estimation for Multirate Data

Guy Nason

Gaussbound function

<dl> <dt>mode</dt>
<dd>Numeric. The location of the density's mode.</dd> <dt>tau</dt>
<dd>Numeric. The square root of the expected squared deviation from the mode.</dd> <dt>prob</dt>
<dd>Numeric. A lower bound on the probability mass that is contained within the interval</dd> </dl>

Arguments

Author

Compute the Gauss bounds for a random variable. — Gaussbound

<dl>

 <dt>mode</dt>
<dd>Numeric. The location of the density's mode.</dd>

 <dt>tau</dt>
<dd>Numeric. The square root of the expected squared deviation from the mode.</dd>

 <dt>prob</dt>
<dd>Numeric. A lower bound on the probability mass that is contained within the interval</dd>

 </dl>

Gaussbound: Compute the Gauss bounds for a random variable.

Description

Usage

Value

Arguments

Author

References

Examples