# logdensity.gp: Calculates log prior density of a spectral GP object In spectralGP: Approximate Gaussian Processes Using the Fourier Basis

## Description

Calculates the log prior density of a spectral GP object as the log prior density of the basis coefficients, based on the prior variances and a prior of independent Gaussians.

## Usage

 ```1 2``` ```## S3 method for class 'gp' logdensity(object,...) ```

## Arguments

 `object` A GP object, created by `gp`. `...` Other arguments.

## Details

The log density is calculated based on the real and imaginary components of the basis function coefficients, but only those coefficients that are not determined as the complex conjugates of other coefficients. The density function is that the coefficients are IID normal with mean zero and prior variance based on the spectral density and correlation parameters.

## Value

The logarithm of the prior density.

## Author(s)

Christopher Paciorek [email protected]

## References

Type 'citation("spectralGP")' for references.

`gp`, `propose.coeff.gp`, `calc.variances.gp`
 ```1 2 3 4 5 6 7``` ```library(spectralGP) gp1=gp(128,matern.specdens,c(1,4)) gp2=gp(c(64,64),matern.specdens,c(1,4)) propose.coeff(gp1) propose.coeff(gp2) print(logdensity(gp1)) print(logdensity(gp2)) ```