DiffusionRgqd (version 0.1.2)

GQD.aic: Summarize MLE Selection Output for a List of GQD.mle or BiGQD.mle objects.

Description

GQD.aic() summarizes the MCMC output from a list of GQD.mle() objects. This may be used to neatly summarize the MCMC output of various models fitted to a given dataset.

Usage

GQD.aic(model.list, type = "col")

Arguments

model.list

A list of GQD.mle() objects.

type

Shoould output be of row ('row') or column ('col') format.

Value

A data frame with summary of model output. See Details.

Details

GQD.aic() summarizes the output from various models fitted via GQD.mle(). By ranking them according to DIC. [=] indicates which model has the minimal DIC.

	Convergence	p	min.likelihood	AIC	BIC
N	Model 1	0	5	171.5576	[=] 353.1152
[=] 369.6317	201	Model 2	0	5	185.7518
381.5036	398.0201	201		Convergence	p

References

Updates available on GitHub at https://github.com/eta21.

See Also

GQD.mle

Examples

#===============================================================================
# Simulate a time inhomogeneous diffusion.
#-------------------------------------------------------------------------------

  data(SDEsim1)
  attach(SDEsim1)
  par(mfrow=c(1,1))
  expr1=expression(dX[t]==2*(5+3*sin(0.5*pi*t)-X[t])*dt+0.5*sqrt(X[t])*dW[t])
  plot(Xt~time,type='l',col='blue',xlab='Time (t)',ylab=expression(X[t]),main=expr1)

 #------------------------------------------------------------------------------
 # Define coefficients of the process.
 #------------------------------------------------------------------------------

  GQD.remove()
  G0 <- function(t){theta[1]*(theta[2]+theta[3]*sin(0.25*pi*t))}
  G1 <- function(t){-theta[1]}
  Q0 <- function(t){theta[4]*theta[4]}

  theta.start  <- c(1,1,1,1)                      # Starting values for the chain
  mesh.points  <- 10                              # Number of mesh points

  m1 <- GQD.mle(Xt,time,mesh=mesh.points,theta=theta.start)

  GQD.remove()

  G1 <- function(t){theta[1]*(theta[2]+theta[3]*sin(0.25*pi*t))}
  G2 <- function(t){-theta[1]}
  Q2 <- function(t){theta[4]*theta[4]}

  theta.start  <- c(1,1,1,1)                      # Starting values for the chain
  mesh.points  <- 10                              # Number of mesh points

  m2 <- GQD.mle(Xt,time,mesh=mesh.points,theta=theta.start)

  # Check estimates:
  GQD.estimates(m1)
  GQD.estimates(m2)

  # Compare models:
  GQD.aic(list(m1,m2))

#===============================================================================