org.omegahat.Simulation.MCMC.Proposals
Class LocallyAdaptiveNormalProposal
java.lang.Object
|
+--org.omegahat.Simulation.MCMC.Proposals.AdaptiveMultiKernelProposal
|
+--org.omegahat.Simulation.MCMC.Proposals.LocallyAdaptiveNormalProposal
- All Implemented Interfaces:
- HastingsCoupledProposal
- public class LocallyAdaptiveNormalProposal
- extends AdaptiveMultiKernelProposal
Constructor Summary |
LocallyAdaptiveNormalProposal(int numStates,
int numNeighbors,
double[][] var,
double inflationFactor,
PRNG prng)
Constructor for normal increments with specified covariance matrix. |
LocallyAdaptiveNormalProposal(int numStates,
int numNeighbors,
double[][] var,
PRNG prng)
Constructor for normal increment proposal with specified
covariance matrix, no variance inflation |
LocallyAdaptiveNormalProposal(int numStates,
int numNeighbors,
int length,
double inflationFactor,
PRNG prng)
Constructor for a spherical independent standard normal increments |
LocallyAdaptiveNormalProposal(int numStates,
int numNeighbors,
int length,
PRNG prng)
Constructor for a sperical independent standard normal increments
No variance inflation. |
Methods inherited from class java.lang.Object |
, clone, equals, finalize, getClass, hashCode, notify, notifyAll, registerNatives, toString, wait, wait, wait |
inflationFactor
protected double inflationFactor
DEBUG
protected boolean DEBUG
numNeighbors
protected int numNeighbors
method
protected int method
LocallyAdaptiveNormalProposal
public LocallyAdaptiveNormalProposal(int numStates,
int numNeighbors,
double[][] var,
PRNG prng)
- Constructor for normal increment proposal with specified
covariance matrix, no variance inflation
- Parameters:
var
- variance matrix
LocallyAdaptiveNormalProposal
public LocallyAdaptiveNormalProposal(int numStates,
int numNeighbors,
double[][] var,
double inflationFactor,
PRNG prng)
- Constructor for normal increments with specified covariance matrix.
- Parameters:
var
- variance matrix
LocallyAdaptiveNormalProposal
public LocallyAdaptiveNormalProposal(int numStates,
int numNeighbors,
int length,
PRNG prng)
- Constructor for a sperical independent standard normal increments
No variance inflation.
- Parameters:
length
- number of dimensions
LocallyAdaptiveNormalProposal
public LocallyAdaptiveNormalProposal(int numStates,
int numNeighbors,
int length,
double inflationFactor,
PRNG prng)
- Constructor for a spherical independent standard normal increments
- Parameters:
length
- number of dimensionsinflationFactor
- factor to inflate observed variance when adaptng.
getInflationFactor
public double getInflationFactor()
setInflationFactor
public double setInflationFactor(double factor)
getDEBUG
public boolean getDEBUG()
setDEBUG
public boolean setDEBUG(boolean flag)
getDistanceMethod
public int getDistanceMethod()
setDistanceMethod
public int setDistanceMethod(int method)
adapt
public void adapt(MultiState mstate,
int which)
- Description copied from class:
AdaptiveMultiKernelProposal
- modify the state of the enclosed proposal distribution using information from the provided state vector
- Overrides:
adapt
in class AdaptiveMultiKernelProposal
main
public static void main(java.lang.String[] argv)