org.omegahat.Simulation.MCMC.Proposals
Class AdaptiveKernelProposal
java.lang.Object
|
+--org.omegahat.Simulation.MCMC.Proposals.KernelProposal
|
+--org.omegahat.Simulation.MCMC.Proposals.AdaptiveKernelProposal
- All Implemented Interfaces:
- HastingsCoupledProposal
- Direct Known Subclasses:
- AdaptiveNormalDualKernelProposal, AdaptiveNormalKernelProposal
- public abstract class AdaptiveKernelProposal
- extends KernelProposal
Field Summary |
boolean |
DEBUG
|
Method Summary |
abstract void |
adapt(MultiState mstate,
int which)
modify the state of the enclosed proposal distribution using information from the provided state vector |
double |
conditionalPDF(java.lang.Object state,
java.lang.Object conditions,
int which,
MultiState stateVector)
Computes the HastingsCoupled transition probability for one sub-state given the entire state vector |
java.lang.Object |
generate(java.lang.Object conditionals,
int which,
MultiState stateVector)
Generate a new component state given the entire state vector |
double |
logConditionalPDF(java.lang.Object state,
java.lang.Object conditions,
int which,
MultiState stateVector)
Computes the HastingsCoupled transition probability for one sub-state given the entire state vector |
double |
logTransitionProbability(java.lang.Object from,
java.lang.Object to,
int which,
MultiState stateVector)
Computes the HastingsCoupled transition probability for one sub-state given the entire state vector |
double |
transitionProbability(java.lang.Object from,
java.lang.Object to,
int which,
MultiState stateVector)
Computes the HastingsCoupled transition probability for one sub-state given the entire state vector |
Methods inherited from class java.lang.Object |
, clone, equals, finalize, getClass, hashCode, notify, notifyAll, registerNatives, toString, wait, wait, wait |
DEBUG
public boolean DEBUG
AdaptiveKernelProposal
public AdaptiveKernelProposal()
conditionalPDF
public double conditionalPDF(java.lang.Object state,
java.lang.Object conditions,
int which,
MultiState stateVector)
- Description copied from class:
KernelProposal
- Computes the HastingsCoupled transition probability for one sub-state given the entire state vector
- Overrides:
conditionalPDF
in class KernelProposal
- Following copied from class:
org.omegahat.Simulation.MCMC.Proposals.KernelProposal
- Parameters:
conditions
- Current value of the component state being updatedstate
- Proposed state of the component state being updatedwhich
- index of the component state being updatedstateVector
- entire set of states, including the state being updated
logConditionalPDF
public double logConditionalPDF(java.lang.Object state,
java.lang.Object conditions,
int which,
MultiState stateVector)
- Description copied from class:
KernelProposal
- Computes the HastingsCoupled transition probability for one sub-state given the entire state vector
- Overrides:
logConditionalPDF
in class KernelProposal
- Following copied from class:
org.omegahat.Simulation.MCMC.Proposals.KernelProposal
- Parameters:
conditions
- Current value of the component state being updatedstate
- Proposed state of the component state being updatedwhich
- index of the component state being updatedstateVector
- entire set of states, including the state being updated
generate
public java.lang.Object generate(java.lang.Object conditionals,
int which,
MultiState stateVector)
- Generate a new component state given the entire state vector
- Overrides:
generate
in class KernelProposal
- Parameters:
conditions
- Current value of the component state being updatedwhich
- index of the component state being updatedstateVector
- entire set of states, including the state being updated
transitionProbability
public double transitionProbability(java.lang.Object from,
java.lang.Object to,
int which,
MultiState stateVector)
- Description copied from class:
KernelProposal
- Computes the HastingsCoupled transition probability for one sub-state given the entire state vector
- Overrides:
transitionProbability
in class KernelProposal
- Following copied from class:
org.omegahat.Simulation.MCMC.Proposals.KernelProposal
- Parameters:
from
- Current value of the component state being updatedto
- Proposed state of the component state being updatedwhich
- index of the component state being updatedstateVector
- entire set of states, including the state being updated
logTransitionProbability
public double logTransitionProbability(java.lang.Object from,
java.lang.Object to,
int which,
MultiState stateVector)
- Description copied from class:
KernelProposal
- Computes the HastingsCoupled transition probability for one sub-state given the entire state vector
- Overrides:
logTransitionProbability
in class KernelProposal
- Following copied from class:
org.omegahat.Simulation.MCMC.Proposals.KernelProposal
- Parameters:
from
- Current value of the component state being updatedto
- Proposed state of the component state being updatedwhich
- index of the component state being updatedstateVector
- entire set of states, including the state being updated
adapt
public abstract void adapt(MultiState mstate,
int which)
- modify the state of the enclosed proposal distribution using information from the provided state vector