object GibbsSampling
- Alphabetic
- By Inheritance
- GibbsSampling
- AnyRef
- Any
- Hide All
- Show All
- Public
- All
Type Members
- case class State(p: DlmParameters, state: Vector[SamplingState]) extends Product with Serializable
Value Members
-
final
def
!=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
final
def
##(): Int
- Definition Classes
- AnyRef → Any
-
final
def
==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
arlikelihood(state: Vector[SamplingState], p: DlmParameters, phi: DenseVector[Double]): Double
Calculate the marginal likelihood of phi given the values of the latent-state and other static parameters
Calculate the marginal likelihood of phi given the values of the latent-state and other static parameters
- state
a sample of the latent state of an AR(1) DLM
- p
the static parameters of a DLM
- phi
autoregressive
-
final
def
asInstanceOf[T0]: T0
- Definition Classes
- Any
-
def
clone(): AnyRef
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @native() @throws( ... )
-
def
dinvGammaStep(mod: Dlm, priorV: InverseGamma, priorW: InverseGamma, observations: Vector[Data]): (State) ⇒ Rand[State]
A single step of a Gibbs Sampler
A single step of a Gibbs Sampler
- mod
the model containing the definition of the observation matrix F_t and system evolution matrix G_t
- priorV
the prior distribution on the observation noise matrix, V
- priorW
the prior distribution on the system noise matrix, W
- observations
an array of Data containing the observed time series
-
final
def
eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
def
equals(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
-
def
finalize(): Unit
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @throws( classOf[java.lang.Throwable] )
-
final
def
getClass(): Class[_]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
def
gibbsMetropStep(proposal: (DlmParameters) ⇒ Rand[DlmParameters], mod: Dlm, priorV: InverseGamma, priorW: InverseGamma, observations: Vector[Data]): (State) ⇒ Rand[State]
Use metropolis hastings to determine the initial state distribution x0 ~ N(m0, C0)
Use metropolis hastings to determine the initial state distribution x0 ~ N(m0, C0)
- proposal
a proposal distribution for the parameters of the initial state
- mod
a DLM model specification
- priorV
the prior distribution of the observation noise matrix
- priorW
the prior distribution of the system noise matrix
- observations
a vector of observations
-
def
hashCode(): Int
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
-
final
def
isInstanceOf[T0]: Boolean
- Definition Classes
- Any
-
def
likelihood(theta: Vector[SamplingState], g: (Double) ⇒ DenseMatrix[Double])(p: DlmParameters): Double
Calculate the marginal likelihood for metropolis hastings
-
def
metropSamples(proposal: (DlmParameters) ⇒ Rand[DlmParameters], mod: Dlm, priorV: InverseGamma, priorW: InverseGamma, initParams: DlmParameters, observations: Vector[Data]): Process[State]
Use metropolis hastings to determine the initial state distribution x0 ~ N(m0, C0) And Gibbs sampling for the state and observation variance matrices
-
def
metropStep(mod: Dlm, theta: Vector[SamplingState], proposal: (DlmParameters) ⇒ Rand[DlmParameters]): (DlmParameters) ⇒ Rand[DlmParameters]
A metropolis step for a DLM
A metropolis step for a DLM
- mod
a DLM model
- theta
the currently sampled state of the DLM
- proposal
a symmetric proposal distribution for the parameters of a DLM
- returns
a function from Parameters => Rand[Parameters] which performs a metropolis step to be used in a Markov Chain
-
final
def
ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
-
final
def
notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
final
def
notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
-
def
sample(mod: Dlm, priorV: InverseGamma, priorW: InverseGamma, initParams: DlmParameters, observations: Vector[Data]): Process[State]
Return a Markov chain using Gibbs Sampling to determine the values of the system and observation noise covariance matrices, W and V
Return a Markov chain using Gibbs Sampling to determine the values of the system and observation noise covariance matrices, W and V
- mod
the model containing the definition of the observation matrix F_t and system evolution matrix G_t
- priorV
the prior distribution on the observation noise matrix, V
- priorW
the prior distribution on the system noise matrix, W
- initParams
the initial parameters of the Markov Chain
- observations
an array of Data containing the observed time series
- returns
a Process
-
def
sampleObservationMatrix(prior: InverseGamma, f: (Double) ⇒ DenseMatrix[Double], ys: Vector[DenseVector[Option[Double]]], theta: Vector[(Double, DenseVector[Double])]): Rand[DenseMatrix[Double]]
Sample the (diagonal) observation noise covariance matrix from an Inverse Gamma distribution
Sample the (diagonal) observation noise covariance matrix from an Inverse Gamma distribution
- prior
an Inverse Gamma prior distribution for each variance element of the observation matrix
- ys
the observed values of the time series
- theta
a sample of the DLM state
- returns
the posterior distribution over the diagonal observation matrix
-
def
samplePhi(prior: Beta, lambda: Double, tau: Double, s: State): (Double) ⇒ Rand[Double]
Sample the autoregressive parameter with a Beta Prior and proposal distribution
-
def
sampleSvd(mod: Dlm, priorV: InverseGamma, priorW: InverseGamma, initParams: DlmParameters, observations: Vector[Data]): Process[State]
Perform Gibbs Sampling using the SVD Kalman Filter for numerical stability
-
def
sampleSystemMatrix(prior: InverseGamma, theta: Vector[(Double, DenseVector[Double])], g: (Double) ⇒ DenseMatrix[Double]): Rand[DenseMatrix[Double]]
Sample the diagonal system matrix for an irregularly observed DLM
- def stepSvd(mod: Dlm, priorV: InverseGamma, priorW: InverseGamma, observations: Vector[Data]): (State) ⇒ Rand[State]
-
final
def
synchronized[T0](arg0: ⇒ T0): T0
- Definition Classes
- AnyRef
-
def
toString(): String
- Definition Classes
- AnyRef → Any
-
def
updateModel(mod: Dlm, phi: Double*): Dlm
Update an autoregressive model with a new value of the autoregressive parameter
-
final
def
wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws( ... )
-
final
def
wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @native() @throws( ... )