KalmanFilter

Type Members

case class State(time: Double, mt: DenseVector[Double], ct: DenseMatrix[Double], at: DenseVector[Double], rt: DenseMatrix[Double], y: Option[DenseVector[Double]], cov: Option[DenseMatrix[Double]], ll: Double) extends Product with Serializable

State for the Kalman Filter
State for the Kalman Filter
time
the current timestep
mt
the posterior mean of the latent state
ct
the posterior covariance of the latent state
at
the prior mean of the latent state
rt
the prior covariance of the latent state
y
the one step predicted observation mean, not present at the first timestep
cov
the one step predicted observation covariance, not present at the first timestep
ll
the current log-likelihood of all the observations up until the current time

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 advanceState(g: (Double) ⇒ DenseMatrix[Double], mt: DenseVector[Double], ct: DenseMatrix[Double], dt: Double, w: DenseMatrix[Double]): (DenseVector[Double], DenseMatrix[Double])

Advance the state mean and variance to the a-priori value of the state at time t
Advance the state mean and variance to the a-priori value of the state at time t
g
the system matrix, a function from a time increment to DenseMatrix
mt
the a-posteriori mean of the state at time t-1
ct
the a-posteriori covariance of the state at time t-1
dt
the time increment
w
the system noise matrix
returns
the a-priori mean and covariance of the state at time t
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def conditionalLikelihood(ft: DenseVector[Double], qt: DenseMatrix[Double], y: DenseVector[Double]): Double

Calculate the conditional likelihood of the
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def filter(mod: Model, observations: Array[Data], p: Parameters): Array[State]

Run the Kalman Filter over an array of data
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def flattenObs(y: DenseVector[Option[Double]]): DenseVector[Double]

Remove optional data from an observation vector
Remove optional data from an observation vector
y
a vector containing optional observations
returns
a vector containing only the observations which are there
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
def indexNonMissing[A](y: DenseVector[Option[A]]): Array[Int]

Get the index of the non-missing data
Get the index of the non-missing data
y
a vector of observations possibly containing missing data
returns
a vector containing the indices of non-missing observations
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def logLikelihood(mod: Model, observations: Array[Data])(p: Parameters): Double

Calculate the marginal likelihood of a DLM using a kalman filter
def missingF[A](f: (Double) ⇒ DenseMatrix[Double], time: Double, y: DenseVector[Option[A]]): DenseMatrix[Double]

Build observation matrix for potentially missing data
def missingV[A](v: DenseMatrix[Double], y: DenseVector[Option[A]]): DenseMatrix[Double]

Build observation error variance matrix for potentially missing data
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def oneStepMissing(f: (Double) ⇒ DenseMatrix[Double], at: DenseVector[Double], rt: DenseMatrix[Double], time: Double, v: DenseMatrix[Double], y: DenseVector[Option[Double]]): (DenseVector[Double], DenseMatrix[Double])

Perform a one-step prediction taking into account missing data in the observations, this alters the size of the F-matrix
Perform a one-step prediction taking into account missing data in the observations, this alters the size of the F-matrix
f
the observation matrix
at
the a-priori mean state at time t
rt
the a-priori covariance of the state at time t
time
the current time
v
the observation variance
y
the observation at time t
def oneStepPrediction(f: (Double) ⇒ DenseMatrix[Double], at: DenseVector[Double], rt: DenseMatrix[Double], time: Double, v: DenseMatrix[Double]): (DenseVector[Double], DenseMatrix[Double])

Perform a one-step prediction
def step(mod: Model, p: Parameters)(state: State, y: Data): State

Step the Kalman Filter a single Step
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
def updateState(f: (Double) ⇒ DenseMatrix[Double], at: DenseVector[Double], rt: DenseMatrix[Double], d: Data, v: DenseMatrix[Double], ll: Double): (DenseVector[Double], DenseMatrix[Double], DenseVector[Double], DenseMatrix[Double], Double)

Update the state using Joseph Form Update given the newly observed data
Update the state using Joseph Form Update given the newly observed data
f
the observation matrix
at
the a priori state mean at time t
rt
the a priori state variance at time t
d
the actual observation at time t
v
the variance of the measurement noise
ll
the current log-likelihood
returns
the posterior mean and variance of the latent state at time t
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
@throws( ... )

Related Doc: package model

object KalmanFilter

Type Members

case class State(time: Double, mt: DenseVector[Double], ct: DenseMatrix[Double], at: DenseVector[Double], rt: DenseMatrix[Double], y: Option[DenseVector[Double]], cov: Option[DenseMatrix[Double]], ll: Double) extends Product with Serializable

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def advanceState(g: (Double) ⇒ DenseMatrix[Double], mt: DenseVector[Double], ct: DenseMatrix[Double], dt: Double, w: DenseMatrix[Double]): (DenseVector[Double], DenseMatrix[Double])

final def asInstanceOf[T0]: T0

def clone(): AnyRef

def conditionalLikelihood(ft: DenseVector[Double], qt: DenseMatrix[Double], y: DenseVector[Double]): Double

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def filter(mod: Model, observations: Array[Data], p: Parameters): Array[State]

def finalize(): Unit

def flattenObs(y: DenseVector[Option[Double]]): DenseVector[Double]

final def getClass(): Class[_]

def hashCode(): Int

def indexNonMissing[A](y: DenseVector[Option[A]]): Array[Int]

final def isInstanceOf[T0]: Boolean

def logLikelihood(mod: Model, observations: Array[Data])(p: Parameters): Double

def missingF[A](f: (Double) ⇒ DenseMatrix[Double], time: Double, y: DenseVector[Option[A]]): DenseMatrix[Double]

def missingV[A](v: DenseMatrix[Double], y: DenseVector[Option[A]]): DenseMatrix[Double]

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def oneStepMissing(f: (Double) ⇒ DenseMatrix[Double], at: DenseVector[Double], rt: DenseMatrix[Double], time: Double, v: DenseMatrix[Double], y: DenseVector[Option[Double]]): (DenseVector[Double], DenseMatrix[Double])

def oneStepPrediction(f: (Double) ⇒ DenseMatrix[Double], at: DenseVector[Double], rt: DenseMatrix[Double], time: Double, v: DenseMatrix[Double]): (DenseVector[Double], DenseMatrix[Double])

def step(mod: Model, p: Parameters)(state: State, y: Data): State

final def synchronized[T0](arg0: ⇒ T0): T0

def toString(): String

def updateState(f: (Double) ⇒ DenseMatrix[Double], at: DenseVector[Double], rt: DenseMatrix[Double], d: Data, v: DenseMatrix[Double], ll: Double): (DenseVector[Double], DenseMatrix[Double], DenseVector[Double], DenseMatrix[Double], Double)

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from AnyRef

Inherited from Any

Ungrouped