Package 'rjd3sts' reference manual

Title:	State Space Framework and Structural Time Series with 'JDemetra+ 3.x'
Description:	R Interface to 'JDemetra+ 3.x' (<https://github.com/jdemetra>) time series analysis software. It offers access to several functions on state space models and structural time series.
Authors:	Jean Palate [aut, cre], Tanguy Barthelemy [art]
Maintainer:	Jean Palate <[email protected]>
License:	file LICENSE
Version:	2.4.1.9000
Built:	2026-05-08 09:20:24 UTC
Source:	https://github.com/rjdverse/rjd3sts

Creates the state space form of an airline model;

Description

Creates the state space form of an airline model;

Usage

.airline(period = 12, theta = -0.6, btheta = -0.8)
.airline(period = 12, theta = -0.6, btheta = -0.8)

Arguments

period

Period of the model.

theta

Regular moving average parameter.

btheta

Seasonal moving average parameter.

Value

The raw state space form of the Airline model.

Examples

ssf<-.airline(24)
.dk_likelihood(ssf, rjd3toolkit::ABS$X0.2.09.10.M)
ssf<-.airline(24)
.dk_likelihood(ssf, rjd3toolkit::ABS$X0.2.09.10.M)

Computes the diffuse likelihood by means of the augmented Kalman filter.

Description

Computes the diffuse likelihood by means of the augmented Kalman filter.

Usage

.akf_likelihood(
  ssf,
  data,
  qtype = c("NORMAL", "PARTIAL_TRIANGULARIZATION", "FULL_TRIANGULARIZATION", "QR"),
  collapsing = TRUE,
  rescalingFactor = TRUE
)
.akf_likelihood(
  ssf,
  data,
  qtype = c("NORMAL", "PARTIAL_TRIANGULARIZATION", "FULL_TRIANGULARIZATION", "QR"),
  collapsing = TRUE,
  rescalingFactor = TRUE
)

Arguments

ssf

A state space form.

data

Arrays of data.

qtype

Type of the initialization in the augmented Kalman filter

rescalingFactor

True if the innovation covariance matrix is defined up to a scaling factor.

Value

The diffuse likelihood

Examples

sarima<-.sarima(12, NULL, 1,  -.6, NULL, 1, -.5)
ssf<-.ssf(sarima, .loading(0))
.akf_likelihood(ssf, rjd3toolkit::ABS$X0.2.09.10.M)
sarima<-.sarima(12, NULL, 1,  -.6, NULL, 1, -.5)
ssf<-.ssf(sarima, .loading(0))
.akf_likelihood(ssf, rjd3toolkit::ABS$X0.2.09.10.M)

Creates an ARIMA state block (representation I)

Description

Creates an ARIMA state block (representation I)

Usage

.arima(ar, delta, ma, var = 1)
.arima(ar, delta, ma, var = 1)

Arguments

ar

Stationary auto-regressive polynomial, including the constant (=1). True signs.

delta

Non-stationary auto-regressive polynomial, including the constant (=1). True signs.

ma

Moving average polynomial, including the constant (=1). True signs.

var

Variance of the innovations

Value

A raw java state block.

Examples

sb<-.arima(c(1, -.5), NULL, c(1,-.8))
.ssf_P0(sb)
sb<-.arima(c(1, -.5), NULL, c(1,-.8))
.ssf_P0(sb)

Creates an ARIMA state block (representation II)

Description

Creates an ARIMA state block (representation II)

Usage

.arima2(ar, delta, ma, var = 1)
.arima2(ar, delta, ma, var = 1)

Arguments

ar

Stationary auto-regressive polynomial, including the constant (=1). True signs.

delta

Non-stationary auto-regressive polynomial, including the constant (=1). True signs.

ma

Moving average polynomial, including the constant (=1). True signs.

var

Variance of the innovations

Value

A raw java state block

Examples

sb<-.arima2(c(1, -.5), NULL, c(1,-.8))
.ssf_P0(sb)
sb<-.arima2(c(1, -.5), NULL, c(1,-.8))
.ssf_P0(sb)

Title

Description

Title

Usage

.bsm2spec(jbsm, fixed = FALSE, fixedCycle = TRUE)
.bsm2spec(jbsm, fixed = FALSE, fixedCycle = TRUE)

Arguments

fixedCycle

Examples

bsm<-bsm_model(12)
jbsm<-.r2jd_bsm(bsm)
jspec<-.bsm2spec(jbsm)
bsm<-bsm_model(12)
jbsm<-.r2jd_bsm(bsm)
jspec<-.bsm2spec(jbsm)

Title

Description

Title

Usage

.bsm2ucm(jbsm, normalized = TRUE)
.bsm2ucm(jbsm, normalized = TRUE)

Arguments

normalized

Examples

bsm<-bsm_model(12)
jbsm<-.r2jd_bsm(bsm)
jucm<-.bsm2ucm(jbsm)
bsm<-bsm_model(12)
jbsm<-.r2jd_bsm(bsm)
jucm<-.bsm2ucm(jbsm)

Computes the diffuse likelihood by means of the diffuse Kalman filter (Durbin-Koopman).

Description

Computes the diffuse likelihood by means of the diffuse Kalman filter (Durbin-Koopman).

Usage

.dk_likelihood(ssf, data, sqr = TRUE, rescalingFactor = TRUE)
.dk_likelihood(ssf, data, sqr = TRUE, rescalingFactor = TRUE)

Arguments

ssf

A state space form.

data

Arrays of data.

sqr

Square root diffuse initialization, if any

rescalingFactor

True if the innovation covariance matrix is defined up to a scaling factor.

Value

The diffuse likelihood

Examples

sarima<-.sarima(12, NULL, 1,  -.6, NULL, 1, -.5)
ssf<-.ssf(sarima, .loading(0))
.dk_likelihood(ssf, rjd3toolkit::ABS$X0.2.09.10.M)
sarima<-.sarima(12, NULL, 1,  -.6, NULL, 1, -.5)
ssf<-.ssf(sarima, .loading(0))
.dk_likelihood(ssf, rjd3toolkit::ABS$X0.2.09.10.M)

Creates a composite loading

Description

Creates a composite loading

Usage

.loading_composite(dims, cmps)
.loading_composite(dims, cmps)

Arguments

dims

The dimensions of the corresponding state blocks

cmps

The loadings

Examples

l<-.loading_composite(c(1,2,3), list(.loading(0), .loading(0), .loading(0)))
.ssf_Z(l, 6, 0)
l<-.loading_composite(c(1,2,3), list(.loading(0), .loading(0), .loading(0)))
.ssf_Z(l, 6, 0)

Creates a local level state block

Description

Creates a local level state block

Usage

.local_level(var = 1, start = NaN)
.local_level(var = 1, start = NaN)

Arguments

var

Innovation variance of local level

start

Initial value of the state block. Should be NaN for a diffuse initialization

Value

A wrapper around the java object (class JD3_RawStateBlock).

Examples

sb<-.local_level(1.5, 0)
.ssf_T(sb, 0)
sb<-.local_level(1.5, 0)
.ssf_T(sb, 0)

Creates a local linear trend state block.

Description

Creates a local linear trend state block.

Usage

.local_linear_trend(lvar, svar = 0)
.local_linear_trend(lvar, svar = 0)

Arguments

lvar

Innovation variance of the level equation.

svar

Innovation variance of the slope equation.

Value

A wrapper around the java object (class JD3_RawStateBlock).

Examples

sb<-.local_linear_trend(1.5, 0.5)
.ssf_T(sb, 0)
sb<-.local_linear_trend(1.5, 0.5)
.ssf_T(sb, 0)

Creates a white noise.

Description

Creates a white noise.

Usage

.noise(var = 1)
.noise(var = 1)

Arguments

var

Variance of the noise.

Value

A wrapper around the java object (class JD3_RawStateBlock).

Examples

sb<-.noise(.01)
.ssf_T(sb, 0)
sb<-.noise(.01)
.ssf_T(sb, 0)

Creates an ARMA state block

Description

Creates an ARMA state block

Usage

.sarima(period, phi, d = 1, theta, bphi, bd = 1, btheta)
.sarima(period, phi, d = 1, theta, bphi, bd = 1, btheta)

Arguments

period

Period of the seasonality

phi

Regular stationary auto-regressive polynomial. True signs, without the constant

d

Regular differencing order

theta

Regular moving average polynomial. True signs, without the constant

bphi

Seasonal stationary auto-regressive polynomial. True signs, without the constant

bd

Seasonal differencing order

btheta

Seasonal moving average polynomial. True signs, without the constant

Value

A raw java state block

Examples

sb<-.sarima(12, c(0.5, -.2, .1), 1, -.8, NULL, 1, -.6)
.ssf_P0(sb)
sb<-.sarima(12, c(0.5, -.2, .1), 1, -.8, NULL, 1, -.6)
.ssf_P0(sb)

Creates an ARMA state block (representation I)

Description

Creates an ARMA state block (representation I)

Usage

.sarma(period, phi, theta, bphi, btheta)
.sarma(period, phi, theta, bphi, btheta)

Arguments

period

Period of the seasonality

phi

Regular stationary auto-regressive polynomial. True signs, without the constant

theta

Regular moving average polynomial. True signs, without the constant

bphi

Seasonal stationary auto-regressive polynomial. True signs, without the constant

btheta

Seasonal moving average polynomial. True signs, without the constant

Value

A raw java state block

Examples

sb<-.sarma(12, c(0.5, -.2, .1), -.8, NULL, -.6)
.ssf_P0(sb)
sb<-.sarma(12, c(0.5, -.2, .1), -.8, NULL, -.6)
.ssf_P0(sb)

Creates an ARMA state block (representation II)

Description

Creates an ARMA state block (representation II)

Usage

.sarma2(period, phi, theta, bphi, btheta)
.sarma2(period, phi, theta, bphi, btheta)

Arguments

period

Period of the seasonality

phi

Regular stationary auto-regressive polynomial. True signs, without the constant

theta

Regular moving average polynomial. True signs, without the constant

bphi

Seasonal stationary auto-regressive polynomial. True signs, without the constant

btheta

Seasonal moving average polynomial. True signs, without the constant

Value

A raw java state block

Examples

sb<-.sarma2(12, c(0.5, -.2, .1), -.8, NULL, -.6)
.ssf_P0(sb)
sb<-.sarma2(12, c(0.5, -.2, .1), -.8, NULL, -.6)
.ssf_P0(sb)

Creates a seasonal component, corresponding to a multivariate random walk, with an aggregation constraint to 0 and various covariances for the innovations of the transition equation.

Description

Creates a seasonal component, corresponding to a multivariate random walk, with an aggregation constraint to 0 and various covariances for the innovations of the transition equation.

Usage

.seasonal(
  period,
  type = c("Trigonometric", "Crude", "HarrisonStevens", "Dummy"),
  var = 1
)
.seasonal(
  period,
  type = c("Trigonometric", "Crude", "HarrisonStevens", "Dummy"),
  var = 1
)

Arguments

period

Period of the seasonality

type

Type of the innovations of the transition equation

var

Variance of the innovations

Value

A wrapper around the java object (class JD3_RawStateBlock)

Examples

sb<-.seasonal(4, "HarrisonStevens", .01)
.ssf_V(sb, 0)
sb<-.seasonal(4, "HarrisonStevens", .01)
.ssf_V(sb, 0)

Transforms a time invariant state space form based on functions into a state space models represented by matrices.

Description

Transforms a time invariant state space form based on functions into a state space models represented by matrices.

Usage

.ssf_as_time_invariant(jssf)
.ssf_as_time_invariant(jssf)

Arguments

jssf

The object oriented (java) state space form, which should be time invariant

Value

A new Java object based on matrices

Examples

ll<-.local_linear_trend(0.1, 0.1)
s<-.seasonal(12, var=.5)
m<-.composite(list(ll, s))
ssf1<-.ssf(m, .loading(c(0,2)), 1)
ssf2<-.ssf_as_time_invariant(ssf1)
ll1<-.akf_likelihood(ssf1, rjd3toolkit::ABS$X0.2.09.10.M)
ll2<-.akf_likelihood(ssf2, rjd3toolkit::ABS$X0.2.09.10.M)
print(ll1$ll-ll2$ll)
ll<-.local_linear_trend(0.1, 0.1)
s<-.seasonal(12, var=.5)
m<-.composite(list(ll, s))
ssf1<-.ssf(m, .loading(c(0,2)), 1)
ssf2<-.ssf_as_time_invariant(ssf1)
ll1<-.akf_likelihood(ssf1, rjd3toolkit::ABS$X0.2.09.10.M)
ll2<-.akf_likelihood(ssf2, rjd3toolkit::ABS$X0.2.09.10.M)
print(ll1$ll-ll2$ll)

Computes smoothed states by means of the augmented Kalman filter in the case of diffuse initialization

Description

Computes smoothed states by means of the augmented Kalman filter in the case of diffuse initialization

Usage

.ssf_smooth(
  ssf,
  data,
  all = TRUE,
  qtype = c("NORMAL", "PARTIAL_TRIANGULARIZATION", "FULL_TRIANGULARIZATION", "QR")
)
.ssf_smooth(
  ssf,
  data,
  all = TRUE,
  qtype = c("NORMAL", "PARTIAL_TRIANGULARIZATION", "FULL_TRIANGULARIZATION", "QR")
)

Arguments

ssf

A state space form.

data

Arrays of data.

all

True if the covariances of the smoothed states are compted.

qtype

Type of the initialization in the augmented Kalman filter

Value

A matrix with the smoothed states and - if requested - their standard deviations.

Gets the transition matrix.

Description

Gets the transition matrix.

Usage

.ssf_T(x, pos = 0)
.ssf_T(x, pos = 0)

Arguments

x

A state block or a state space form.

pos

The 0-based position (use 0 for time invariant models)

Value

The requested matrix.

Examples

sarima<-.sarma(12, .9, -.6, .9, -.5)
.ssf_T(sarima)
sarima<-.sarma(12, .9, -.6, .9, -.5)
.ssf_T(sarima)

Gets the covariance of the innovations in the transition equation.

Description

Gets the covariance of the innovations in the transition equation.

Usage

.ssf_V(x, pos = 0)
.ssf_V(x, pos = 0)

Arguments

x

A state block or a state space form.

pos

The 0-based position (use 0 for time invariant models)

Value

The requested matrix.

Examples

sarima<-.sarma(12, .9, -.6, .9, -.5)
.ssf_V(sarima)
sarima<-.sarma(12, .9, -.6, .9, -.5)
.ssf_V(sarima)

Gets the loading vector. It should have the same length as the corresponding state block.

Description

Gets the loading vector. It should have the same length as the corresponding state block.

Usage

.ssf_Z(x, n, pos)
.ssf_Z(x, n, pos)

Arguments

x

n

the Length of the corresponding state block (on which the loading will be applied)

pos

0-based position of the filter

Value

the loading vector

Retrieves the dimension of a state block

Description

Retrieves the dimension of a state block

Usage

.state_dim(x)
.state_dim(x)

Arguments

x

A state block

Value

The length of the state block

Examples

s<-.seasonal(12)
.state_dim(s)
s<-.seasonal(12)
.state_dim(s)

Gets the state of the state space form

Description

Gets the state of the state space form

Usage

.state_of(ssf)
.state_of(ssf)

Arguments

ssf

A state space form

Value

A state block

Adds a state block or a measurement equation to a given state space model

Description

Adds a state block or a measurement equation to a given state space model

Usage

add(model, item)
add(model, item)

Arguments

model

A state space model

item

A state block or a measurement equation

Examples

model<-model()
llt<-locallineartrend("llt")
add(model,llt)
model<-model()
llt<-locallineartrend("llt")
add(model,llt)

Add a building block to the considered equation

Description

Add a building block to the considered equation

Usage

add_equation(equation, item, coeff = 1, fixed = TRUE, loading = NULL)
add_equation(equation, item, coeff = 1, fixed = TRUE, loading = NULL)

Arguments

equation

the equation

item

the block of the state array that will be linked to the observation corresponding to this equation through the specified loading and coefficient

coeff

the value of the coefficient associated to the block of latent variables defined by item.

fixed

logical that triggers estimation of coeff (FALSE) or fixes it (TRUE) to a pre-specified value

loading

the loading that links the block to the observations

Examples

eq<- equation('eq1')
ll<-locallevel('ll')
n<-noise("n", variance = 1, fixed = TRUE)
add_equation(eq, ll)
add_equation(eq, n, coeff=0.1, fixed=FALSE)
eq<- equation('eq1')
ll<-locallevel('ll')
n<-noise("n", variance = 1, fixed = TRUE)
add_equation(eq, ll)
add_equation(eq, n, coeff=0.1, fixed=FALSE)

Autoregressive model

Description

Functions to create an autoregressive model (ar) or a modified autoregressive model (ar2)

Usage

ar(
  name,
  ar,
  fixedar = FALSE,
  variance = 0.01,
  fixedvariance = FALSE,
  nlags = 0,
  zeroinit = FALSE
)

ar2(
  name,
  ar,
  fixedar = FALSE,
  variance = 0.01,
  fixedvariance = FALSE,
  nlags = 0,
  nfcasts = 0
)
ar(
  name,
  ar,
  fixedar = FALSE,
  variance = 0.01,
  fixedvariance = FALSE,
  nlags = 0,
  zeroinit = FALSE
)

ar2(
  name,
  ar,
  fixedar = FALSE,
  variance = 0.01,
  fixedvariance = FALSE,
  nlags = 0,
  nfcasts = 0
)

Arguments

ar

vector of the AR coefficients (See @details Additional details...).

fixedar

boolean that triggers the estimation of the AR coefficients (FALSE) or fixed it (TRUE) to a pre-specified value set by the parameter ar.

variance

the variance ( $\sigma^2_{ar}$ ).

fixedvariance

boolean that triggers the estimation of the variance (FALSE) or fixed it (TRUE) to a pre-specified value set by the parameter variance.

nlags

integer specifying how many lags of the state variable are needed

zeroinit

boolean determining the initial condition for the state variable, which is equal to zero if zeroinit = TRUE. The default (zeroinit = FAKSE) triggers the an initialization based on the unconditional mean and variance of the AR(p) process.

nfcasts

integer specifying how many forecasts of the state variable are needed

Details

The AR process is defined by

$y_t = \phi_1 y_{t-1} + \phi_2 y_{t-2} + \dots + \phi_p y_{t-p} + \epsilon_t$

The stability of the auto-regressive polynomial is not checked.

Value

An element of type "JD3_SsfStateBlock" (wrapper around the corresponding Java object))

Examples

b_ar<-ar("my_ar", c(.8,-.3,.2), variance=1)
block_p0(b_ar)
b_ar<-ar("my_ar", c(.8,-.3,.2), variance=1)
block_p0(b_ar)

Autoregressive Integrated Moving Average (ARIMA) Model

Description

Autoregressive Integrated Moving Average (ARIMA) Model

Usage

arima(name, ar, diff, ma, var = 1, fixed = FALSE)
arima(name, ar, diff, ma, var = 1, fixed = FALSE)

Arguments

fixed

Autoregressive Moving Average (ARMA) Model

Description

Autoregressive Moving Average (ARMA) Model

Usage

arma(name, ar, fixedar = FALSE, ma, fixedma = FALSE, var = 1, fixedvar = FALSE)
arma(name, ar, fixedar = FALSE, ma, fixedma = FALSE, var = 1, fixedvar = FALSE)

Arguments

fixedvar

Title

Description

Title

Usage

block_d0(block, pos = 0)
block_d0(block, pos = 0)

Arguments

pos

Title

Description

Title

Usage

block_p0(block)
block_p0(block)

Arguments

block

Title

Description

Title

Usage

block_t(block, pos = 0)
block_t(block, pos = 0)

Arguments

pos

Title

Description

Title

Usage

block_v(block, pos = 0)
block_v(block, pos = 0)

Arguments

block

Title

Description

Title

Usage

bsm_model(
  period,
  noise.var = 1,
  level.var = 1,
  slope.var = NULL,
  seasonal.var = 1,
  seasonal.model = c("HarrisonStevens", "Trigonometric", "Dummy", "Crude", "Fixed"),
  cycle.var = NULL,
  cycle.dumpingfactor = 0.9,
  cycle.length = 6
)
bsm_model(
  period,
  noise.var = 1,
  level.var = 1,
  slope.var = NULL,
  seasonal.var = 1,
  seasonal.model = c("HarrisonStevens", "Trigonometric", "Dummy", "Crude", "Fixed"),
  cycle.var = NULL,
  cycle.dumpingfactor = 0.9,
  cycle.length = 6
)

Arguments

cycle.length

Title

Description

Title

Usage

bsm_to_ucm(bsm, normalized = TRUE)
bsm_to_ucm(bsm, normalized = TRUE)

Arguments

normalized

Position of the components

Description

Position of the components

Usage

components_pos(model)
components_pos(model)

Arguments

model

Estimated model

Value

The first position of the different blocks in the state array

Examples

model<-model()
ll<-locallevel("ll")
seas<-seasonal("seas", 12, "Crude")
n<-noise("n")
add(model,ll)
add(model,seas)
add(model,n)
emodel<-estimate(model, rjd3toolkit::Retail$BookStores)
print(components_pos(emodel))
model<-model()
ll<-locallevel("ll")
seas<-seasonal("seas", 12, "Crude")
n<-noise("n")
add(model,ll)
add(model,seas)
add(model,n)
emodel<-estimate(model, rjd3toolkit::Retail$BookStores)
print(components_pos(emodel))

Title

Description

Title

Usage

cumul(name, core, period, start = 0)
cumul(name, core, period, start = 0)

Arguments

start

Title

Description

Title

Usage

cycle(
  name,
  factor = 0.9,
  period = 60,
  fixed = FALSE,
  variance = 0.01,
  fixedvariance = FALSE
)
cycle(
  name,
  factor = 0.9,
  period = 60,
  fixed = FALSE,
  variance = 0.01,
  fixedvariance = FALSE
)

Arguments

name

Name of the block

variance

Variance of the innovations

fixedvariance

Indicates if the variance if fixed

Create equation

Description

Create equation

Usage

equation(name, variance = 0, fixed = TRUE)
equation(name, variance = 0, fixed = TRUE)

Arguments

fixed

Estimate a SSF Model

Description

Estimate a SSF Model

Usage

estimate(
  model,
  data,
  marginal = FALSE,
  concentrated = TRUE,
  initialization = c("Augmented_Robust", "Diffuse", "SqrtDiffuse", "Augmented",
    "Augmented_NoCollapsing"),
  optimizer = c("LevenbergMarquardt", "MinPack", "BFGS", "LBFGS"),
  precision = 1e-15,
  initialParameters = NULL
)
estimate(
  model,
  data,
  marginal = FALSE,
  concentrated = TRUE,
  initialization = c("Augmented_Robust", "Diffuse", "SqrtDiffuse", "Augmented",
    "Augmented_NoCollapsing"),
  optimizer = c("LevenbergMarquardt", "MinPack", "BFGS", "LBFGS"),
  precision = 1e-15,
  initialParameters = NULL
)

Arguments

model

the model

data

a matrix containing the data (one time series per column, time series dimension on the rows)

marginal

logical value used to specify whether the marginal likelihood definition is used (TRUE) or not (FALSE) during the optimization. The marginal likelihood is recommended when there is at least one variable that loads on a non-stationary latent variable and the loading coefficient needs to be estimated.

concentrated

logical value used to specify whether the likelihood is concentrated (TRUE) or not (FALSE) during the optimization

initialization

initialization method.

precision

indicating the largest likelihood deviations that make the algorithm stop.

initialParameters

Title

Description

Title

Usage

filtered_states(model)
filtered_states(model)

Arguments

model

Title

Description

Title

Usage

filtered_states_stdev(model)
filtered_states_stdev(model)

Arguments

model

Title

Description

Title

Usage

filtering_states(model)
filtering_states(model)

Arguments

model

Title

Description

Title

Usage

filtering_states_stdev(model)
filtering_states_stdev(model)

Arguments

model

Title

Description

Title

Usage

loading(pos = NULL, weights = NULL)
loading(pos = NULL, weights = NULL)

Arguments

pos

defines the position of each one of the elements of the block of states defined. NULL indicates by default the first state included in the block (pos=0)

weights

defines the weights associated to each one of the state variables included in the block.

Title

Description

Title

Usage

loading_cyclical(period, startpos)
loading_cyclical(period, startpos)

Arguments

startpos

Title

Description

Title

Usage

loading_periodic(period, startpos)
loading_periodic(period, startpos)

Arguments

startpos

Title

Description

Title

Usage

loading_sum(length = 0)
loading_sum(length = 0)

Arguments

length

Give all the loadings for a given variable

Description

Give all the loadings for a given variable

Usage

loadings(object, var = 1)
loadings(object, var = 1)

Arguments

object

Estimated model

var

loadings for the given variable (or equation). Useless in the case of univariate models

Value

A matrix with the requested loadings. The number of rows corresponds to the number of observations.

Examples

model<-model()
llt<-locallineartrend("llt")
seas<-seasonal("seas", 12, "Crude")
n<-noise("n")
add(model,llt)
add(model,seas)
add(model,n)
y<-rjd3toolkit::Retail$BookStores
emodel<-estimate(model, y)
print(loadings(emodel))
model<-model()
llt<-locallineartrend("llt")
seas<-seasonal("seas", 12, "Crude")
n<-noise("n")
add(model,llt)
add(model,seas)
add(model,n)
y<-rjd3toolkit::Retail$BookStores
emodel<-estimate(model, y)
print(loadings(emodel))

Local Level

Description

Local Level

Usage

locallevel(name, variance = 0.01, fixed = FALSE, initial = NaN)
locallevel(name, variance = 0.01, fixed = FALSE, initial = NaN)

Arguments

name

Name of the block

variance

the value of the variance ( $\sigma^2_l$ ).

fixed

boolean that triggers estimation of $\sigma^2_l$ (FALSE) or fixes it (TRUE) to a pre-specified value set by the parameter variance.

initial

initial value of the level ( $l_0$ ).

Details

$\begin{cases}l_{t+1} = l_t + \mu_t \\ \mu_t \sim N(0, \sigma^2 \sigma^2_l) \end{cases}$

Examples

ll<-locallevel('ll', variance=1)
print(block_t(ll))
ll<-locallevel('ll', variance=1)
print(block_t(ll))

Local linear trend state block

Description

Local linear trend state block

Usage

locallineartrend(
  name,
  levelVariance = 0.01,
  slopeVariance = 0.01,
  fixedLevelVariance = FALSE,
  fixedSlopeVariance = FALSE
)
locallineartrend(
  name,
  levelVariance = 0.01,
  slopeVariance = 0.01,
  fixedLevelVariance = FALSE,
  fixedSlopeVariance = FALSE
)

Arguments

name

Name of the block

levelVariance

variance of the level ( $\sigma^2_l$ )

fixedLevelVariance, fixedSlopeVariance

boolean that triggers the estimation of the variances $\sigma^2_l$ and $\sigma^2_n$ (FALSE) or fixes it (TRUE) to a pre-specified value set by the parameters levelVariance and slopevariance.

Details

$\begin{cases}l_{t+1} = l_t + n_t + \xi_t \\ n_{t+1} = n_t + \mu_t \\ \xi_t \sim N(0, \sigma^2_l)\\ \mu_t \sim N(0, \sigma^2_n) \end{cases}$

Examples

llt<-locallineartrend('llt', levelVariance=1, slopeVariance=.25)
print(block_t(llt))
llt<-locallineartrend('llt', levelVariance=1, slopeVariance=.25)
print(block_t(llt))

Title

Description

Title

Usage

ltd_airline(
  name,
  length,
  period,
  th0 = -0.6,
  th1 = -0.6,
  bth0 = -0.6,
  bth1 = -0.6,
  fixedth = FALSE,
  variance = 0.01,
  fixedvariance = FALSE
)
ltd_airline(
  name,
  length,
  period,
  th0 = -0.6,
  th1 = -0.6,
  bth0 = -0.6,
  bth1 = -0.6,
  fixedth = FALSE,
  variance = 0.01,
  fixedvariance = FALSE
)

Arguments

fixedvariance

Create Composite Model

Description

Create Composite Model

Usage

model()
model()

Modeling errors in surveys with overlapping panels

Description

Modeling errors in surveys with overlapping panels

Usage

msae(name, nwaves, ar, fixedar = TRUE, lag = 1)

msae2(name, vars, fixedvars = FALSE, ar, fixedar = TRUE, lag = 1)

msae3(name, vars, fixedvars = FALSE, ar, fixedar = TRUE, k, lag = 1)
msae(name, nwaves, ar, fixedar = TRUE, lag = 1)

msae2(name, vars, fixedvars = FALSE, ar, fixedar = TRUE, lag = 1)

msae3(name, vars, fixedvars = FALSE, ar, fixedar = TRUE, k, lag = 1)

Arguments

name

Name of the block

nwaves

integer representing the number of waves

ar

matrix representing the covariance structure of the wave specific survey error.

fixedar

logical that triggers the estimation of the correlation patterns (TRUE) or fixes them to the values given by the entries ar (FALSE)

lag

integer specifying the number of time periods (in the base frequency) that compose the survey period. This coincides with the number of time periods an individual has to wait between two different waves. Note that if the survey period is one quarter, all of them have already responded in the previous wave exactly 3 months ago (because individuals are always interviewed at the same stint during each survey period).

Title

Description

Title

Usage

msignal(object, m, pos = NULL, stdev = FALSE)
msignal(object, m, pos = NULL, stdev = FALSE)

Arguments

object

Estimated model

stdev

Noise state block

Description

Noise state block

Usage

noise(name, variance = 0.01, fixed = FALSE)
noise(name, variance = 0.01, fixed = FALSE)

Arguments

name

Name of the block

variance

Variance of the noise

fixed

Indicates if the variance is fixed

Examples

n<-noise("n", 1)
block_t(n)
n<-noise("n", 1)
block_t(n)

Get Parameters of SSF Model

Description

Get Parameters of SSF Model

Usage

parameters(model)
parameters(model)

Arguments

model

Title

Description

Title

Usage

periodic(name, period, harmonics, variance = 0.01, fixedvariance = FALSE)
periodic(name, period, harmonics, variance = 0.01, fixedvariance = FALSE)

Arguments

name

Name of the block

fixedvariance

Title

Description

Title

Usage

## S3 method for class 'JD3STS'
print(x, ...)
## S3 method for class 'JD3STS'
print(x, ...)

Arguments

...

Time Varying Regressors

Description

Time Varying Regressors

Usage

reg(name, x, var = NULL, fixed = FALSE)
reg(name, x, var = NULL, fixed = FALSE)

Arguments

x

matrix containing the regressors

fixed

Title

Description

Title

Usage

reg_td(
  name,
  period,
  start,
  length,
  groups = c(1, 2, 3, 4, 5, 6, 0),
  contrast = TRUE,
  variance = 1,
  fixed = FALSE
)
reg_td(
  name,
  period,
  start,
  length,
  groups = c(1, 2, 3, 4, 5, 6, 0),
  contrast = TRUE,
  variance = 1,
  fixed = FALSE
)

Arguments

fixed

Title

Description

Title

Usage

sae(name, ar, fixedar = FALSE, lag = 1, zeroinit = FALSE)
sae(name, ar, fixedar = FALSE, lag = 1, zeroinit = FALSE)

Arguments

name

Name of the block

zeroinit

Title

Description

Title

Usage

sarima(
  name,
  period,
  orders,
  seasonal,
  parameters = NULL,
  fixedparameters = FALSE,
  var = 1,
  fixedvariance = FALSE
)
sarima(
  name,
  period,
  orders,
  seasonal,
  parameters = NULL,
  fixedparameters = FALSE,
  var = 1,
  fixedvariance = FALSE
)

Arguments

fixedvariance

Seasonal state block

Description

Seasonal state block

Usage

seasonal(
  name,
  period,
  type = c("Trigonometric", "Crude", "HarrisonStevens", "Dummy"),
  variance = 0.01,
  fixed = FALSE
)
seasonal(
  name,
  period,
  type = c("Trigonometric", "Crude", "HarrisonStevens", "Dummy"),
  variance = 0.01,
  fixed = FALSE
)

Arguments

name

Name of the block

period

Period of the seasonality

type

Type of the seasonal component

variance

Innovation variance

fixed

Indicates if the variance is fixed

Examples

seas1<-seasonal("seas1", 12, "HarrisonStevens", variance=1)
print(block_v(seas1))
seas2<-seasonal("seas2", 12, "Trigonometric", variance=1)
print(block_v(seas2))
seas1<-seasonal("seas1", 12, "HarrisonStevens", variance=1)
print(block_v(seas1))
seas2<-seasonal("seas2", 12, "Trigonometric", variance=1)
print(block_v(seas2))

Title

Description

Title

Usage

seasonalbreaks(
  y,
  period = NA,
  level = 1,
  slope = 1,
  noise = 1,
  seasonal = c("HarrisonStevens", "Trigonometric", "Dummy", "Crude", "Fixed", "Unused"),
  X = NULL,
  X.td = NULL
)
seasonalbreaks(
  y,
  period = NA,
  level = 1,
  slope = 1,
  noise = 1,
  seasonal = c("HarrisonStevens", "Trigonometric", "Dummy", "Crude", "Fixed", "Unused"),
  X = NULL,
  X.td = NULL
)

Arguments

y

input time series.

period

annual frequency.

level

-1 = no level, 0 = fixed level, 1 = sotchastic level

seasonal

Seasonal model

X

Regression variables (same length as y) or NULL

X.td

Groups of days for trading days regressors. The length of the array must be 7. It indicates to what group each week day belongs. The first item corresponds to Mondays and the last one to Sundays. The group used for contrasts (usually Sundays) is identified by 0. The other groups are identified by 1, 2,... n (<= 6). For instance, usual trading days are defined by c(1,2,3,4,5,6,0), week days by c(1,1,1,1,1,0,0), etc...

Examples

 x<-rjd3toolkit::Retail$BookStores
 seasonalbreaks(x)
x<-rjd3toolkit::Retail$BookStores
 seasonalbreaks(x)

Title

Description

Title

Usage

signal(object, obs = 1, pos = NULL, loading = NULL, stdev = FALSE)
signal(object, obs = 1, pos = NULL, loading = NULL, stdev = FALSE)

Arguments

stdev

Retrieves the components of the model (univariate case) or the components corresponding to a given equation (multivariate case)

Description

Retrieves the components of the model (univariate case) or the components corresponding to a given equation (multivariate case)

Usage

smoothed_components(model, equation = 1, fast = TRUE)
smoothed_components(model, equation = 1, fast = TRUE)

Arguments

model

Estimated state space model

equation

Equation containing the components

fast

if true, only the components are computed. Otherwise, their stdev are also computed (not returned but available for future use).

Value

A matrix with the components

Examples

model<-model()
llt<-locallineartrend("llt")
seas<-seasonal("seas", 12, "Crude")
n<-noise("n")
add(model,llt)
add(model,seas)
add(model,n)
y<-rjd3toolkit::Retail$BookStores
emodel<-estimate(model, y)
scmp<-smoothed_components(emodel)
high<-cbind(scmp[,1], y-scmp[,2])
low<-scmp[,c(2,3)]
matplot(high, type='l')
matplot(low, type='l')
model<-model()
llt<-locallineartrend("llt")
seas<-seasonal("seas", 12, "Crude")
n<-noise("n")
add(model,llt)
add(model,seas)
add(model,n)
y<-rjd3toolkit::Retail$BookStores
emodel<-estimate(model, y)
scmp<-smoothed_components(emodel)
high<-cbind(scmp[,1], y-scmp[,2])
low<-scmp[,c(2,3)]
matplot(high, type='l')
matplot(low, type='l')

Retrieves the standard deviations of the components of the model (univariate case) or of the components corresponding to a given equation (multivariate case)

Description

Retrieves the standard deviations of the components of the model (univariate case) or of the components corresponding to a given equation (multivariate case)

Usage

smoothed_components_stdev(model, equation = 1)
smoothed_components_stdev(model, equation = 1)

Arguments

model

Estimated state space model

equation

Equation containing the components

Value

A matrix with the stdev of the components

Title

Description

Title

Usage

smoothed_states(model)
smoothed_states(model)

Arguments

model

Standard deviations of the smoothed states

Description

Standard deviations of the smoothed states

Usage

smoothed_states_stdev(model)
smoothed_states_stdev(model)

Arguments

model

Estimated model

Value

A matrix with the standard deviations of the states (a row corresponding to one time point)

Examples

model<-model()
ll<-locallevel("ll")
seas<-seasonal("seas", 12, "Crude")
n<-noise("n")
add(model,ll)
add(model,seas)
add(model,n)
emodel<-estimate(model, rjd3toolkit::Retail$BookStores)
ess<-smoothed_states_stdev(emodel)
cmps<-ess[,c(1,2,13)]
matplot(cmps, type='l')
model<-model()
ll<-locallevel("ll")
seas<-seasonal("seas", 12, "Crude")
n<-noise("n")
add(model,ll)
add(model,seas)
add(model,n)
emodel<-estimate(model, rjd3toolkit::Retail$BookStores)
ess<-smoothed_states_stdev(emodel)
cmps<-ess[,c(1,2,13)]
matplot(cmps, type='l')

Title

Description

Title

Usage

splines_daily(name, startYear, knots, start = 1, variance = 1, fixed = FALSE)
splines_daily(name, startYear, knots, start = 1, variance = 1, fixed = FALSE)

Arguments

fixed

Title

Description

Title

Usage

splines_generic(
  name,
  period,
  knots,
  order = 4,
  start = 1,
  variance = 1,
  fixed = FALSE
)
splines_generic(
  name,
  period,
  knots,
  order = 4,
  start = 1,
  variance = 1,
  fixed = FALSE
)

Arguments

fixed

Title

Description

Title

Usage

splines_regular(
  name,
  period,
  nknots = 0,
  knots = NULL,
  start = 1,
  variance = 1,
  fixed = FALSE
)
splines_regular(
  name,
  period,
  nknots = 0,
  knots = NULL,
  start = 1,
  variance = 1,
  fixed = FALSE
)

Arguments

fixed

Title

Description

Title

Usage

ssf(initialization, dynamics, measurement)
ssf(initialization, dynamics, measurement)

Arguments

measurement

Title

Description

Title

Usage

sts(
  y,
  X = NULL,
  X.td = NULL,
  level = 1,
  slope = 1,
  cycle = -1,
  noise = 1,
  seasonal = c("Trigonometric", "Dummy", "Crude", "HarrisonStevens", "Fixed", "Unused"),
  diffuse.regs = TRUE,
  tol = 1e-09
)
sts(
  y,
  X = NULL,
  X.td = NULL,
  level = 1,
  slope = 1,
  cycle = -1,
  noise = 1,
  seasonal = c("Trigonometric", "Dummy", "Crude", "HarrisonStevens", "Fixed", "Unused"),
  diffuse.regs = TRUE,
  tol = 1e-09
)

Arguments

y

input time series.

X

Regression variables (same length as y) or NULL

X.td

level

-1 = no level, 0 = fixed level, 1 = sotchastic level

seasonal

Seasonal model

tol

Examples

 x<-rjd3toolkit::Retail$BookStores
 sts(x)
x<-rjd3toolkit::Retail$BookStores
 sts(x)

Forecast with STS model

Description

Forecast with STS model

Usage

sts_forecast(y, model = c("none", "td2", "td3", "td7", "full"), nf = 12)
sts_forecast(y, model = c("none", "td2", "td3", "td7", "full"), nf = 12)

Arguments

y

Series

model

Model for calendar effects

td2: leap year + week days (week-end derived)
td3: leap year + week days + saturdays (sundays derived)
td7: leap year + all days (sundays derived)
full: td3 + easter effect
none: no calendar effect

nf

number of forecasts

Examples

fcasts<-sts_forecast(rjd3toolkit::ABS$X0.2.09.10.M)
fcasts<-sts_forecast(rjd3toolkit::ABS$X0.2.09.10.M)

Title

Description

Title

Usage

sts_outliers(
  y,
  period = NA,
  X = NULL,
  X.td = NULL,
  level = 1,
  slope = 1,
  noise = 1,
  seasonal = c("Trigonometric", "Dummy", "Crude", "HarrisonStevens", "Fixed", "Unused"),
  ao = TRUE,
  ls = TRUE,
  so = FALSE,
  cv = 0,
  tcv = 0,
  estimation.forward = c("Score", "Point", "Full"),
  estimation.backward = c("Point", "Score", "Full")
)
sts_outliers(
  y,
  period = NA,
  X = NULL,
  X.td = NULL,
  level = 1,
  slope = 1,
  noise = 1,
  seasonal = c("Trigonometric", "Dummy", "Crude", "HarrisonStevens", "Fixed", "Unused"),
  ao = TRUE,
  ls = TRUE,
  so = FALSE,
  cv = 0,
  tcv = 0,
  estimation.forward = c("Score", "Point", "Full"),
  estimation.backward = c("Point", "Score", "Full")
)

Arguments

y

input time series.

period

annual frequency.

X

Regression variables (same length as y) or NULL

X.td

level

-1 = no level, 0 = fixed level, 1 = sotchastic level

seasonal

Seasonal model

ao, ls, so

boolean indicating if additive outliers (ao), level shift (ls) and seasonal outliers (so) should be detected.

estimation.backward

Examples

 x<-rjd3toolkit::Retail$BookStores
 sts_outliers(x)
x<-rjd3toolkit::Retail$BookStores
 sts_outliers(x)

Title

Description

Title

Usage

sts_raw(
  y,
  period = NA,
  X = NULL,
  X.td = NULL,
  level = 1,
  slope = 1,
  cycle = -1,
  noise = 1,
  seasonal = c("Trigonometric", "Dummy", "Crude", "HarrisonStevens", "Fixed", "Unused"),
  diffuse.regs = TRUE,
  tol = 1e-09
)
sts_raw(
  y,
  period = NA,
  X = NULL,
  X.td = NULL,
  level = 1,
  slope = 1,
  cycle = -1,
  noise = 1,
  seasonal = c("Trigonometric", "Dummy", "Crude", "HarrisonStevens", "Fixed", "Unused"),
  diffuse.regs = TRUE,
  tol = 1e-09
)

Arguments

tol

Title

Description

Title

Usage

tdairline_estimation(s, td = NULL, vartd = FALSE, precision = 1e-09)
tdairline_estimation(s, td = NULL, vartd = FALSE, precision = 1e-09)

Arguments

precision

Title

Description

Title

Usage

var_ar(
  name,
  ar,
  fixedar = FALSE,
  stderr,
  scale = 1,
  fixed = FALSE,
  zeroinit = FALSE
)
var_ar(
  name,
  ar,
  fixedar = FALSE,
  stderr,
  scale = 1,
  fixed = FALSE,
  zeroinit = FALSE
)

Arguments

name

Name of the block

zeroinit

Title

Description

Title

Usage

var_loading(pos, weights)
var_loading(pos, weights)

Arguments

weights

Title

Description

Title

Usage

var_locallevel(name, std, scale = 1, fixed = FALSE, initial = NaN)
var_locallevel(name, std, scale = 1, fixed = FALSE, initial = NaN)

Arguments

initial

Title

Description

Title

Usage

var_locallineartrend(
  name,
  lstd,
  sstd = NULL,
  levelScale = 1,
  slopeScale = 1,
  fixedLevelScale = FALSE,
  fixedSlopeScale = FALSE
)
var_locallineartrend(
  name,
  lstd,
  sstd = NULL,
  levelScale = 1,
  slopeScale = 1,
  fixedLevelScale = FALSE,
  fixedSlopeScale = FALSE
)

Arguments

fixedSlopeScale

Title

Description

Title

Usage

var_noise(name, std, scale = 1, fixed = FALSE)
var_noise(name, std, scale = 1, fixed = FALSE)

Arguments

fixed

Time Varying Regressor

Description

Time Varying Regressor

Usage

var_reg(name, x, stderr, scale = 1, fixed = FALSE)
var_reg(name, x, stderr, scale = 1, fixed = FALSE)

Arguments

x

Regression variable. Numerics

stderr

Standard error of the innovations of the coefficient (1 in extrapolation)

scale

Scaling factor

fixed

Fixed scaling factor

Examples

 x<-rjd3toolkit::Retail$BookStores
 std<-rep(1, length(x))
 std[c(20, 50, 150)]<-5
 v<-var_reg("vx", x, std, 0.1)
x<-rjd3toolkit::Retail$BookStores
 std<-rep(1, length(x))
 std[c(20, 50, 150)]<-5
 v<-var_reg("vx", x, std, 0.1)

Title

Description

Title

Usage

var_seasonal(
  name,
  period,
  type = c("Trigonometric", "Crude", "HarrisonStevens", "Dummy"),
  std,
  scale = 1,
  fixed = FALSE
)
var_seasonal(
  name,
  period,
  type = c("Trigonometric", "Crude", "HarrisonStevens", "Dummy"),
  std,
  scale = 1,
  fixed = FALSE
)

Arguments

fixed

Package 'rjd3sts'

Help Index

Creates the state space form of an airline model;

Description

Usage

Arguments

Value

Examples

Computes the diffuse likelihood by means of the augmented Kalman filter.

Description

Usage

Arguments

Value

Examples

Creates an ARIMA state block (representation I)

Description

Usage

Arguments

Value

Examples

Creates an ARIMA state block (representation II)

Description

Usage

Arguments

Value

Examples

Title

Description

Usage

Arguments

Examples

Title

Description

Usage

Arguments

Examples

Title

Description

Usage

Arguments

Title

Description

Usage

Arguments

Title

Description

Usage

Arguments

Title

Description

Usage

Arguments

Computes the diffuse likelihood by means of the diffuse Kalman filter (Durbin-Koopman).

Description

Usage

Arguments

Value

Examples

Title

Description

Usage

Arguments

Creates a composite loading

Description

Usage

Arguments

Examples

Creates a local level state block

Description

Usage

Arguments

Value

Examples

Creates a local linear trend state block.

Description

Usage

Arguments

Value

Examples

Title