Pipe operator

Description

See magrittr::%>% for details.

Usage

lhs %>% rhs

Estimate forecast error variance decomposition

Description

Estimate the forecast error variance decomposition for VARs with either short or 'IV-short' structural errors. See VAR and RVAR documentation for details regarding structural errors.

Usage

FEVD(model, horizon = 10, scale = TRUE)

Arguments

Value

long-form data.frame

See Also

VAR()

var_fevd()

RVAR()

rvar_fevd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)

 # estimate VAR
  var =
    sovereign::VAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      lag.ic = 'BIC',
      lag.max = 4)

# impulse response functions
var.irf = sovereign::IRF(var)

# forecast error variance decomposition
var.fevd = sovereign::FEVD(var)

# historical shock decomposition
var.hd = sovereign::HD(var)

Estimate historical decomposition

Description

Estimate the historical decomposition for VARs with either 'short' or 'IV-short' structural errors. See VAR and RVAR documentation for details regarding structural errors.

Usage

HD(model)

Arguments

Value

long-from data.frame

See Also

VAR()

var_hd()

RVAR()

rvar_hd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)

 # estimate VAR
  var =
    sovereign::VAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      lag.ic = 'BIC',
      lag.max = 4)

# impulse response functions
var.irf = sovereign::IRF(var)

# forecast error variance decomposition
var.fevd = sovereign::FEVD(var)

# historical shock decomposition
var.hd = sovereign::HD(var)

Estimate impulse response functions

Description

See VAR, RVAR, LP, and RLP documentation for details regarding models and structural errors.

Usage

IRF(
  model,
  horizon = 10,
  CI = c(0.1, 0.9),
  bootstrap.type = "auto",
  bootstrap.num = 100,
  bootstrap.parallel = FALSE,
  bootstrap.cores = -1
)

Arguments

Value

data frame with columns target, shock, horizon, response.lower, response, response.upper; regime-based models return a list with a data frame per regime.

See Also

var_irf()

rvar_irf()

lp_irf()

rlp_irf()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)

 # estimate VAR
  var =
    sovereign::VAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      lag.ic = 'BIC',
      lag.max = 4
    )

 # impulse response function
 var.irf = sovereign::IRF(var)

  # local projection forecasts
  lp =
    sovereign::LP(
      data = Data,
      horizon = c(1:10),
      lag.ic = 'AIC',
      lag.max = 4,
      type =  'both',
      freq = 'month')

  # LP impulse response function
  lp.irf = sovereign::IRF(lp)

Estimate local projections

Description

Estimate local projections

Usage

LP(
  data,
  horizons = 1,
  freq = "month",
  type = "const",
  p = 1,
  lag.ic = NULL,
  lag.max = NULL,
  NW = FALSE,
  NW_lags = NULL,
  NW_prewhite = NULL
)

Arguments

Value

list object with elements data, model, forecasts, residuals; if there is more than one forecast horizon estimated, then model, forecasts, residuals will each be a list where each element corresponds to a single horizon

References

1. Jorda, Oscar "Estimation and Inference of Impulse Responses by Local Projections" 2005.

See Also

LP()

lp_irf()

RLP()

rlp_irf()

Examples

  # simple time series
  AA = c(1:100) + rnorm(100)
  BB = c(1:100) + rnorm(100)
  CC = AA + BB + rnorm(100)
  date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
  Data = data.frame(date = date, AA, BB, CC)

  # local projection forecasts
  lp =
    sovereign::LP(
      data = Data,
      horizon = c(1:10),
      lag.ic = 'AIC',
      lag.max = 4,
      type =  'both',
      freq = 'month')

  # impulse response function
  irf = sovereign::lp_irf(lp)

Estimate regime-dependent local projections

Description

Estimate a regime-dependent local projection (i.e. a state-dependent LP), with an exogenous state indicator, of the specification:

Y_{t+h} = X_t \beta_{s_t} + \epsilon_t

where t is the time index, and s is a mutually exclusive state of the world observed at time t. When the regime vector is not supplied by the user, then a two-state regime series is estimated via random forest.

Usage

RLP(
  data,
  horizons = 1,
  freq = "month",
  type = "const",
  p = 1,
  lag.ic = NULL,
  lag.max = NULL,
  NW = FALSE,
  NW_lags = NULL,
  NW_prewhite = NULL,
  regime = NULL,
  regime.method = "rf",
  regime.n = 2
)

Arguments

Value

list of lists, one list per regime, each regime with objects with elements data, model, forecasts, residuals; if there is more than one forecast horizon estimated, then model, forecasts, residuals will each be a list where each element corresponds to a single horizon

References

1. Jorda, Oscar "Estimation and Inference of Impulse Responses by Local Projections" 2005.

See Also

LP()

lp_irf()

RLP()

rlp_irf()

Examples

  # simple time series
  AA = c(1:100) + rnorm(100)
  BB = c(1:100) + rnorm(100)
  CC = AA + BB + rnorm(100)
  date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
  Data = data.frame(date = date, AA, BB, CC)
  # add regime
  Data = dplyr::mutate(Data, reg = dplyr::if_else(AA > median(AA), 1, 0))

  # local projection forecasts
  rlp =
    sovereign::RLP(
      data = Data,
      regime = 'reg',
      horizon = c(1:10),
      freq = 'month',
      p = 1,
      type =  'const',
      NW = TRUE,
      NW_lags = 1,
      NW_prewhite = FALSE)

 # impulse response function
 rirf = sovereign::rlp_irf(rlp)

Estimate regime-dependent VAR, SVAR, or Proxy-SVAR

Description

Estimate a regime-dependent VAR (i.e. a state-dependent VAR), with an exogenous state indicator, of the specification:

Y_{t+1} = X_t \beta_{s_t} + \epsilon_t

where t is the time index, Y is the set of outcome vectors, X the design matrix (of p lagged values of Y), and s is a mutually exclusive state of the world observed at time t. When the regime vector is not supplied by the user, then a two-state regime series is estimated via random forest.

Usage

RVAR(
  data,
  horizon = 10,
  freq = "month",
  type = "const",
  p = 1,
  lag.ic = NULL,
  lag.max = NULL,
  regime = NULL,
  regime.method = "rf",
  regime.n = 2,
  structure = "short",
  instrument = NULL,
  instrumented = NULL
)

Arguments

Details

The regime-dependent VAR is a generalization of the popular threshold VAR - which trades off estimating a threshold value for an endogenous variable for accepting an exogenous regime that can be based on information from inside or outside of the system, with or without parametric assumptions, and with or without timing restrictions. Moreover, the RVAR may be extended to include structural shocks, including the use of instrumental variables.

State dependence. The RVAR augments the traditional VAR by allowing state-dependence in the coefficient matrix. The RVAR differs from the more common threshold VAR (TVAR), due to the fact that states are exegonesouly determined. As a result, the states (i.e. regimes) do not need to be based on information inside the model, moreover, regimes can be determined by any process the user determines best fits their needs. For example, regimes based on NBER dated recessions and expansions are based on a judgmental process considering hundreds of series, potentially none of which are in the VAR being modeled. Alternatively, a user may use unsupervised machine learning to assign regimes - this is the process the sovereign::regimes function facilitates.

Structural shocks. See Sims (1980) for details regarding the baseline vector-autoregression (VAR) model. The VAR may be augmented to become a structural VAR (SVAR) with one of three different structural identification strategies:

1. short-term impact restrictions via Cholesky decomposition, see Christiano et al (1999) for details (structure = 'short')

2. external instrument identification, i.e. a Proxy-SVAR strategy, see Mertens and Ravn (2013) for details (structure = 'IV')

3. or a combination of short-term and IV identification via Lunsford (2015) (structure = 'IV-short')

Note that including structure does not change the estimation of model coefficients or forecasts, but does change impulse response functions, forecast error variance decomposition, and historical decompositions. Historical decompositions will not be available for models using the 'IV' structure. Additionally note that only one instrument may be used in this estimation routine.

Value

List of lists, where each regime is a list with items:

1. data: data.frame with endogenous variables and 'date' column.

2. model: list with data.frame of model coefficients (in psuedo-companion form), data.frame of coefficient standard errors, integer of lags p, integer of horizons, string of frequency, string of deterministic term type, numeric of log-likelihood, regime indicator

3. forecasts: list of data.frames per horizon; data.frame with column for date (day the forecast was made), forecast.date (the date being forecasted), target (variable forecasted), and forecast

4. residuals: list of data.frames per horizon; data.frame of residuals

5. structure: string denoting which structural identification strategy will be used in analysis (or NA)

6. instrument: data.frame with 'date' column and 'instrument' column (or NULL)

7. instrumented: string denoting which column will be instrumted in 'IV' and 'IV-short' strategies (or NULL)

References

1. Christiano, Lawrence, Martin Eichenbaum, and Charles Evans "Monetary policy shocks: What have we learned and to what end?" Handbook of Macroeconomics, Vol 1, Part A, 1999.

2. Lunsford, Kurt "Identifying Structural VARs with a Proxy Variable and a Test for a Weak Proxy" 2015.

3. Mertens, Karel and Morten Ravn "The Dynamic Effects of Personal and Corporate Income Tax Changes in the United States" 2013.

4. Sims, Christopher "Macroeconomics and Reality" 1980.

See Also

VAR()

RVAR()

IRF()

FEVD()

HD()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)
 Data = dplyr::mutate(Data, reg = dplyr::if_else(AA > median(AA), 1, 0))

 # estimate regime-dependent VAR
  rvar =
    sovereign::RVAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      regime.method = 'rf',
      regime.n = 2,
      lag.ic = 'BIC',
      lag.max = 4)

 # impulse response functions
 rvar.irf = sovereign::rvar_irf(rvar)

 # forecast error variance decomposition
 rvar.fevd = sovereign::rvar_fevd(rvar)

 # historical shock decomposition
 rvar.hd = sovereign::rvar_hd(rvar)

Estimate VAR, SVAR, or Proxy-SVAR

Description

Estimate VAR, SVAR, or Proxy-SVAR

Usage

VAR(
  data,
  horizon = 10,
  freq = "month",
  type = "const",
  p = 1,
  lag.ic = NULL,
  lag.max = NULL,
  structure = "short",
  instrument = NULL,
  instrumented = NULL
)

Arguments

Details

See Sims (1980) for details regarding the baseline vector-autoregression (VAR) model. The VAR may be augmented to become a structural VAR (SVAR) with one of three different structural identification strategies:

1. short-term impact restrictions via Cholesky decomposition, see Christiano et al (1999) for details (structure = 'short')

2. external instrument identification, i.e. a Proxy-SVAR strategy, see Mertens and Ravn (2013) for details (structure = 'IV')

3. or a combination of short-term and IV identification via Lunsford (2015) (structure = 'IV-short')

Note that including structure does not change the estimation of model coefficients or forecasts, but does change impulse response functions, forecast error variance decomposition, and historical decompositions. Historical decompositions will not be available for models using the 'IV' structure. Additionally note that only one instrument may be used in this estimation routine.

Value

1. data: data.frame with endogenous variables and 'date' column.

2. model: list with data.frame of model coefficients (in psuedo-companion form), data.frame of coefficient standard errors, integer of lags p, integer of horizons, string of frequency, string of deterministic term type, numeric of log-likelihood

3. forecasts: list of data.frames per horizon; data.frame with column for date (day the forecast was made), forecast.date (the date being forecasted), target (variable forecasted), and forecast

4. residuals: list of data.frames per horizon; data.frame of residuals

5. structure: string denoting which structural identification strategy will be used in analysis (or NA)

6. instrument: data.frame with 'date' column and 'instrument' column (or NULL)

7. instrumented: string denoting which column will be instrumted in 'IV' and 'IV-short' strategies (or NA)

References

1. Christiano, Lawrence, Martin Eichenbaum, and Charles Evans "Monetary policy shocks: What have we learned and to what end?" Handbook of Macroeconomics, Vol 1, Part A, 1999.

2. Lunsford, Kurt "Identifying Structural VARs with a Proxy Variable and a Test for a Weak Proxy" 2015.

3. Mertens, Karel and Morten Ravn "The Dynamic Effects of Personal and Corporate Income Tax Changes in the United States" 2013.

4. Sims, Christopher "Macroeconomics and Reality" 1980.

See Also

VAR()

var_irf()

var_fevd()

var_hd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)

 # estimate VAR
  var =
    sovereign::VAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      lag.ic = 'BIC',
      lag.max = 4)

  # impulse response functions
  var.irf = sovereign::var_irf(var)

  # forecast error variance decomposition
  var.fevd = sovereign::var_fevd(var)

  # historical shock decomposition
  var.hd = sovereign::var_hd(var)

Lenza-Primiceri Covid Shock Correction

Description

Implement the deterministic volatility correction method of Lenza, Michele and Giorgio Primiceri "How to Estimate a VAR after March 2020" (2020) [NBER Working Paper]. Correction factors are estimated via maximum likelihood.

Usage

covid_volatility_correction(var, theta_initial = c(5, 2, 1.5, 0.8))

Arguments

Value

var object

See Also

VAR()

var_irf()

var_fevd()

var_hd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2018-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)

 # estimate VAR
 var =
   sovereign::VAR(
     data = Data,
     horizon = 10,
     freq = 'month',
     lag.ic = 'BIC',
     lag.max = 4)

# correct VAR for COVID shock
var = sovereign::covid_volatility_correction(var)

# impulse response functions
var.irf = sovereign::var_irf(var)

# forecast error variance decomposition
var.fevd = sovereign::var_fevd(var)

# historical shock decomposition
var.hd = sovereign::var_hd(var)

Estimate impulse response functions

Description

Estimate impulse response functions

Usage

lp_irf(lp, CI = c(0.1, 0.9), regime = NULL)

Arguments

Value

long-form data.frame with one row per target-shock-horizon identifier

See Also

LP()

lp_irf()

RLP()

rlp_irf()

Examples

  # simple time series
  AA = c(1:100) + rnorm(100)
  BB = c(1:100) + rnorm(100)
  CC = AA + BB + rnorm(100)
  date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
  Data = data.frame(date = date, AA, BB, CC)

  # local projection forecasts
  lp =
    sovereign::LP(
      data = Data,
      horizon = c(1:10),
      lag.ic = 'AIC',
      lag.max = 4,
      type =  'both',
      freq = 'month')

  # impulse response function
  irf = sovereign::lp_irf(lp)

Chart residuals

Description

Chart residuals

Usage

plot_error(residuals, series = NULL, verticle = FALSE)

Arguments

Value

grid of ggplot2 graphs

Chart FEVDs

Description

Chart FEVDs

Usage

plot_fevd(fevd, responses = NULL, verticle = FALSE)

Arguments

Value

grid of ggplot2 graphs

Chart forecasts

Description

Chart forecasts

Usage

plot_forecast(forecasts, series = NULL, verticle = FALSE)

Arguments

Value

grid of ggplot2 graphs

Chart HDs

Description

Chart HDs

Usage

plot_hd(hd, verticle = FALSE)

Arguments

Value

grid of ggplot2 graphs

Chart individual residuals

Description

Chart individual residuals

Usage

plot_individual_error(
  data,
  target,
  title = NULL,
  ylab = NULL,
  freq = NULL,
  zeroline = FALSE
)

Arguments

Value

ggplot2 chart

Plot an individual FEVD

Description

Plot an individual FEVD

Usage

plot_individual_fevd(fevd, response.var, title, ylab)

Arguments

Value

ggplot2 graph

Chart individual forecast

Description

Chart individual forecast

Usage

plot_individual_forecast(
  data,
  target,
  title = NULL,
  ylab = NULL,
  freq = NULL,
  zeroline = FALSE
)

Arguments

Value

ggplot2 chart

Plot an individual HD

Description

Plot an individual HD

Usage

plot_individual_hd(hd, target.var, title)

Arguments

Value

ggplot2 graph

Plot an individual IRF

Description

Plot an individual IRF

Usage

plot_individual_irf(irf, shock.var, response.var, title, ylab)

Arguments

Value

ggplot2 graph

Chart IRFs

Description

Chart IRFs

Usage

plot_irf(irf, shocks = NULL, responses = NULL, verticle = FALSE)

Arguments

Value

grid of ggplot2 graphs

Identify regimes via unsupervised ML algorithms

Description

Regime assignment (clustering) methods available include the unsupervised random forest, k-mean clustering, Fraley and Raftery Model-based clustering EM algorithm, and the Bai & Perron (2003) method for simultaneous estimation of multiple breakpoints.

Usage

regimes(data, method = "rf", regime.n = NULL)

Arguments

Value

data as a data.frame with a regime column assigning rows to mutually exclusive regimes

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)

 # estimate reigme
 regime =
  sovereign::regimes(
     data = Data,
     method = 'kmeans',
     regime.n = 3)

Estimate regime-dependent impulse response functions

Description

Estimate regime-dependent impulse response functions

Usage

rlp_irf(rlp, CI = c(0.1, 0.9))

Arguments

Value

list of long-form data.frame with one row per target-shock-horizon identifier

See Also

LP()

lp_irf()

RLP()

rlp_irf()

Examples

  # simple time series
  AA = c(1:100) + rnorm(100)
  BB = c(1:100) + rnorm(100)
  CC = AA + BB + rnorm(100)
  date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
  Data = data.frame(date = date, AA, BB, CC)
  # add regime
  Data = dplyr::mutate(Data, reg = dplyr::if_else(AA > median(AA), 1, 0))

  # local projection forecasts
  rlp =
    sovereign::RLP(
      data = Data,
      regime = 'reg',
      horizon = c(1:10),
      freq = 'month',
      p = 1,,
      type =  'const',
      NW = TRUE,
      NW_lags = 1,
      NW_prewhite = FALSE)

 # impulse response function
 rirf = sovereign::rlp_irf(rlp)

Estimate regime-dependent forecast error variance decomposition

Description

Estimate forecast error variance decomposition for RVARs with either short or 'IV-short' structural errors.

Usage

rvar_fevd(rvar, horizon = 10, scale = TRUE)

Arguments

Value

list, each regime returns its own long-form data.frame

See Also

VAR()

var_irf()

var_fevd()

var_hd()

RVAR()

rvar_irf()

rvar_fevd()

rvar_hd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)
 Data = dplyr::mutate(Data, reg = dplyr::if_else(AA > median(AA), 1, 0))

 # estimate VAR
  rvar =
    sovereign::RVAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      regime.method = 'rf',
      regime.n = 2,
      lag.ic = 'BIC',
      lag.max = 4)

# impulse response functions
rvar.irf = sovereign::rvar_irf(rvar)

# forecast error variance decomposition
rvar.fevd = sovereign::rvar_fevd(rvar)

# historical shock decomposition
rvar.hd = sovereign::rvar_hd(rvar)

Estimate regime-dependent historical decomposition

Description

Estimate historical decomposition for RVARs with either short or 'IV-short' structural errors.

Usage

rvar_hd(rvar)

Arguments

Value

long form data.frames

See Also

VAR()

var_irf()

var_fevd()

var_hd()

RVAR()

rvar_irf()

rvar_fevd()

rvar_hd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)
 Data = dplyr::mutate(Data, reg = dplyr::if_else(AA > median(AA), 1, 0))

 # estimate VAR
  rvar =
    sovereign::RVAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      regime.method = 'rf',
      regime.n = 2,
      lag.ic = 'BIC',
      lag.max = 4)

# impulse response functions
rvar.irf = sovereign::rvar_irf(rvar)

# forecast error variance decomposition
rvar.fevd = sovereign::rvar_fevd(rvar)

# historical shock decomposition
rvar.hd = sovereign::rvar_hd(rvar)

Estimate regime-dependent impulse response functions

Description

Estimate regime-dependent impulse response functions

Usage

rvar_irf(
  rvar,
  horizon = 10,
  CI = c(0.1, 0.9),
  bootstrap.type = "auto",
  bootstrap.num = 100,
  bootstrap.parallel = FALSE,
  bootstrap.cores = -1
)

Arguments

Value

list of regimes, each with data.frame of columns target, shock, horizon, response.lower, response, response.upper

See Also

VAR()

var_irf()

var_fevd()

RVAR()

rvar_irf()

rvar_fevd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)
 Data = dplyr::mutate(Data, reg = dplyr::if_else(AA > median(AA), 1, 0))

 # estimate VAR
  rvar =
    sovereign::RVAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      regime.method = 'rf',
      regime.n = 2,
      lag.ic = 'BIC',
      lag.max = 4)

 # impulse response functions
 rvar.irf = sovereign::rvar_irf(rvar)

 # forecast error variance decomposition
 rvar.fevd = sovereign::rvar_fevd(rvar)

 # historical shock decomposition
 rvar.hd = sovereign::rvar_hd(rvar)

Estimate forecast error variance decomposition

Description

Estimate forecast error variance decomposition for VARs with either short or 'IV-short' structural errors.

Usage

var_fevd(var, horizon = 10, scale = TRUE)

Arguments

Value

long-form data.frame

See Also

VAR()

var_irf()

var_fevd()

var_hd()

RVAR()

rvar_irf()

rvar_fevd()

rvar_hd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)

 # estimate VAR
  var =
    sovereign::VAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      lag.ic = 'BIC',
      lag.max = 4)

# impulse response functions
var.irf = sovereign::var_irf(var)

# forecast error variance decomposition
var.fevd = sovereign::var_fevd(var)

# historical shock decomposition
var.hd = sovereign::var_hd(var)

Estimate historical decomposition

Description

Estimate historical decomposition for VARs with either short or 'IV-short' structural errors.

Usage

var_hd(var)

Arguments

Value

long-from data.frame

See Also

VAR()

var_irf()

var_fevd()

var_hd()

RVAR()

rvar_irf()

rvar_fevd()

rvar_hd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)

 # estimate VAR
  var =
    sovereign::VAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      lag.ic = 'BIC',
      lag.max = 4)

# impulse response functions
var.irf = sovereign::var_irf(var)

# forecast error variance decomposition
var.fevd = sovereign::var_fevd(var)

# historical shock decomposition
var.hd = sovereign::var_hd(var)

Estimate impulse response functions

Description

Estimate impulse response functions

Usage

var_irf(
  var,
  horizon = 10,
  CI = c(0.1, 0.9),
  bootstrap.type = "auto",
  bootstrap.num = 100,
  bootstrap.parallel = FALSE,
  bootstrap.cores = -1
)

Arguments

Value

data.frame with columns target, shock, horizon, response.lower, response, response.upper

See Also

VAR()

var_irf()

var_fevd()

var_hd()

RVAR()

rvar_irf()

rvar_fevd()

rvar_hd()

Examples

 # simple time series
 AA = c(1:100) + rnorm(100)
 BB = c(1:100) + rnorm(100)
 CC = AA + BB + rnorm(100)
 date = seq.Date(from = as.Date('2000-01-01'), by = 'month', length.out = 100)
 Data = data.frame(date = date, AA, BB, CC)

 # estimate VAR
  var =
    sovereign::VAR(
      data = Data,
      horizon = 10,
      freq = 'month',
      lag.ic = 'BIC',
      lag.max = 4)

 # impulse response functions
 var.irf = sovereign::var_irf(var)

 # forecast error variance decomposition
 var.fevd = sovereign::var_fevd(var)

 # historical shock decomposition
 var.hd = sovereign::var_hd(var)