R: Parallel hierarchical Bayesian vector autoregression

par_bvar {BVAR}

R Documentation

Parallel hierarchical Bayesian vector autoregression

Description

Wrapper for bvar to simplify parallel computation via parLapply. Make sure to properly start and stop the provided cluster.

Usage

par_bvar(
  cl,
  n_runs = length(cl),
  data,
  lags,
  n_draw = 10000L,
  n_burn = 5000L,
  n_thin = 1L,
  priors = bv_priors(),
  mh = bv_mh(),
  fcast = NULL,
  irf = NULL
)

Arguments

`cl`	A `cluster` object obtained from `makeCluster`.
`n_runs`	The number of parallel runs to calculate. Defaults to the length of cl, i.e. the number of registered nodes.
`data`	Numeric matrix or dataframe. Note that observations are expected to be ordered from earliest to latest, and variables in the columns.
`lags`	Integer scalar. Lag order of the model.
`n_draw`, `n_burn`	Integer scalar. The number of iterations to (a) cycle through and (b) burn at the start.
`n_thin`	Integer scalar. Every n_thin'th iteration is stored. For a given memory requirement thinning reduces autocorrelation, while increasing effective sample size.
`priors`	Object from `bv_priors` with prior settings. Used to adjust the Minnesota prior, add custom dummy priors, and choose hyperparameters for hierarchical estimation.
`mh`	Object from `bv_mh` with settings for the Metropolis-Hastings step. Used to tune automatic adjustment of the acceptance rate within the burn-in period, or manually adjust the proposal variance.
`fcast`	Object from `bv_fcast` with forecast settings. Options include the horizon and settings for conditional forecasts i.e. scenario analysis. May also be calculated ex-post using `predict.bvar`.
`irf`	Object from `bv_irf` with settings for the calculation of impulse responses and forecast error variance decompositions. Options include the horizon and different identification schemes. May also be calculated ex-post using `irf.bvar`.

Value

Returns a list of class bvar_chain with bvar objects.

Examples


library("parallel")

cl <- makeCluster(2L)

# Access a subset of the fred_qd dataset
data <- fred_qd[, c("CPIAUCSL", "UNRATE", "FEDFUNDS")]
# Transform it to be stationary
data <- fred_transform(data, codes = c(5, 5, 1), lag = 4)

# A singular run using one lag, default settings and very few draws
x <- bvar(data, lags = 1, n_draw = 1000L, n_burn = 200L, verbose = FALSE)

# Two parallel runs
y <- par_bvar(cl, n_runs = 2,
  data = data, lags = 1, n_draw = 1000L, n_burn = 200L)

stopCluster(cl)

# Plot lambda for all of the runs
## Not run: 
plot(x, type = "full", vars = "lambda", chains = y)

# Convert the hyperparameter lambda to a coda mcmc.list object
coda::as.mcmc(y, vars = "lambda")

## End(Not run)