dfm: Bayesian Dynamic Factor Model Objects

Description

dfm is used to create objects of class "dfm".

A plot function for objects of class "dfm".

Usage

dfm(x, lambda = NULL, fac, sigma_u = NULL, a = NULL, sigma_v = NULL)
# S3 method for dfm
plot(x, ci = 0.95, ...)

Value

An object of class "dfm" containing the following components, if specified:

x: the standardised time-series object of observable variables.
lambda: an $S \times MN$ "mcmc" object of draws of factor loadings of the measurement equation.
factor: an $S \times NT$ "mcmc" object of draws of factors.
sigma_u: an $S \times M$ "mcmc" object of variance draws of the measurement equation.
a: an $S \times pN^2$ "mcmc" object of coefficient draws of the transition equation.
sigma_v: an $S \times N$ "mcmc" object of variance draws of the transition equation.
specifications: a list containing information on the model specification.

Arguments

x: an object of class "dfm", usually, a result of a call to dfm.
lambda: an $MN \times S$ matrix of MCMC coefficient draws of factor loadings of the measurement equation.
fac: an $NT \times S$ matrix of MCMC draws of the factors in the transition equation, where the first N rows correspond to the N factors in period 1 and the next N rows to the factors in period 2 etc.
sigma_u: an $M \times S$ matrix of MCMC draws for the error variances of the measurement equation.
a: a $pN^2 \times S$ matrix of MCMC coefficient draws of the transition equation.
sigma_v: an $N \times S$ matrix of MCMC draws for the error variances of the transition equation.
ci: interval used to calculate credible bands.
...: further graphical parameters.

Details

The function produces a standardised object from S draws of a Gibbs sampler (after the burn-in phase) for the dynamic factor model (DFM) with measurement equation $$x_t = \lambda f_t + u_t,$$ where $x_t$ is an $M \times 1$ vector of observed variables, $f_t$ is an $N \times 1$ vector of unobserved factors and $\lambda$ is the corresponding $M \times N$ matrix of factor loadings. $u_t$ is an $M \times 1$ error term.

The transition equation is $$f_t = \sum_{i=1}^{p} A_i f_{t - i} + v_t,$$ where $A_i$ is an $N \times N$ coefficient matrix and $v_t$ is an $N \times 1$ error term.

Examples

Run this code


# Load data
data("bem_dfmdata")

# Generate model data
model <- gen_dfm(x = bem_dfmdata, p = 1, n = 1,
                 iterations = 20, burnin = 10)
# Number of iterations and burnin should be much higher.

# Add prior specifications
model <- add_priors(model,
                    lambda = list(v_i = .01),
                    sigma_u = list(shape = 5, rate = 4),
                    a = list(v_i = .01),
                    sigma_v = list(shape = 5, rate = 4))

# Obtain posterior draws
object <- dfmpost(model)


# Load data
data("bem_dfmdata")

# Generate model data
model <- gen_dfm(x = bem_dfmdata, p = 1, n = 1,
                 iterations = 20, burnin = 10)
# Number of iterations and burnin should be much higher.

# Add prior specifications
model <- add_priors(model,
                    lambda = list(v_i = .01),
                    sigma_u = list(shape = 5, rate = 4),
                    a = list(v_i = .01),
                    sigma_v = list(shape = 5, rate = 4))

# Obtain posterior draws
object <- draw_posterior(model)

# Plot factors
plot(object)

Run the code above in your browser using DataLab