bsts (version 0.7.0)

plot.bsts.mixed: Plotting functions for mixed frequency Bayesian structural time series

Description

Functions for plotting the output of a mixed frequency time series regression.

Usage

# S3 method for bsts.mixed
plot(x,
                            y = c("state", "components",
                                  "coefficients", "predictors", "size"),
                            ...)
   PlotBstsMixedState(bsts.mixed.object,
                      burn = SuggestBurn(.1, bsts.mixed.object),
                      time = NULL,
                      fine.scale = FALSE,
                      style = c("dynamic", "boxplot"),
                      trim.left = NULL,
                      trim.right = NULL,
                      ...)
   PlotBstsMixedComponents(bsts.mixed.object,
                           burn = SuggestBurn(.1, bsts.mixed.object),
                           time = NULL,
                           same.scale = TRUE,
                           fine.scale = FALSE,
                           style = c("dynamic", "boxplot"),
                           layout = c("square", "horizontal", "vertical"),
                           ylim = NULL,
                           trim.left = NULL,
                           trim.right = NULL,
                           ...)

Arguments

x

An object of class bsts.mixed.

bsts.mixed.object

An object of class bsts.mixed.

y

A character string indicating the aspect of the model that should be plotted.

burn

The number of MCMC iterations to discard as burn-in.

time

An optional vector of values to plot against. If missing, the default is to obtain the time scale from the original time series.

fine.scale

Logical. If TRUE then the plots will be at the weekly level of granularity. If FALSE they will be at the monthly level.

same.scale

Logical. If TRUE then all the state components will be plotted with the same scale on the vertical axis. If FALSE then each component will get its own scale for the vertical axis.

style

character. If "dynamic" then a dynamic distribution plot will be shown. If "box" then boxplots will be shown.

layout

A character string indicating whether the plots showing components of state should be laid out in a square, horizontally, or vertically.

trim.left

A logical indicating whether the first (presumedly partial) observation in the aggregated state time series should be removed.

trim.right

A logical indicating whether the last (presumedly partial) observation in the aggregated state time series should be removed.

ylim

Limits for the vertical axis. Optional.

...

Additional arguments to be passed to PlotDynamicDistribution or TimeSeriesBoxplot

Value

These functions are called for their side effect, which is to produce a plot on the current graphics device.

Details

PlotBstsMixedState plots the aggregate state contribution (including regression effects) to the mean, while PlotBstsComponents plots the contribution of each state component separately. PlotBstsCoefficients creates a significance plot for the predictors used in the state space regression model.

See Also

bsts.mixed PlotDynamicDistribution plot.lm.spike PlotBstsSize

Examples

<!-- % TODO(stevescott):  fix flaky mixed.frequency examples in .Rd files -->
## Not run: ------------------------------------
# ## This example is flaky and needs to be fixed
#   data <- SimulateFakeMixedFrequencyData(nweeks = 104, xdim = 20)
#   state.specification <- AddLocalLinearTrend(list(), data$coarse.target)
#   weeks <- index(data$predictor)
#   months <- index(data$coarse.target)
#   which.month <- MatchWeekToMonth(weeks, months[1])
#   membership.fraction <- GetFractionOfDaysInInitialMonth(weeks)
#   contains.end <- WeekEndsMonth(weeks)
# 
#   model <- bsts.mixed(target.series = data$coarse.target,
#                       predictors = data$predictors,
#                       membership.fraction = membership.fraction,
#                       contains.end = contains.end,
#                       which.coarse = which.month,
#                       state.specification = state.specification,
#                       niter = 500)
# 
#   plot(model, "state")
#   plot(model, "components")
## ---------------------------------------------