Learn R Programming

bsts (version 0.9.5)

plot.bsts.prediction: Plot predictions from Bayesian structural time series

Description

Plot the posterior predictive distribution from a bsts prediction object.

Usage

# S3 method for bsts.prediction
plot(x,
     y = NULL,
     burn = 0,
     plot.original = TRUE,
     median.color = "blue",
     median.type = 1,
     median.width = 3,
     interval.quantiles = c(.025, .975),
     interval.color = "green",
     interval.type = 2,
     interval.width = 2,
     style = c("dynamic", "boxplot"),
     ylim = NULL,
     ...)

Arguments

x

An object of class bsts.prediction created by calling predict on a bsts object.

y

A dummy argument necessary to match the signature of the plot generic function. This argument is unused.

plot.original

Logical or numeric. If TRUE then the prediction is plotted after a time series plot of the original series. If FALSE, the prediction fills the entire plot. If numeric, then it specifies the number of trailing observations of the original time series to plot in addition to the predictions.

burn

The number of observations you wish to discard as burn-in from the posterior predictive distribution. This is in addition to the burn-in discarded using predict.bsts.

median.color

The color to use for the posterior median of the prediction.

median.type

The type of line (lty) to use for the posterior median of the prediction.

median.width

The width of line (lwd) to use for the posterior median of the prediction.

interval.quantiles

The lower and upper limits of the credible interval to be plotted.

interval.color

The color to use for the upper and lower limits of the 95% credible interval for the prediction.

interval.type

The type of line (lty) to use for the upper and lower limits of the 95% credible inerval for of the prediction.

interval.width

The width of line (lwd) to use for the upper and lower limits of the 95% credible inerval for of the prediction.

style

Either "dynamic", for dynamic distribution plots, or "boxplot", for box plots. Partial matching is allowed, so "dyn" or "box" would work, for example.

ylim

Limits on the vertical axis.

...

Extra arguments to be passed to PlotDynamicDistribution and lines.

Value

Returns NULL.

Details

Plots the posterior predictive distribution described by x using a dynamic distribution plot generated by PlotDynamicDistribution. Overlays the posterior median and 95% prediction limits for the predictive distribution.

See Also

bsts PlotDynamicDistribution plot.lm.spike

Examples

Run this code
# NOT RUN {
  data(AirPassengers)
  y <- log(AirPassengers)
  ss <- AddLocalLinearTrend(list(), y)
  ss <- AddSeasonal(ss, y, nseasons = 12)
  model <- bsts(y, state.specification = ss, niter = 500)
  pred <- predict(model, horizon = 12, burn = 100)
  plot(pred)
# }

Run the code above in your browser using DataLab