plot_eta: Plot the time series data and the changepoints

In yingboli/BayesMDL: Bayesian MDL for Multiple Changepoint Detection

Description

Create a plot, with time series data x shown in points, linear trends under the selected changepoint model in blue lines, estimated changepoints in verticle dashed blue lines, and fitted value (including seasonal means and linear trends) in a purple line. Optional residual plots can also be plotted.

Usage

plot_eta(x, dates, varname = NULL, current = NULL, A = NULL,
  scale_trend_design = NULL, eta = NULL, seasonal_cycles = NULL,
  mean_and_trend = NULL, plot_res = FALSE, yw_phi = NULL, ...)

Arguments

x	The time series data, a numeric vector of length n.
dates	The dates records are observed, a POSIXlt vector. It should have the mon component for months, and the year component for years. See also strptime.
varname	The name of the variable x, a character.
current	A list object representing a changepoint model. It contains the following components: eta, xi, inference (output of the fit_eta function), change_eta, and change_xi.
A	The design matrix for the nuisance coefficients in the linear model. It is usually the matrix of seasonal indicators, or the design matrix for harmonic regression with a column of all 1 for intercept.
scale_trend_design	The factor multiplied to the design matrix of trend. Default is 1/50.
eta	A multiple changepoint configuration, i.e., model. It is a 0/1 indicator vector of length n, with the first p elemenets always being 0.
seasonal_cycles	Estimated seasonal means, a numeric vector of length n.
mean_and_trend	Estimated piecewise linear fits, a numeric vector of length n.
plot_res	Logical, whether residual plots will be added after the main plots. If TRUE, then the following four plots will be added: scatterplot and acf plot of the linear model residuals, and scatterplot and acf plot fo the white noise estimates.
yw_phi	Yule walker estimator of AR coefficients, a vector of length p; must be non-NULL if plot_res == TRUE and is.null(current).
...	Other arguments for the plot function.

Details

Two sets of inputs can be used:

1. Either current, A, scale_trend_design,

2. Or eta, seasonal_cycles, mean_and_trend.

When used, every inputs in that set must but non-NULL, while all inputs in the other set must be NULL.

yingboli/BayesMDL documentation built on May 29, 2019, 12:18 p.m.