plotTimeSeriesResults {BayesianTools}

Creates a time series plot typical for an MCMC / SMC fit

Description

Creates a time series plot typical for an MCMC / SMC fit

Usage

plotTimeSeriesResults(
  sampler,
  model,
  observed,
  error = NULL,
  plotResiduals = TRUE,
  start = 1,
  prior = FALSE,
  ...
)

Arguments

sampler

Either a) a matrix b) an MCMC object (list or not), or c) an SMC object

model

function that calculates model predictions for a given parameter vector

observed

observed values as vector

error

function with signature f(mean, par) that generates observations with error (error = stochasticity according to what is assumed in the likelihood) from mean model predictions. Par is a vector from the matrix with the parameter samples (full length). f needs to know which of these parameters are parameters of the error function. See example in VSEM

plotResiduals

logical determining whether residuals should be plotted

start

numeric start value for the plot (see getSample)

prior

if a prior sampler is implemented, setting this parameter to TRUE will draw model parameters from the prior instead of the posterior distribution

...

further arguments passed to plot

Author(s)

Florian Hartig

See Also

getPredictiveIntervals

Examples

# Create time series
ts <- VSEMcreatePAR(1:100)

# create fake "predictions"
pred <- ts + rnorm(length(ts), mean = 0, sd = 2)

# plot time series
par(mfrow=c(1,2))

plotTimeSeries(observed = ts, main="Observed")
plotTimeSeries(observed = ts, predicted = pred, main = "Observed and predicted")

par(mfrow=c(1,1))