TS_diagnostics_plot: Plot the diagnostics of the parameters fit in a TS model

In weecology/LDATS: Latent Dirichlet Allocation Coupled with Time Series Analyses

Description

Plot 4-panel figures (showing trace plots, posterior ECDF, posterior density, and iteration autocorrelation) for each of the parameters (change point locations and regressors) fitted within a multinomial time series model (fit by TS).

eta_diagnostics_plots creates the diagnostic plots for the regressors (etas) of a time series model.

rho_diagnostics_plots creates the diagnostic plots for the change point locations (rho) of a time series model.

Usage

TS_diagnostics_plot(x, interactive = TRUE)

eta_diagnostics_plots(x, interactive)

rho_diagnostics_plots(x, interactive)

Arguments

x	Object of class TS_fit, generated by TS to have its diagnostics plotted.
interactive	logical input, should be codeTRUE unless testing.

Value

NULL.

Examples

  data(rodents)
  document_term_table <- rodents$document_term_table
  document_covariate_table <- rodents$document_covariate_table
  LDA_models <- LDA_set(document_term_table, topics = 2)[[1]]
  data <- document_covariate_table
  data$gamma <- LDA_models@gamma
  weights <- document_weights(document_term_table)
  TSmod <- TS(data, gamma ~ 1, nchangepoints = 1, "newmoon", weights)
  TS_diagnostics_plot(TSmod)

weecology/LDATS documentation built on March 28, 2020, 11:20 a.m.