mlts_plot {mlts}

Plot results of mlts

Description

Plot results of mlts

Usage

mlts_plot(
  fit,
  type = c("fe", "re", "re.cor"),
  bpe = c("median", "mean"),
  what = c("all", "Fixed effect", "Random effect SD", "RE correlation",
    "Outcome prediction", "RE prediction", "Item intercepts", "Loading",
    "Measurement Error SD"),
  sort_est = NULL,
  xlab = NULL,
  ylab = NULL,
  facet_ncol = 1,
  dot_size = 1,
  dot_color = "black",
  dot_shape = 1,
  errorbar_color = "black",
  errorbar_width = 0.3,
  add_true = FALSE,
  true_color = "red",
  true_shape = 22,
  true_size = 1,
  hide_xaxis_text = TRUE,
  par_labels = NULL,
  labels_as_expressions = FALSE
)

Arguments

fit

An object of class mlts.fit

type

Type of plot. type = "fe" (Default) Forest-plot of model coefficients. type = "re" Plot of individual (random) effects type = "re.cor" Combined plot depicting the distribution of individual parameter estimates (posterior summary statistics as provided by bpe), as well as bivariate scatter plots.

bpe

The Bayesian point estimate is, by default, the median of the posterior distribution (bpe = "median"). Set bpe = "mean" to use the mean of the posterior distribution as point estimates.

what

Character. For type = "fe", indicate which parameters should be included in the plot by setting what to "all" (the default), or one (or multiple) of "Fixed effect", "Random effect SD", "RE correlation", "Outcome prediction", "RE prediction", "Item intercepts", "Loading", or "Measurement Error SD".

sort_est

Add parameter label for sorting of random effects.

xlab

Title for the x axis.

ylab

Title for the y axis.

facet_ncol

Number of facet columns (see ggplot2::facet_grid).

dot_size

numeric, size of the dots that indicate the point estimates.

dot_color

character. indicating the color of the point estimates.

dot_shape

numeric. shape of the dots that indicate the point estimates.

errorbar_color

character. Color of error bars.

errorbar_width

integer. Width of error bars.

add_true

logical. If model was fitted with simulated data using mlts_sim, true population parameter values can be plotted as reference by setting the argument ot TRUE.

true_color

character. Color of points depicting true population parameter used in the data generation.

true_shape

integer. Shape of points depicting true population parameter used in the data generation.

true_size

integer. Size of points depicting true population parameter used in the data generation.

hide_xaxis_text

logical. Hide x-axis text if set to TRUE.

par_labels

character vector. User-specified labels for random effect parameters can be specified.

labels_as_expressions

logical. Should parameter names on plot labels be printed as mathematical expressions? Defaults to FALSE. Still experimental.

Value

Returns a ggplot-object .

Examples

# build simple vector-autoregressive mlts model for two time-series variables
var_model <- mlts_model(q = 2)

# fit model with (artificial) dataset ts_data
fit <- mlts_fit(
  model = var_model,
  data = ts_data,
  ts = c("Y1", "Y2"), # time-series variables
  id = "ID", # identifier variable
  time = "time",
  tinterval = 1 # interval for approximation of continuous-time dynamic model,
)

# inspect model summary
mlts_plot(fit, type = "fe", what = "Fixed effect")