plot_em_classifications: Plot EM classifications

In timothy-barry/glmeiv: Implements the GLM-EIV model and method

Plot EM classifications

Description

Creates a histogram containing the EM estimates for m_perturbation colored by type.

Usage

plot_em_classifications(
  em_classifications,
  sim_spec,
  grid_row_id,
  categories = c("confident-plausible", "confident-implausible", "unconfident-plausible",
    "unconfident-implausible"),
  parameter = "m_perturbation"
)

Arguments

em_classifications	dataframe outputted by obtain_valid_ids
sim_spec	a simulatr specifier object (to supply the ground truth)
grid_row_id	grid_row_id giving row to plot
categories	classification categories to include in plot
parameter	parameter to make histogram for

Details

There are four categories: the cartesian product of (confident vs. unconfident) and (pluasible vs. implausible). An estimate is "confident" if the posterior membership probabilities are sufficiently spread out (see function obtain valid IDs); and estimate is "plausible" if the estimates themselves are in biologically realistic ranges. Valid IDs are those that are both confident and plausible.

Value

a histogram (in ggplot format)

timothy-barry/glmeiv documentation built on Jan. 30, 2024, 3:46 p.m.