rating.emmeans: EMMeans for Cumulative Link (Mixed) Models

In RVAideMemoire: Testing and Plotting Procedures for Biostatistics

EMMeans for Cumulative Link (Mixed) Models

Description

Extracts EMMeans (produced by emmeans) from Cumulative Link (Mixed) Models (produced by clm or clmm), with different possible formats.

Usage

rating.emmeans(emm, type = c("prob", "cumprob", "class1", "class2"), level = 0.9)

Arguments

emm	object returned by emmeans applied on a clm or clmm object.
type	type of output to be returned: "prob" (default) gives probability of each rating, "cumprob" gives cumulative probabilities (Pi is probability to be <= to rating i), "class1" gives the most probable rating and "class2" gives the first rating for which the cumulative probability is >= to level.
level	used only for type "class2" (see type).

Details

A factor named cut must have been called in emmeans, to compute EMMeans per cut point (i.e. rating). Additionally, the argument mode of emmeans must have been set to "linear.predictor". Finally, the call to emmeans is typically like emmeans(model,~factor|cut,mode="linear.predictor") where factor is the factor (or interaction) giving levels for which EMMeans have to be computed.

Author(s)

Maxime HERVE <[e-mail]>

See Also

emmeans, clm, clmm

Examples

if (require("ordinal",quietly=TRUE) & require("emmeans",quietly=TRUE)) {
  model <- clm(rating~contact*temp,data=wine)
  EMM <- emmeans(model,~contact:temp|cut,mode="linear.predictor")

  # Probabilities
  rating.emmeans(EMM)

  # Cumulative probabilities
  rating.emmeans(EMM,type="cumprob")

  # Most probable rating
  rating.emmeans(EMM,type="class1")
}

RVAideMemoire documentation built on Aug. 8, 2025, 6:34 p.m.