MixPlot: Plotting univariable GLMM

In MixedPsy: Statistical Tools for the Analysis of Psychophysical Data

Description

Plot binomial data and the fitted GLMM (object of class xplode).

Usage

MixPlot(xplode.obj, pf = 1, p05line = F, x.range, x.ref, col = F,
  x.label = "Stimulus Intensity", y.label = "Predicted Response")

Arguments

xplode.obj	an object of class xplode
pf	integer: for multivariable GLMM including one factorial predictor, the level number to be plotted
p05line	logical, should be an horizontal and a vertical line added? the horizontal line is fixed at P(Y = 1) = 0.5.
x.range	a vector of length two specifying the range for model predictions
x.ref	if p05line = T, this is the position of the vertical line on the x axis
col	logical, if TRUE a different color will be used for different clusters/participants
x.label, y.label	label for the x and the y axes. If not specified, x.labels = ""Stimulus Intensity", y.label = "Predicted Response"

Value

a data.frame object including the intercept and slope for each participant (algebraic sum of the fixed effects and the modes of the random effects) and the color number for the plot.

Note

The function is currently only working with GLMM including maximum three random effects (random intercept, random slope and covariance of the two)

See Also

xplode objects of class xplode.obj.

Examples

library(lme4)
data(vibro_exp3)
formula.mod <- cbind(faster, slower) ~ speed + (1 + speed| subject)
mod <- glmer(formula = formula.mod, family = binomial(link = "probit"),
              data = vibro_exp3[vibro_exp3$vibration == 0,])
define.mod <- list(pf1 = list(intercept = 1, slope = 2))
xplode.mod <- xplode(model = mod, name.cont = "speed", define.pf = define.mod)
myplot <- MixPlot(xplode.mod, pf = 1,  p05line = FALSE, x.ref = 8.5, x.range = c(1,16),
                  col = TRUE, x.label = "Stimulus Speed", y.label = "Predicted Response")

MixedPsy documentation built on May 2, 2019, 3:40 p.m.