DHARMa (version 0.2.4)

plot.DHARMa: DHARMa standard residual plots

Description

This function creates standard plots for the simulated residuals

Usage

# S3 method for DHARMa
plot(x, rank = TRUE, ...)

Arguments

x

an object with simualted residuals created by simulateResiduals

rank

if T (default), the values of pred will be rank transformed. This will usually make patterns easier to spot visually, especially if the distribution of the predictor is skewed.

...

further options for plotResiduals. Consider in particular parameters quantreg, rank and asFactor. xlab, ylab and main cannot be changed when using plotSimulatedResiduals, but can be changed when using plotResiduals.

Details

The function creates two plots. To the left, a qq-uniform plot to detect deviations from overall uniformity of the residuals (calling plotQQunif), and to the right, a plot of residuals against predicted values (calling plotResiduals). Outliers are highlighted in red (for more on oultiers, see testOutliers). For a correctly specified model, we would expect

a) a straight 1-1 line in the uniform qq-plot -> evidence for an overal uniform (flat) distribution of the residuals

b) uniformity of residuals in the vertical direction in the res against predictor plot

Deviations of this can be interpreted as for a linear regression. See the vignette for detailed examples.

To provide a visual aid in detecting deviations from uniformity in y-direction, the plot of the residuals against the predited values also performs an (optional) quantile regression, which provides 0.25, 0.5 and 0.75 quantile lines across the plots. These lines should be straight, horizontal, and at y-values of 0.25, 0.5 and 0.75. Note, however, that some deviations from this are to be expected by chance, even for a perfect model, especially if the sample size is small. See further comments on this plot, and options, in plotResiduals

The quantile regression can take some time to calculate, especially for larger datasets. For that reason, quantreg = F can be set to produce a smooth spline instead. This is default for n > 2000.

See Also

plotResiduals, plotQQunif

Examples

# NOT RUN {
testData = createData(sampleSize = 200, family = poisson(), 
                      randomEffectVariance = 1, numGroups = 5)
fittedModel <- glm(observedResponse ~ Environment1, 
                   family = "poisson", data = testData)
simulationOutput <- simulateResiduals(fittedModel = fittedModel)

######### main plotting function #############

# for all functions, quantreg = T will be more
# informative, but slower

plot(simulationOutput, quantreg = FALSE)

#############  Distribution  ######################

plotQQunif(simulationOutput = simulationOutput)

hist(simulationOutput )

#############  residual plots  ###############

# rank transformation, using a simulationOutput
plotResiduals(simulationOutput, rank = TRUE, quantreg = FALSE)

# residual vs predictors, using explicit values for pred, residual 
plotResiduals(pred = testData$Environment1, 
              residuals = simulationOutput$scaledResiduals, quantreg = FALSE)

# if pred is a factor, or asFactor = T, will produce a boxplot
plotResiduals(pred = testData$group, residuals = simulationOutput$scaledResiduals, 
              quantreg = FALSE, asFactor = TRUE)

# All these options can also be provided to the main plotting function
plot(simulationOutput, quantreg = FALSE, rank = FALSE)

# If you want to plot summaries per group, use
simulationOutput = recalculateResiduals(simulationOutput, group = testData$group)
plot(simulationOutput, asFactor = TRUE) # we see one residual point per RE


# }