R/cplot.R
, R/cplot_clm.R
, R/cplot_glm.R
, and 4 more
cplot.Rd
Draw one or more conditional effects plots reflecting predictions or marginal effects from a model, conditional on a covariate. Currently methods exist for “lm”, “glm”, “loess” class models.
cplot(object, ...) # S3 method for default cplot(object, x = attributes(terms(object))[["term.labels"]][1L], dx = x, what = c("prediction", "effect"), data = prediction::find_data(object), type = c("response", "link"), vcov = stats::vcov(object), at, n = 25L, xvals = prediction::seq_range(data[[x]], n = n), level = 0.95, draw = TRUE, xlab = x, ylab = if (match.arg(what) == "prediction") paste0("Predicted value") else paste0("Marginal effect of ", dx), xlim = NULL, ylim = NULL, lwd = 1L, col = "black", lty = 1L, se.type = c("shade", "lines", "none"), se.col = "black", se.fill = grDevices::gray(0.5, 0.5), se.lwd = lwd, se.lty = if (match.arg(se.type) == "lines") 1L else 0L, factor.lty = 0L, factor.pch = 19L, factor.col = se.col, factor.fill = factor.col, factor.cex = 1L, xaxs = "i", yaxs = xaxs, las = 1L, scatter = FALSE, scatter.pch = 19L, scatter.col = se.col, scatter.bg = scatter.col, scatter.cex = 0.5, rug = TRUE, rug.col = col, rug.size = -0.02, ...) # S3 method for clm cplot(object, x = attributes(terms(object))[["term.labels"]][1L], dx = x, what = c("prediction", "classprediction", "stackedprediction", "effect"), data = prediction::find_data(object), type = c("response", "link"), vcov = stats::vcov(object), at, n = 25L, xvals = seq_range(data[[x]], n = n), level = 0.95, draw = TRUE, xlab = x, ylab = if (match.arg(what) == "effect") paste0("Marginal effect of ", dx) else paste0("Predicted value"), xlim = NULL, ylim = if (match.arg(what) %in% c("prediction", "stackedprediction")) c(0, 1.04) else NULL, lwd = 1L, col = "black", lty = 1L, factor.lty = 1L, factor.pch = 19L, factor.col = col, factor.fill = factor.col, factor.cex = 1L, xaxs = "i", yaxs = xaxs, las = 1L, scatter = FALSE, scatter.pch = 19L, scatter.col = factor.col, scatter.bg = scatter.col, scatter.cex = 0.5, rug = TRUE, rug.col = col, rug.size = -0.02, ...) # S3 method for glm cplot(object, x = attributes(terms(object))[["term.labels"]][1L], dx = x, what = c("prediction", "effect"), data = prediction::find_data(object), type = c("response", "link"), vcov = stats::vcov(object), at, n = 25L, xvals = prediction::seq_range(data[[x]], n = n), level = 0.95, draw = TRUE, xlab = x, ylab = if (match.arg(what) == "prediction") paste0("Predicted value") else paste0("Marginal effect of ", dx), xlim = NULL, ylim = NULL, lwd = 1L, col = "black", lty = 1L, se.type = c("shade", "lines", "none"), se.col = "black", se.fill = grDevices::gray(0.5, 0.5), se.lwd = lwd, se.lty = if (match.arg(se.type) == "lines") 1L else 0L, factor.lty = 0L, factor.pch = 19L, factor.col = se.col, factor.fill = factor.col, factor.cex = 1L, xaxs = "i", yaxs = xaxs, las = 1L, scatter = FALSE, scatter.pch = 19L, scatter.col = se.col, scatter.bg = scatter.col, scatter.cex = 0.5, rug = TRUE, rug.col = col, rug.size = -0.02, ...) # S3 method for lm cplot(object, x = attributes(terms(object))[["term.labels"]][1L], dx = x, what = c("prediction", "effect"), data = prediction::find_data(object), type = c("response", "link"), vcov = stats::vcov(object), at, n = 25L, xvals = prediction::seq_range(data[[x]], n = n), level = 0.95, draw = TRUE, xlab = x, ylab = if (match.arg(what) == "prediction") paste0("Predicted value") else paste0("Marginal effect of ", dx), xlim = NULL, ylim = NULL, lwd = 1L, col = "black", lty = 1L, se.type = c("shade", "lines", "none"), se.col = "black", se.fill = grDevices::gray(0.5, 0.5), se.lwd = lwd, se.lty = if (match.arg(se.type) == "lines") 1L else 0L, factor.lty = 0L, factor.pch = 19L, factor.col = se.col, factor.fill = factor.col, factor.cex = 1L, xaxs = "i", yaxs = xaxs, las = 1L, scatter = FALSE, scatter.pch = 19L, scatter.col = se.col, scatter.bg = scatter.col, scatter.cex = 0.5, rug = TRUE, rug.col = col, rug.size = -0.02, ...) # S3 method for loess cplot(object, x = attributes(terms(object))[["term.labels"]][1L], dx = x, what = c("prediction", "effect"), data = prediction::find_data(object), type = c("response", "link"), vcov = stats::vcov(object), at, n = 25L, xvals = prediction::seq_range(data[[x]], n = n), level = 0.95, draw = TRUE, xlab = x, ylab = if (match.arg(what) == "prediction") paste0("Predicted value") else paste0("Marginal effect of ", dx), xlim = NULL, ylim = NULL, lwd = 1L, col = "black", lty = 1L, se.type = c("shade", "lines", "none"), se.col = "black", se.fill = grDevices::gray(0.5, 0.5), se.lwd = lwd, se.lty = if (match.arg(se.type) == "lines") 1L else 0L, factor.lty = 0L, factor.pch = 19L, factor.col = se.col, factor.fill = factor.col, factor.cex = 1L, xaxs = "i", yaxs = xaxs, las = 1L, scatter = FALSE, scatter.pch = 19L, scatter.col = se.col, scatter.bg = scatter.col, scatter.cex = 0.5, rug = TRUE, rug.col = col, rug.size = -0.02, ...) # S3 method for polr cplot(object, x = attributes(terms(object))[["term.labels"]][1L], dx = x, what = c("prediction", "classprediction", "stackedprediction", "effect"), data = prediction::find_data(object), type = c("response", "link"), vcov = stats::vcov(object), at, n = 25L, xvals = seq_range(data[[x]], n = n), level = 0.95, draw = TRUE, xlab = x, ylab = if (match.arg(what) == "effect") paste0("Marginal effect of ", dx) else paste0("Predicted value"), xlim = NULL, ylim = if (match.arg(what) %in% c("prediction", "stackedprediction")) c(0, 1.04) else NULL, lwd = 1L, col = "black", lty = 1L, factor.lty = 1L, factor.pch = 19L, factor.col = col, factor.fill = factor.col, factor.cex = 1L, xaxs = "i", yaxs = xaxs, las = 1L, scatter = FALSE, scatter.pch = 19L, scatter.col = factor.col, scatter.bg = scatter.col, scatter.cex = 0.5, rug = TRUE, rug.col = col, rug.size = -0.02, ...) # S3 method for multinom cplot(object, x = attributes(terms(object))[["term.labels"]][1L], dx = x, what = c("prediction", "classprediction", "stackedprediction", "effect"), data = prediction::find_data(object), type = c("response", "link"), vcov = stats::vcov(object), at, n = 25L, xvals = seq_range(data[[x]], n = n), level = 0.95, draw = TRUE, xlab = x, ylab = if (match.arg(what) == "effect") paste0("Marginal effect of ", dx) else paste0("Predicted value"), xlim = NULL, ylim = if (match.arg(what) %in% c("prediction", "stackedprediction")) c(0, 1.04) else NULL, lwd = 1L, col = "black", lty = 1L, factor.lty = 1L, factor.pch = 19L, factor.col = col, factor.fill = factor.col, factor.cex = 1L, xaxs = "i", yaxs = xaxs, las = 1L, scatter = FALSE, scatter.pch = 19L, scatter.col = factor.col, scatter.bg = scatter.col, scatter.cex = 0.5, rug = TRUE, rug.col = col, rug.size = -0.02, ...)
object | A model object. |
---|---|
… | Additional arguments passed to |
x | A character string specifying the name of variable to use as the x-axis dimension in the plot. |
dx | If |
what | A character string specifying whether to draw a “prediction” (fitted values from the model, calculated using |
data | A data frame to override the default value offered in |
type | A character string specifying whether to calculate predictions on the response scale (default) or link (only relevant for non-linear models). |
vcov | A matrix containing the variance-covariance matrix for estimated model coefficients, or a function to perform the estimation with |
at | Currently ignored. |
n | An integer specifying the number of points across |
xvals | A numeric vector of values at which to calculate predictions or marginal effects, if |
level | The confidence level required (used to draw uncertainty bounds). |
draw | A logical (default |
xlab | A character string specifying the value of |
ylab | A character string specifying the value of |
xlim | A two-element numeric vector specifying the x-axis limits. Set automatically if missing. |
ylim | A two-element numeric vector specifying the y-axis limits. Set automatically if missing. |
lwd | An integer specifying the width of the prediction or marginal effect line. See |
col | A character string specifying the color of the prediction or marginal effect line. If |
lty | An integer specifying the “line type” of the prediction or marginal effect line. See |
se.type | A character string specifying whether to draw the confidence interval as “lines” (the default, using |
se.col | If |
se.fill | If |
se.lwd | If |
se.lty | If |
factor.lty | If |
factor.pch | If |
factor.col | If |
factor.fill | If |
factor.cex | If |
xaxs | A character string specifying |
yaxs | A character string specifying |
las | An integer string specifying |
scatter | A logical indicating whether to plot the observed data in |
scatter.pch | If |
scatter.col | If |
scatter.bg | If |
scatter.cex | If |
rug | A logical specifying whether to include an x-axis “rug” (see |
rug.col | A character string specifying |
rug.size | A numeric value specifying |
A tidy data frame containing the data used to draw the plot. Use draw = FALSE
to simply generate the data structure for use elsewhere.
Note that when what = "prediction"
, the plots show predictions holding values of the data at their mean or mode, whereas when what = "effect"
average marginal effects (i.e., at observed values) are shown.
When examining generalized linear models (e.g., logistic regression models), confidence intervals for predictions can fall outside of the response scale (again, for logistic regression this means confidence intervals can exceed the (0,1) bounds). This is consistent with the behavior of predict
but may not be desired. The examples (below) show ways of constraining confidence intervals to these bounds.
The overall aesthetic is somewhat similar to to the output produced by the marginalModelPlot()
function in the car package.
# NOT RUN { require('datasets') # prediction from several angles m <- lm(Sepal.Length ~ Sepal.Width, data = iris) cplot(m) # more complex model m <- lm(Sepal.Length ~ Sepal.Width * Petal.Width * I(Petal.Width ^ 2), data = head(iris, 50)) ## marginal effect of 'Petal.Width' across 'Petal.Width' cplot(m, x = "Petal.Width", what = "effect", n = 10) # factor independent variables mtcars[["am"]] <- factor(mtcars[["am"]]) m <- lm(mpg ~ am * wt, data = mtcars) ## predicted values for each factor level cplot(m, x = "am") ## marginal effect of each factor level across numeric variable cplot(m, x = "wt", dx = "am", what = "effect") # marginal effect of 'Petal.Width' across 'Sepal.Width' ## without drawing the plot ## this might be useful for using, e.g., ggplot2 for plotting tmp <- cplot(m, x = "Sepal.Width", dx = "Petal.Width", what = "effect", n = 10, draw = FALSE) if (require("ggplot2")) { # use ggplot2 instead of base graphics ggplot(tmp, aes(x = Petal.Width, y = "effect")) + geom_line(lwd = 2) + geom_line(aes(y = effect + 1.96*se.effect)) + geom_line(aes(y = effect - 1.96*se.effect)) } # a non-linear model m <- glm(am ~ wt*drat, data = mtcars, family = binomial) cplot(m, x = "wt") # prediction (response scale) cplot(m, x = "wt") # prediction (link scale) if (require("ggplot2")) { # prediction (response scale, constrained to [0,1]) cplotdat <- cplot(m, x = "wt", type = "link", draw = FALSE) ggplot(cplotdat, aes(x = xvals, y = plogis(yvals))) + geom_line(lwd = 1.5) + geom_line(aes(y = plogis(upper))) + geom_line(aes(y = plotis(lower))) } # effects on linear predictor and outcome cplot(m, x = "drat", dx = "wt", what = "effect", type = "link") cplot(m, x = "drat", dx = "wt", what = "effect", type = "response") # plot conditional predictions across a third factor local({ iris$long <- rbinom(nrow(iris), 1, 0.6) x <- glm(long ~ Sepal.Width*Species, data = iris) cplot(x, x = "Sepal.Width", data = iris[iris$Species == "setosa", ], ylim = c(0,1), col = "red", se.fill = rgb(1,0,0,.5), xlim = c(2,4.5)) cplot(x, x = "Sepal.Width", data = iris[iris$Species == "versicolor", ], draw = "add", col = "blue", se.fill = rgb(0,1,0,.5)) cplot(x, x = "Sepal.Width", data = iris[iris$Species == "virginica", ], draw = "add", col = "green", se.fill = rgb(0,0,1,.5)) }) # ordinal outcome if (require("MASS")) { # x is a factor variable house.plr <- polr(Sat ~ Infl + Type + Cont, weights = Freq, data = housing) ## predicted probabilities cplot(house.plr) ## cumulative predicted probabilities cplot(house.plr, what = "stacked") ## ggplot2 example if (require("ggplot2")) { ggplot(cplot(house.plr), aes(x = xvals, y = yvals, group = level)) + geom_line(aes(color = level)) } # x is continuous cyl.plr <- polr(factor(cyl) ~ wt, data = mtcars) cplot(cyl.plr, col = c("red", "purple", "blue"), what = "stacked") cplot(cyl.plr, what = "class") } # }