Zelig (version 3.5.1)

rocplot: Receiver Operator Characteristic Plots

Description

The rocplot command generates a receiver operator characteristic plot to compare the in-sample (default) or out-of-sample fit for two logit or probit regressions.

Usage

rocplot(y1, y2, fitted1, fitted2, cutoff = seq(from=0, to=1, length=100), 
        lty1 = "solid", lty2 = "dashed", lwd1 = par("lwd"), lwd2 = par("lwd"),
        col1 = par("col"), col2 = par("col"), main, xlab, ylab,
        plot = TRUE, ...)

Arguments

y1

Response variable for the first model.

y2

Response variable for the second model.

fitted1

Fitted values for the first model. These values may represent either the in-sample or out-of-sample fitted values.

fitted2

Fitted values for the second model.

cutoff

A vector of cut-off values between 0 and 1, at which to evaluate the proportion of 0s and 1s correctly predicted by the first and second model. By default, this is 100 increments between 0 and 1, inclusive.

lty1, lty2

The line type for the first model (lty1) and the second model (lty2), defaulting to solid and dashed, respectively.

lwd1, lwd2

The width of the line for the first model (lwd1) and the second model (lwd2), defaulting to 1 for both.

col1, col2

The colors of the line for the first model (col1) and the second model (col2), defaulting to black for both.

main

a title for the plot. Defaults to ROC Curve.

xlab

a label for the x-axis. Defaults to Proportion of 1's Correctly Predicted.

ylab

a label for the y-axis. Defaults to Proportion of 0's Correctly Predicted.

plot

defaults to TRUE, which generates a plot to the selected device. If FALSE, returns a list of items (see below).

...

Additional parameters passed to plot, including xlab, ylab, and main.

Value

• If plot = TRUE, rocplot generates an ROC plot for two logit or probit models. If plot = FALSE, rocplot returns a list with the following elements:
• roc1
  a matrix containing a vector of x-coordinates and y-coordinates corresponding to the number of ones and zeros correctly predicted for the first model.
• roc2
  a matrix containing a vector of x-coordinates and y-coordinates corresponding to the number of ones and zeros correctly predicted for the second model.
• area1
  the area under the first ROC curve, calculated using Reimann sums.
• area2
  the area under the second ROC curve, calculated using Reimann sums.

See Also

The full Zelig manual (available at http://gking.harvard.edu/zelig), plot, lines.

Examples

data(turnout)
z.out1 <- zelig(vote ~ race + educate + age, model = "logit", 
  data = turnout)
z.out2 <- zelig(vote ~ race + educate, model = "logit", 
  data = turnout)
rocplot(z.out1$y, z.out2$y, fitted(z.out1), fitted(z.out2))