qqnorm and qqline in ggplot2

Solution 1:

The following code will give you the plot you want. The ggplot package doesn't seem to contain code for calculating the parameters of the qqline, so I don't know if it's possible to achieve such a plot in a (comprehensible) one-liner.

qqplot.data <- function (vec) # argument: vector of numbers
{
  # following four lines from base R's qqline()
  y <- quantile(vec[!is.na(vec)], c(0.25, 0.75))
  x <- qnorm(c(0.25, 0.75))
  slope <- diff(y)/diff(x)
  int <- y[1L] - slope * x[1L]

  d <- data.frame(resids = vec)

  ggplot(d, aes(sample = resids)) + stat_qq() + geom_abline(slope = slope, intercept = int)

}

Solution 2:

You can also add confidence Intervals/confidence bands with this function (Parts of the code copied from car:::qqPlot)

gg_qq <- function(x, distribution = "norm", ..., line.estimate = NULL, conf = 0.95,
                  labels = names(x)){
  q.function <- eval(parse(text = paste0("q", distribution)))
  d.function <- eval(parse(text = paste0("d", distribution)))
  x <- na.omit(x)
  ord <- order(x)
  n <- length(x)
  P <- ppoints(length(x))
  df <- data.frame(ord.x = x[ord], z = q.function(P, ...))

  if(is.null(line.estimate)){
    Q.x <- quantile(df$ord.x, c(0.25, 0.75))
    Q.z <- q.function(c(0.25, 0.75), ...)
    b <- diff(Q.x)/diff(Q.z)
    coef <- c(Q.x[1] - b * Q.z[1], b)
  } else {
    coef <- coef(line.estimate(ord.x ~ z))
  }

  zz <- qnorm(1 - (1 - conf)/2)
  SE <- (coef[2]/d.function(df$z)) * sqrt(P * (1 - P)/n)
  fit.value <- coef[1] + coef[2] * df$z
  df$upper <- fit.value + zz * SE
  df$lower <- fit.value - zz * SE

  if(!is.null(labels)){ 
    df$label <- ifelse(df$ord.x > df$upper | df$ord.x < df$lower, labels[ord],"")
    }

  p <- ggplot(df, aes(x=z, y=ord.x)) +
    geom_point() + 
    geom_abline(intercept = coef[1], slope = coef[2]) +
    geom_ribbon(aes(ymin = lower, ymax = upper), alpha=0.2) 
  if(!is.null(labels)) p <- p + geom_text( aes(label = label))
  print(p)
  coef
}

Example:

Animals2 <- data(Animals2, package = "robustbase")
mod.lm <- lm(log(Animals2$brain) ~ log(Animals2$body))
x <- rstudent(mod.lm)
gg_qq(x)