Return to Answer

As an example I use exactly the same simulated data in my earlier answer (with an extreme high outlier thrown into y):

As an example I use data simulated as in my earlier answer (with an extreme high outlier thrown into y and quite a bit more contamination in x this time):

There are some details to take care of, especially to cope with datasets of different length. I do this by replacing the shorter one by the quantiles corresponding to the longer one: in effect, a piecewise linear approximation of the EDF of the shorter one is used instead of its actual data values.

qq <- function(x0, y0, t.y=0.0005) {
  qq.int <- function(x,y, i.min,i.max) {
    # x, y are sorted and of equal length
    n <-length(y)
    if (n==1) stop(print(c(x,y,i.max)))
    if (n==2) return(cbind(x,y, i=c(i.min,i.max)))
    beta <- ifelse( x[1]==x[n], 0, (y[n] - y[1]) / (x[n] - x[1]))
    alpha <- y[1] - beta*x[1]
    fit <- alpha + x * beta
    i <- median(c(2, n-1, which.max(abs(y-fit))))
    if (abs(y[i]-fit[i]) > thresh) {
      assemble(qq.int(x[1:i], y[1:i], i.min, i.min+i-1), 
               qq.int(x[i:n], y[i:n], i.min+i-1, i.max))
    } else {
      cbind(c(x[1],x[n]), c(y[1], y[n]), i=c(i.min, i.max))
    }
  }
  assemble <- function(xy1, xy2) {
    rbind(xy1, xy2[-1,])
  }
  #
  # Pre-process the input so that sorting is done once
  # and the most detail is extracted from the data.
  #
  is.reversed <- length(y0) < length(x0)
  if (is.reversed) {
    y <- sort(x0)
    n <- length(y)
    x <- quantile(y0, prob=(1:n-1)/(n-1))    
  } else {
    y <- sort(y0)
    n <- length(y)
    x <- quantile(x0, prob=(1:n-1)/(n-1))    
  }
  #
  # Convert the relative threshold t.y into an absolute.
  #
  thresh <- t.y * diff(range(y))
  #
  # Recursively obtain points on the QQ plot.
  #
  xy <- qq.int(x, y, 1, n)
  if (is.reversed) cbind(x=xy[,2], y=xy[,1], i=xy[,3]) else xy
}

I have modified the original code for qq to return a third column of indexes into the longest of the original two arrays, x and y, corresponding to the points that are selected. These indexes point to "interesting" values of the data and so could be useful for further analysis.

There are some details to take care of, especially to cope with datasets of different length. I do this by replacing the shorter one by the quantiles corresponding to the longer one: in effect, a piecewise linear approximation of the EDF of the shorter one is used instead of its actual data values. ("Shorter" and "longer" can be reversed by setting use.shortest=TRUE.)

qq <- function(x0, y0, t.y=0.0005, use.shortest=FALSE) {
  qq.int <- function(x,y, i.min,i.max) {
    # x, y are sorted and of equal length
    n <-length(y)
    if (n==1) return(c(x=x, y=y, i=i.max))
    if (n==2) return(cbind(x=x, y=y, i=c(i.min,i.max)))
    beta <- ifelse( x[1]==x[n], 0, (y[n] - y[1]) / (x[n] - x[1]))
    alpha <- y[1] - beta*x[1]
    fit <- alpha + x * beta
    i <- median(c(2, n-1, which.max(abs(y-fit))))
    if (abs(y[i]-fit[i]) > thresh) {
      assemble(qq.int(x[1:i], y[1:i], i.min, i.min+i-1), 
               qq.int(x[i:n], y[i:n], i.min+i-1, i.max))
    } else {
      cbind(x=c(x[1],x[n]), y=c(y[1], y[n]), i=c(i.min, i.max))
    }
  }
  assemble <- function(xy1, xy2) {
    rbind(xy1, xy2[-1,])
  }
  #
  # Pre-process the input so that sorting is done once
  # and the most detail is extracted from the data.
  #
  is.reversed <- length(y0) < length(x0)
  if (use.shortest) is.reversed <- !is.reversed
  if (is.reversed) {
    y <- sort(x0)
    n <- length(y)
    x <- quantile(y0, prob=(1:n-1)/(n-1))    
  } else {
    y <- sort(y0)
    n <- length(y)
    x <- quantile(x0, prob=(1:n-1)/(n-1))    
  }
  #
  # Convert the relative threshold t.y into an absolute.
  #
  thresh <- t.y * diff(range(y))
  #
  # Recursively obtain points on the QQ plot.
  #
  xy <- qq.int(x, y, 1, n)
  if (is.reversed) cbind(x=xy[,2], y=xy[,1], i=xy[,3]) else xy
}

I have modified the original code for qq to return a third column of indexes into the longest (or shortest, as specified) of the original two arrays, x and y, corresponding to the points that are selected. These indexes point to "interesting" values of the data and so could be useful for further analysis.

I also removed a bug occurring with repeated values of x (which caused beta to be undefined).

qq <- function(x0, y0, t.y=0.0005) {
  qq.int <- function(x,y) {
    # x, y are sorted and of equal length
    n <-length(y)
    if (n < 3) return (cbind(x,y))
    beta <- (y[n] - y[1]) / (x[n] - x[1])
    alpha <- y[1] - beta*x[1]
    fit <- alpha + x * beta
    i <- which.max(abs(y-fit))
    if (abs(y[i]-fit[i]) > thresh) {
      assemble(qq.int(x[1:i], y[1:i]), qq.int(x[i:n], y[i:n]))
    }
    else {
      matrix(c(x[1], y[1], x[n], y[n]), ncol=2, byrow=TRUE)
    }
  }
  assemble <- function(xy1, xy2) {
    rbind(xy1, xy2[-1,])
  }
  #
  # Pre-process the input so that sorting is done once
  # and the most detail is extracted from the data.
  #
  is.reversed <- length(y0) < length(x0)
  if (is.reversed) {
    y <- sort(x0)
    n <- length(y)
    x <- quantile(y0, prob=(1:n-1)/(n-1))    
  }
  else {
    y <- sort(y0)
    n <- length(y)
    x <- quantile(x0, prob=(1:n-1)/(n-1))    
  }
  #
  # Convert the relative threshold t.y into an absolute vertical deviation.
  #
  thresh <- t.y * diff(range(y))
  #
  # Recursively obtain points on the QQ plot.
  #
  xy <- qq.int(x, y)
  if (is.reversed) cbind(xy[,2], xy[,1]) else xy
}

qq <- function(x0, y0, t.y=0.0005) {
  qq.int <- function(x,y, i.min,i.max) {
    # x, y are sorted and of equal length
    n <-length(y)
    if (n==1) stop(print(c(x,y,i.max)))
    if (n==2) return(cbind(x,y, i=c(i.min,i.max)))
    beta <- ifelse( x[1]==x[n], 0, (y[n] - y[1]) / (x[n] - x[1]))
    alpha <- y[1] - beta*x[1]
    fit <- alpha + x * beta
    i <- median(c(2, n-1, which.max(abs(y-fit))))
    if (abs(y[i]-fit[i]) > thresh) {
      assemble(qq.int(x[1:i], y[1:i], i.min, i.min+i-1), 
               qq.int(x[i:n], y[i:n], i.min+i-1, i.max))
    } else {
      cbind(c(x[1],x[n]), c(y[1], y[n]), i=c(i.min, i.max))
    }
  }
  assemble <- function(xy1, xy2) {
    rbind(xy1, xy2[-1,])
  }
  #
  # Pre-process the input so that sorting is done once
  # and the most detail is extracted from the data.
  #
  is.reversed <- length(y0) < length(x0)
  if (is.reversed) {
    y <- sort(x0)
    n <- length(y)
    x <- quantile(y0, prob=(1:n-1)/(n-1))    
  } else {
    y <- sort(y0)
    n <- length(y)
    x <- quantile(x0, prob=(1:n-1)/(n-1))    
  }
  #
  # Convert the relative threshold t.y into an absolute.
  #
  thresh <- t.y * diff(range(y))
  #
  # Recursively obtain points on the QQ plot.
  #
  xy <- qq.int(x, y, 1, n)
  if (is.reversed) cbind(x=xy[,2], y=xy[,1], i=xy[,3]) else xy
}

###Edit###

I have modified the original code for qq to return a third column of indexes into the longest of the original two arrays, x and y, corresponding to the points that are selected. These indexes point to "interesting" values of the data and so could be useful for further analysis.