Produces a quantile-quantile (Q-Q) plot, also called a probability plot. The qqPlot function is a modified version of the R functions qqnorm and qqplot. The EnvStats function qqPlot allows the user to specify a number of different distributions in addition to the normal distribution, and to optionally estimate the distribution parameters of the fitted distribution.

qqPlot(x, y = NULL, distribution = "norm", param.list = list(mean = 0, sd = 1), 
    estimate.params = plot.type == "Tukey Mean-Difference Q-Q", 
    est.arg.list = NULL, plot.type = "Q-Q", plot.pos.con = NULL, plot.it = TRUE, 
    equal.axes = qq.line.type == "0-1" || estimate.params, add.line = FALSE, 
    qq.line.type = "least squares", duplicate.points.method = "standard", 
    points.col = 1, line.col = 1, line.lwd = par("cex"), line.lty = 1, 
    digits = .Options$digits, ..., main = NULL, xlab = NULL, ylab = NULL, 
    xlim = NULL, ylim = NULL)

Arguments

x

numeric vector of observations. When y is not supplied, x represents a sample from the hypothesized distribution specifed by distribution. When y is supplied, the distribution of x is compared with the distribuiton of y. Missing (NA), undefined (NaN), and infinite (Inf, -Inf) values are allowed but will be removed.

y

optional numeric vector of observations (not necessarily the same lenght as x). Missing (NA), undefined (NaN), and infinite (Inf, -Inf) values are allowed but will be removed.

distribution

when y is not supplied, a character string denoting the distribution abbreviation. The default value is distribution="norm". See the help file for
Distribution.df for a list of possible distribution abbreviations. This argument is ignored if y is supplied.

param.list

when y is not supplied, a list with values for the parameters of the distribution. The default value is param.list=list(mean=0, sd=1). See the help file for Distribution.df for the names and possible values of the parameters associated with each distribution. This argument is ignored if y is supplied or estimate.params=TRUE.

estimate.params

when y is not supplied, a logical scalar indicating whether to compute quantiles based on estimating the distribution parameters (estimate.params=TRUE) or using the known distribution parameters specified in param.list
(estimate.params=FALSE). The default value of estimate.params is FALSE if plot.type="Q-Q" because the default configuration is a standard normal (mean=0, sd=1) Q-Q plot, which will yield roughly a straight line if the observations in x are from any normal distribution. The default value of estimate.params is TRUE if plot.type="Tukey Mean-Difference Q-Q". The argument
estimate.params is ignored if y is supplied.

est.arg.list

when y is not supplied and estimate.params=TRUE, a list whose components are optional arguments associated with the function used to estimate the parameters of the assumed distribution (see the help file Estimating Distribution Parameters). For example, all functions used to estimate distribution parameters have an optional argument called method that specifies the method to use to estimate the parameters. (See the help file for Distribution.df for a list of available estimation methods for each distribution.) To override the default estimation method, supply the argument est.arg.list with a component called method; for example est.arg.list=list(method="mle"). The default value is est.arg.list=NULL so that all default values for the estimating function are used. This argument is ignored if estimate.params=FALSE or y is supplied.

plot.type

a character string denoting the kind of plot. Possible values are "Q-Q" (Quantile-Quantile plot, the default) and "Tukey Mean-Difference Q-Q" (Tukey mean-difference Q-Q plot). This argument may be abbreviated (e.g., plot.type="T" to indicate a Tukey mean-difference Q-Q plot).

plot.pos.con

numeric scalar between 0 and 1 containing the value of the plotting position constant. The default value of plot.pos.con depends on whether the argument y is supplied, and if not the value of the argument distribution. When y is supplied, the default value is plot.pos.con=0.5, corresponding to Hazen plotting positions. When y is not supplied, for the normal, lognormal, three-parameter lognormal, zero-modified normal, and zero-modified lognormal distributions, the default value is plot.pos.con=0.375. For the Type I extreme value (Gumbel) distribution (distribution="evd"), the default value is
plot.pos.con=0.44. For all other distributions, the default value is
plot.pos.con=0.4.

plot.it

a logical scalar indicating whether to create a plot on the current graphics device. The default value is plot.it=TRUE.

equal.axes

a logical scalar indicating whether to use the same range on the \(x\)- and \(y\)-axes when plot.type="Q-Q". The default value is TRUE if qq.line.type="0-1" or estimate.params=TRUE, otherwise it is FALSE. This argument is ignored if plot.type="Tukey Mean-Difference Q-Q".

add.line

a logical scalar indicating whether to add a line to the plot. If add.line=TRUE and plot.type="Q-Q", a line determined by the value of qq.line.type is added to the plot. If add.line=TRUE and
plot.type="Tukey Mean-Difference Q-Q", a horizontal line at \(y=0\) is added to the plot. The default value is add.line=FALSE.

qq.line.type

character string determining what kind of line to add to the Q-Q plot. Possible values are "least squares" (the default), "0-1" and "robust". For the value "least squares", a least squares line is fit and added. For the value "0-1", a line with intercept 0 and slope 1 is added. For the value "robust", a line is fit through the first and third quartiles of the x and y data. This argument is ignored if add.line=FALSE or plot.type="Tukey Mean-Difference Q-Q".

duplicate.points.method

a character string denoting how to plot points with duplicate \((x,y)\) values. Possible values are "standard" (the default), "jitter", and "number". For the value "standard", a single plotting symbol is plotted (this is the default behavior of R). For the value "jitter", a separate plotting symbol is plotted for each duplicate point, where the plotting symbols cluster around the true value of \(x\) and \(y\). For the value "number", a single number is plotted at \((x,y)\) that represents how many duplicate points are at that \((x,y)\) coordinate.

points.col

a numeric scalar or character string determining the color of the points in the plot. The default value is points.col=1. See the entry for col in the help file for par for more information.

line.col

a numeric scalar or character string determining the color of the line in the plot. The default value is points.col=1. See the entry for col in the help file for par for more information. This argument is ignored if add.line=FALSE.

line.lwd

a numeric scalar determining the width of the line in the plot. The default value is line.lwd=par("cex"). See the entry for lwd in the help file for par for more information. This argument is ignored if add.line=FALSE.

line.lty

a numeric scalar determining the line type of the line in the plot. The default value is line.lty=1. See the entry for lty in the help file for par for more information. This argument is ignored if add.line=FALSE.

digits

a scalar indicating how many significant digits to print for the distribution parameters. The default value is digits=.Options$digits.

main, xlab, ylab, xlim, ylim, ...

additional graphical parameters (see par).

Details

If y is not supplied, the vector x is assumed to be a sample from the probability distribution specified by the argument distribution (and param.list if estimate.params=FALSE). When plot.type="Q-Q", the quantiles of x are plotted on the \(y\)-axis against the quantiles of the assumed distribution on the \(x\)-axis.

If y is supplied and plot.type="Q-Q", the empirical quantiles of y are plotted against the empirical quantiles of x.

When plot.type="Tukey Mean-Difference Q-Q", the difference of the quantiles is plotted on the \(y\)-axis against the mean of the quantiles on the \(x\)-axis.

Special Distributions
When y is not supplied and the argument distribution specifies one of the following distributions, the function qqPlot behaves in the manner described below.

"lnorm"

Lognormal Distribution. The log-transformed quantiles are plotted against quantiles from a Normal (Gaussian) distribution.

"lnormAlt"

Lognormal Distribution (alternative parameterization). The untransformed quantiles are plotted against quantiles from a Lognormal distribution.

"lnorm3"

Three-Parameter Lognormal Distribution. The quantiles of log(x-threshold) are plotted against quantiles from a Normal (Gaussian) distribution. The value of threshold is either specified in the argument param.list, or, if estimate.params=TRUE, then it is estimated.

"zmnorm"

Zero-Modified Normal Distribution. The quantiles of the non-zero values (i.e., x[x!=0]) are plotted against quantiles from a Normal (Gaussian) distribution.

"zmlnorm"

Zero-Modified Lognormal Distribution. The quantiles of the log-transformed positive values (i.e., log(x[x>0])) are plotted against quantiles from a Normal (Gaussian) distribution.

"zmlnormAlt"

Lognormal Distribution (alternative parameterization). The quantiles of the untransformed positive values (i.e., x[x>0]) are plotted against quantiles from a Lognormal distribution.

Explanation of Q-Q Plots
A probability plot or quantile-quantile (Q-Q) plot is a graphical display invented by Wilk and Gnanadesikan (1968) to compare a data set to a particular probability distribution or to compare it to another data set. The idea is that if two population distributions are exactly the same, then they have the same quantiles (percentiles), so a plot of the quantiles for the first distribution vs. the quantiles for the second distribution will fall on the 0-1 line (i.e., the straight line \(y = x\) with intercept 0 and slope 1). If the two distributions have the same shape and spread but different locations, then the plot of the quantiles will fall on the line \(y = x + b\) (parallel to the 0-1 line) where \(b\) denotes the difference in locations. If the distributions have different locations and differ by a multiplicative constant \(m\), then the plot of the quantiles will fall on the line \(y = mx + b\) (D'Agostino, 1986a, p. 25; Helsel and Hirsch, 1986, p. 42). Various kinds of differences between distributions will yield various kinds of deviations from a straight line.

Comparing Observations to a Hypothesized Distribution
Let \(\underline{x} = x_1, x_2, \ldots, x_n\) denote the observations in a random sample of size \(n\) from some unknown distribution with cumulative distribution function \(F()\), and let \(x_{(1)}, x_{(2)}, \ldots, x_{(n)}\) denote the ordered observations. Depending on the particular formula used for the empirical cdf (see ecdfPlot), the \(i\)'th order statistic is an estimate of the \(i/(n+1)\)'th, \((i-0.5)/n\)'th, etc., quantile. For the moment, assume the \(i\)'th order statistic is an estimate of the \(i/(n+1)\)'th quantile, that is: $$\hat{F}[x_{(i)}] = \hat{p}_i = \frac{i}{n+1} \;\;\;\;\;\; (1)$$ so $$x_{(i)} \approx F^{-1}(\hat{p}_i) \;\;\;\;\;\; (2)$$ If we knew the form of the true cdf \(F\), then the plot of \(x_{(i)}\) vs. \(F^{-1}(\hat{p}_i)\) would form approximately a straight line based on Equation (2) above. A probability plot is a plot of \(x_{(i)}\) vs. \(F_0^{-1}(\hat{p}_i)\), where \(F_0\) denotes the cdf associated with the hypothesized distribution. The probability plot should fall roughly on the line \(y=x\) if \(F=F_0\). If \(F\) and \(F_0\) merely differ by a shift in location and scale, that is, if \(F[(x - \mu) / \sigma] = F_0(x)\), then the plot should fall roughly on the line \(y = \sigma x + \mu\).

The quantity \(\hat{p}_i = i/(n+1)\) in Equation (1) above is called the plotting position for the probability plot. This particular formula for the plotting position is appealing because it can be shown that for any continuous distribution $$E\{F[x_{(i)}]\} = \frac{i}{n+1} \;\;\;\;\;\; (3)$$ (Nelson, 1982, pp. 299-300; Stedinger et al., 1993). That is, the \(i\)'th plotting position defined as in Equation (1) is the expected value of the true cdf evaluated at the \(i\)'th order statistic. Many authors and practitioners, however, prefer to use a plotting position that satisfies: $$F^{-1}(\hat{p}_i) = E[x_{(i)}] \;\;\;\;\;\; (4)$$ or one that satisfies $$F^{-1}(\hat{p}_i) = M[x_{(i)}] = F^{-1}\{M[u_{(i)}]\} \;\;\;\;\;\; (5)$$ where \(M[x_{(i)}]\) denotes the median of the distribution of the \(i\)'th order statistic, and \(u_{(i)}\) denotes the \(i\)'th order statistic in a random sample of \(n\) uniform (0,1) random variates.

The plotting positions in Equation (4) are often approximated since the expected value of the \(i\)'th order statistic is often difficult and time-consuming to compute. Note that these plotting positions will differ for different distributions.

The plotting positions in Equation (5) were recommended by Filliben (1975) because they require computing or approximating only the medians of uniform (0,1) order statistics, no matter what the form of the assumed cdf \(F_0\). Also, the median may be preferred as a measure of central tendency because the distributions of most order statistics are skewed.

Most plotting positions can be written as: $$\hat{p}_i = \frac{i - a}{n - 2a + 1} \;\;\;\;\;\; (6)$$ where \(0 \le a \le 1\) (D'Agostino, 1986a, p.25; Stedinger et al., 1993). The quantity \(a\) is sometimes called the “plotting position constant”, and is determined by the argument plot.pos.con in the function qqPlot. The table below, adapted from Stedinger et al. (1993), displays commonly used plotting positions based on equation (6) for several distributions.

Distribution
Often Used
NameaWithReferences
Weibull0Weibull,Weibull (1939),
UniformStedinger et al. (1993)
Median0.3175SeveralFilliben (1975),
Vogel (1986)
Blom0.375NormalBlom (1958),
and OthersLooney and Gulledge (1985)
Cunnane0.4SeveralCunnane (1978),
Chowdhury et al. (1991)
Gringorten0.44GumbelGringorton (1963),
Vogel (1986)
Hazen0.5SeveralHazen (1914),
Chambers et al. (1983),
Cleveland (1993)

For moderate and large sample sizes, there is very little difference in visual appearance of the Q-Q plot for different choices of plotting positions.

Comparing Two Data Sets
Let \(\underline{x} = x_1, x_2, \ldots, x_n\) denote the observations in a random sample of size \(n\) from some unknown distribution with cumulative distribution function \(F()\), and let \(x_{(1)}, x_{(2)}, \ldots, x_{(n)}\) denote the ordered observations. Similarly, let \(\underline{y} = y_1, y_2, \ldots, y_m\) denote the observations in a random sample of size \(m\) from some unknown distribution with cumulative distribution function \(G()\), and let \(y_{(1)}, y_{(2)}, \ldots, y_{(m)}\) denote the ordered observations. Suppose we are interested in investigating whether the shape of the distribution with cdf \(F\) is the same as the shape of the distribution with cdf \(G\) (e.g., \(F\) and \(G\) may both be normal distributions but differ in mean and standard deviation).

When \(n = m\), we can visually explore this question by plotting \(y_{(i)}\) vs. \(x_{(i)}\), for \(i = 1, 2, \ldots, n\). The values in \(\underline{y}\) are spread out in a certain way depending on the true distribution: they may be more or less symmetric about some value (the population mean or median) or they may be skewed to the right or left; they may be concentrated close to the mean or median (platykurtic) or there may be several observations “far away” from the mean or median on either side (leptokurtic). Similarly, the values in \(\underline{x}\) are spread out in a certain way. If the values in \(\underline{x}\) and \(\underline{y}\) are spread out in the same way, then the plot of \(y_{(i)}\) vs. \(x_{(i)}\) will be approximately a straight line. If the cdf \(F\) is exactly the same as the cdf \(G\), then the plot of \(y_{(i)}\) vs. \(x_{(i)}\) will fall roughly on the straight line \(y = x\). If \(F\) and \(G\) differ by a shift in location and scale, that is, if \(F[(x-\mu)/\sigma] = G(x)\), then the plot will fall roughly on the line \(y = \sigma x + \mu\).

When \(n > m\), a slight adjustment has to be made to produce the plot. Let \(\hat{p}_1, \hat{p}_2, \ldots, \hat{p}_m\) denote the plotting positions corresponding to the \(m\) empirical quantiles for the \(y\)'s and let \(\hat{p}^*_1, \hat{p}^*_2, \ldots, \hat{p}^*_n\) denote the plotting positions corresponding the \(n\) empirical quantiles for the \(x\)'s. Then we plot \(y_{(j)}\) vs. \(x^*_{(j)}\) for \(j = 1, 2, \ldots, m\) where $$x^*_{(j)} = (1 - r) x_{(i)} + r x_{(i+1)} \;\;\;\;\;\; (7)$$ $$r = \frac{\hat{p}_j - \hat{p}^*_i}{\hat{p}^*_{i+1} - \hat{p}^*_i} \;\;\;\;\;\; (8)$$ $$\hat{p}^*_i \le \hat{p}_j \le \hat{p}^*_{i+1} \;\;\;\;\;\; (9)$$ That is, the values for the \(x^*_{(j)}\)'s are determined by linear interpolation based on the values of the plotting positions for \(\underline{x}\) and \(\underline{y}\).

A similar adjustment is made when \(n < m\).

Note that the R function qqplot uses a different method than the one in Equation (7) above; it uses linear interpolation based on 1:n and m by calling the approx function.

Value

qqPlot returns a list with components x and y, giving the \((x,y)\) coordinates of the points that have been or would have been plotted. There are four cases to consider:

1. The argument y is not supplied and plot.type="Q-Q".

x

the quantiles from the theoretical distribution.

y

the observed quantiles (order statistics) based on the data in the argument x.


2. The argument y is not supplied and plot.type="Tukey Mean-Difference Q-Q".

x

the averages of the observed and theoretical quantiles.

y

the differences between the observed quantiles (order statistics) and the theoretical quantiles.


3. The argument y is supplied and plot.type="Q-Q".

x

the observed quantiles based on the data in the argument x. Note that these are adjusted quantiles if the number of observations in the argument x is greater then the number of observations in the argument y.

y

the observed quantiles based on the data in the argument y. Note that these are adjusted quantiles if the number of observations in the argument y is greater then the number of observations in the argument x.


4. The argument y is supplied and plot.type="Tukey Mean-Difference Q-Q".

x

the averages of the quantiles based on the argument x and the quantiles based on the argument y.

y

the differences between the quantiles based on the argument x and the quantiles based on the argument y.

References

Chambers, J.M., W.S. Cleveland, B. Kleiner, and P.A. Tukey. (1983). Graphical Methods for Data Analysis. Duxbury Press, Boston, MA, pp.11-16.

Cleveland, W.S. (1993). Visualizing Data. Hobart Press, Summit, New Jersey, 360pp.

D'Agostino, R.B. (1986a). Graphical Analysis. In: D'Agostino, R.B., and M.A. Stephens, eds. Goodness-of Fit Techniques. Marcel Dekker, New York, Chapter 2, pp.7-62.

Author

Steven P. Millard (EnvStats@ProbStatInfo.com)

Note

A quantile-quantile (Q-Q) plot, also called a probability plot, is a plot of the observed order statistics from a random sample (the empirical quantiles) against their (estimated) mean or median values based on an assumed distribution, or against the empirical quantiles of another set of data (Wilk and Gnanadesikan, 1968). Q-Q plots are used to assess whether data come from a particular distribution, or whether two datasets have the same parent distribution. If the distributions have the same shape (but not necessarily the same location or scale parameters), then the plot will fall roughly on a straight line. If the distributions are exactly the same, then the plot will fall roughly on the straight line \(y=x\).

A Tukey mean-difference Q-Q plot, also called an m-d plot, is a modification of a Q-Q plot. Rather than plotting observed quantiles vs. theoretical quantiles or observed \(y\)-quantiles vs. observed \(x\)-quantiles, a Tukey mean-difference Q-Q plot plots the difference between the quantiles on the \(y\)-axis vs. the average of the quantiles on the \(x\)-axis (Cleveland, 1993, pp.22-23). If the two sets of quantiles come from the same parent distribution, then the points in this plot should fall roughly along the horizontal line \(y=0\). If one set of quantiles come from the same distribution with a shift in median, then the points in this plot should fall along a horizontal line above or below the line \(y=0\). A Tukey mean-difference Q-Q plot enhances our perception of how the points in the Q-Q plot deviate from a straight line, because it is easier to judge deviations from a horizontal line than from a line with a non-zero slope.

In a Q-Q plot, the extreme points have more variability than points toward the center. A U-shaped Q-Q plot indicates that the underlying distribution for the observations on the \(y\)-axis is skewed to the right relative to the underlying distribution for the observations on the \(x\)-axis. An upside-down-U-shaped Q-Q plot indicates the \(y\)-axis distribution is skewed left relative to the \(x\)-axis distribution. An S-shaped Q-Q plot indicates the \(y\)-axis distribution has shorter tails than the \(x\)-axis distribution. Conversely, a plot that is bent down on the left and bent up on the right indicates that the \(y\)-axis distribution has longer tails than the \(x\)-axis distribution.

Examples

  # The guidance document USEPA (1994b, pp. 6.22--6.25) 
  # contains measures of 1,2,3,4-Tetrachlorobenzene (TcCB) 
  # concentrations (in parts per billion) from soil samples 
  # at a Reference area and a Cleanup area.  These data are strored 
  # in the data frame EPA.94b.tccb.df.  
  #
  # Create an Q-Q plot for the reference area data first assuming a 
  # normal distribution, then a lognormal distribution, then a 
  # gamma distribution.
  
  # Assume a normal distribution
  #-----------------------------

  dev.new()
  with(EPA.94b.tccb.df, qqPlot(TcCB[Area == "Reference"]))

  dev.new()
  with(EPA.94b.tccb.df, qqPlot(TcCB[Area == "Reference"], add.line = TRUE))

  dev.new()
  with(EPA.94b.tccb.df, qqPlot(TcCB[Area == "Reference"], 
    plot.type = "Tukey", add.line = TRUE))


  # The Q-Q plot based on assuming a normal distribution shows a U-shape,
  # indicating the Reference area TcCB data are skewed to the right
  # compared to a normal distribuiton.

  # Assume a lognormal distribution
  #--------------------------------

  dev.new()
  with(EPA.94b.tccb.df, 
    qqPlot(TcCB[Area == "Reference"], dist = "lnorm", 
      digits = 2, points.col = "blue", add.line = TRUE))

  dev.new()
  with(EPA.94b.tccb.df, 
    qqPlot(TcCB[Area == "Reference"], dist = "lnorm", 
      digits = 2, plot.type = "Tukey", points.col = "blue", 
      add.line = TRUE))

  # Alternative parameterization

  dev.new()
  with(EPA.94b.tccb.df, 
    qqPlot(TcCB[Area == "Reference"], dist = "lnormAlt", 
      estimate.params = TRUE, digits = 2, points.col = "blue", 
      add.line = TRUE))

  dev.new()
  with(EPA.94b.tccb.df, 
    qqPlot(TcCB[Area == "Reference"], dist = "lnormAlt", 
      digits = 2, plot.type = "Tukey", points.col = "blue", 
      add.line = TRUE))


  # The lognormal distribution appears to be an adequate fit.
  # Now look at a Q-Q plot assuming a gamma distribution.
  #----------------------------------------------------------

  dev.new()
  with(EPA.94b.tccb.df, 
    qqPlot(TcCB[Area == "Reference"], dist = "gamma", 
      estimate.params = TRUE, digits = 2, points.col = "blue", 
      add.line = TRUE))

  dev.new()
  with(EPA.94b.tccb.df, 
    qqPlot(TcCB[Area == "Reference"], dist = "gamma", 
      digits = 2, plot.type = "Tukey", points.col = "blue", 
      add.line = TRUE))

  # Alternative Parameterization

  dev.new()
  with(EPA.94b.tccb.df, 
    qqPlot(TcCB[Area == "Reference"], dist = "gammaAlt", 
      estimate.params = TRUE, digits = 2, points.col = "blue", 
      add.line = TRUE))

  dev.new()
  with(EPA.94b.tccb.df, 
    qqPlot(TcCB[Area == "Reference"], dist = "gammaAlt", 
      digits = 2, plot.type = "Tukey", points.col = "blue", 
      add.line = TRUE))

  #-------------------------------------------------------------------------------------

  # Generate 20 observations from a gamma distribution with parameters 
  # shape=2 and scale=2, then create a normal (Gaussian) Q-Q plot for these data. 
  # (Note: the call to set.seed simply allows you to reproduce this example.)

  set.seed(357) 
  dat <- rgamma(20, shape=2, scale=2) 
  dev.new()
  qqPlot(dat, add.line = TRUE)

  # Now assume a gamma distribution and estimate the parameters
  #------------------------------------------------------------

  dev.new()
  qqPlot(dat, dist = "gamma", estimate.params = TRUE, add.line = TRUE)

  # Clean up
  #---------
  rm(dat)
  graphics.off()