The R Project SVN R

% File src/library/stats/man/plot.lm.Rd
% Part of the R package, https://www.R-project.org
% Copyright 1995-2023 R Core Team
% Distributed under GPL 2 or later

\name{plot.lm}
\alias{plot.lm}
% \alias{plot.mlm} %which is .NotYetImplemented()
\title{Plot Diagnostics for an \code{lm} Object}
\usage{
\method{plot}{lm}(x, which = c(1,2,3,5), %% was which = 1:4
     caption = list("Residuals vs Fitted", "Q-Q Residuals",
       "Scale-Location", "Cook's distance",
       "Residuals vs Leverage",
       expression("Cook's dist vs Leverage* " * h[ii] / (1 - h[ii]))),
     panel = if(add.smooth) function(x, y, ...)
              panel.smooth(x, y, iter=iter.smooth, ...) else points,
     sub.caption = NULL, main = "",
     ask = prod(par("mfcol")) < length(which) && dev.interactive(),
     \dots,
     id.n = 3, labels.id = names(residuals(x)), cex.id = 0.75,
     qqline = TRUE, cook.levels = c(0.5, 1.0),
     cook.col = 8, cook.lty = 2, cook.legendChanges = list(),
     add.smooth = getOption("add.smooth"),
     iter.smooth = if(isGlm) 0 else 3,
     label.pos = c(4,2),
     cex.caption = 1, cex.oma.main = 1.25
   , extend.ylim.f = 0.08
     )
}
\arguments{
  \item{x}{\code{lm} object, typically result of \code{\link{lm}} or
    \code{\link{glm}}.}
  \item{which}{a subset of the numbers \code{1:6}, by default \code{1:3, 5},
    referring to \enumerate{
      \item "Residuals vs Fitted", aka \sQuote{Tukey-Anscombe} plot % 1
      \item "Residual Q-Q" plot  % 2
      \item "Scale-Location"     % 3
      \item "Cook's distance"    % 4
      \item "Residuals   vs  Leverage"      % 5
      \item "Cook's dist vs Lev./(1-Lev.)"  % 6
    }
    See also \sQuote{Details} below.}
  \item{caption}{captions to appear above the plots;
    \code{\link{character}} vector or \code{\link{list}} of valid
    graphics annotations, see \code{\link{as.graphicsAnnot}}, of length
    6, the j-th entry corresponding to \code{which[j]}, see also the
    default vector in \sQuote{Usage}.  Can be set to
    \code{""} or \code{NA} to suppress all captions.
  }
  \item{panel}{panel function.  The useful alternative to
    \code{\link{points}}, \code{\link{panel.smooth}} can be chosen
    by \code{add.smooth = TRUE}.}
  \item{sub.caption}{common title---above the figures if there are more
    than one; used as \code{sub} (s.\code{\link{title}}) otherwise.  If
    \code{NULL}, as by default, a possible abbreviated version of
    \code{deparse(x$call)} is used.}
  \item{main}{title to each plot---in addition to \code{caption}.}
  \item{ask}{logical; if \code{TRUE}, the user is \emph{ask}ed before
    each plot, see \code{\link{par}(ask=.)}.}
  \item{\dots}{other parameters to be passed through to plotting
    functions.}
  \item{id.n}{number of points to be labelled in each plot, starting
    with the most extreme.}
  \item{labels.id}{vector of labels, from which the labels for extreme
    points will be chosen.  \code{NULL} uses observation numbers.}
  \item{cex.id}{magnification of point labels.}
  \item{qqline}{logical indicating if a \code{\link{qqline}()} should be
    added to the normal Q-Q plot.}
  \item{cook.levels}{levels of Cook's distance at which to draw contours.}
  \item{cook.col, cook.lty}{color and line type to use for these contour
    lines.}
  \item{cook.legendChanges}{a \code{\link{list}} (or \code{NULL} to
    suppress the call) of arguments to \code{\link{legend}} which should be
    \emph{modified} from (or added to) the \code{plot.lm()} default \code{
      list(x = "bottomleft", legend = "Cook's distance",
           lty = cook.lty, col = cook.col, text.col = cook.col,
           bty = "n", x.intersp = 1/4, y.intersp = 1/8) }.}
  \item{add.smooth}{logical indicating if a smoother should be added to
    most plots; see also \code{panel} above.}
  \item{iter.smooth}{the number of robustness iterations, the argument
    \code{iter} in \code{\link{panel.smooth}()}; the default uses no such
    iterations for \code{\link{glm}} fits which is
    particularly desirable for the (predominant) case of binary
    observations, but also for other models where the response
    distribution can be highly skewed.}
  \item{label.pos}{positioning of labels, for the left half and right
    half of the graph respectively, for plots 1-3, 5, 6.}
  \item{cex.caption}{controls the size of \code{caption}.}
  \item{cex.oma.main}{controls the size of the \code{sub.caption} only if
    that is \emph{above} the figures when there is more than one.}
  \item{extend.ylim.f}{a numeric vector of length 1 or 2, to be used in
    \code{ylim <- \link{extendrange}(r=ylim, f = *)}
    for plots \code{1} and \code{5} when \code{id.n} is non-empty.}
}
\description{
  Six plots (selectable by \code{which}) are currently available: a plot
  of residuals against fitted values, a Scale-Location plot of
  \eqn{\sqrt{| residuals |}}{sqrt(| residuals |)}
  against fitted values, a Q-Q plot of residuals, a
  plot of Cook's distances versus row labels, a plot of residuals
  against leverages, and a plot of Cook's distances against
  leverage/(1-leverage).  By default, the first three and \code{5} are
  provided.
}
\details{
  \code{sub.caption}---by default the function call---is shown as
  a subtitle (under the x-axis title) on each plot when plots are on
  separate pages, or as a subtitle in the outer margin (if any) when
  there are multiple plots per page.

  The \sQuote{Scale-Location} plot (\code{which=3}), also called \sQuote{Spread-Location} or
  \sQuote{S-L} plot, takes the square root of the absolute residuals in
  order to diminish skewness (\eqn{\sqrt{| E |}}{sqrt(|E|)} is much less skewed
  than \eqn{| E |} for Gaussian zero-mean \eqn{E}).

  The \sQuote{S-L}, the Q-Q, and the Residual-Leverage (\code{which=5}) plot use
  \emph{standardized} residuals which have identical variance (under the
  hypothesis).  They are given as
  \eqn{R_i / (s \times \sqrt{1 - h_{ii}})}{R[i] / (s * sqrt(1 - h.ii))}
  where the \emph{\sQuote{leverages}} \eqn{h_{ii}}{h.ii} are the diagonal entries
  of the hat matrix,
  \code{\link{influence}()$hat} (see also \code{\link{hat}}), and
  where the Residual-Leverage plot uses the standardized Pearson residuals
  (\code{\link{residuals.glm}(type = "pearson")}) for \eqn{R[i]}.

  The Residual-Leverage plot (\code{which=5}) shows contours of equal Cook's distance,
  for values of \code{cook.levels} (by default 0.5 and 1) and omits
  cases with leverage one with a warning.  If the leverages are constant
  (as is typically the case in a balanced \code{\link{aov}} situation)
  the plot uses factor level combinations instead of the leverages for
  the x-axis.  (The factor levels are ordered by mean fitted value.)

  In the Cook's distance vs leverage/(1-leverage) (= \dQuote{leverage*})
  plot (\code{which=6}), contours of
  standardized residuals (\code{\link{rstandard}(.)}) that are equal in
  magnitude are lines through the origin.  These lines are labelled with
  the magnitudes.  The x-axis is labeled with the (non equidistant)
  leverages \eqn{h_{ii}}{h.ii}.

  For the \code{glm} case, the Q-Q plot is based on the absolute value
  of the standardized deviance residuals. When the saddlepoint
  approximation applies, these have an approximate half-normal
  distribution.  The saddlepoint approximation is exact for the normal
  and inverse Gaussian family, and holds approximately for the Gamma
  family with small dispersion (large shape) and for the Poisson and
  binomial families with large counts (Dunn and Smyth 2018).
}

\references{
  Belsley, D. A., Kuh, E. and Welsch, R. E. (1980).
  \emph{Regression Diagnostics}.
  New York: Wiley.

  Cook, R. D. and Weisberg, S. (1982).
  \emph{Residuals and Influence in Regression}.
  London: Chapman and Hall.

  Firth, D. (1991) Generalized Linear Models.
  In Hinkley, D. V. and Reid, N. and Snell, E. J., eds:
  Pp.\sspace{}55-82 in Statistical Theory and Modelling.
  In Honour of Sir David Cox, FRS.
  London: Chapman and Hall.

  Hinkley, D. V. (1975).
  On power transformations to symmetry.
  \emph{Biometrika}, \bold{62}, 101--111.
  \doi{10.2307/2334491}.

  McCullagh, P. and Nelder, J. A. (1989).
  \emph{Generalized Linear Models}.
  London: Chapman and Hall.

  Dunn, P.K. and Smyth G.K. (2018)
  \emph{Generalized Linear Models with Examples in R}.
  New York: Springer-Verlag.
}
\author{
  John Maindonald and Martin Maechler.
}
\seealso{\code{\link{termplot}}, \code{\link{lm.influence}},
  \code{\link{cooks.distance}}, \code{\link{hatvalues}}.
}
\examples{
require(graphics)

## Analysis of the life-cycle savings data
## given in Belsley, Kuh and Welsch.
lm.SR <- lm(sr ~ pop15 + pop75 + dpi + ddpi, data = LifeCycleSavings)
plot(lm.SR)

## 4 plots on 1 page;
## allow room for printing model formula in outer margin:
par(mfrow = c(2, 2), oma = c(0, 0, 2, 0)) -> opar
plot(lm.SR)
plot(lm.SR, id.n = NULL)                 # no id's
plot(lm.SR, id.n = 5, labels.id = NULL)  # 5 id numbers

## Was default in R <= 2.1.x:
## Cook's distances instead of Residual-Leverage plot
plot(lm.SR, which = 1:4)

## All the above fit a smooth curve where applicable
## by default unless "add.smooth" is changed.
## Give a smoother curve by increasing the lowess span :
plot(lm.SR, panel = function(x, y) panel.smooth(x, y, span = 1))

par(mfrow = c(2,1)) # same oma as above
plot(lm.SR, which = 1:2, sub.caption = "Saving Rates, n=50, p=5")

## Cook's distance tweaking
par(mfrow = c(2,3)) # same oma ...
plot(lm.SR, which = 1:6, cook.col = "royalblue")

## A case where over plotting of the "legend" is to be avoided:
if(dev.interactive(TRUE)) getOption("device")(height = 6, width = 4)
par(mfrow = c(3,1), mar = c(5,5,4,2)/2 +.1, mgp = c(1.4, .5, 0))
plot(lm.SR, which = 5, extend.ylim.f = c(0.2, 0.08))
plot(lm.SR, which = 5, cook.lty = "dotdash",
     cook.legendChanges = list(x = "bottomright", legend = "Cook"))
plot(lm.SR, which = 5, cook.legendChanges = NULL)  # no "legend"

\dontshow{
## An example with *long* formula that needs abbreviation:
par(mfrow = c(2,2))
for(i in 1:5) assign(paste("long.var.name", i, sep = "."), runif(10))
plot(lm(long.var.name.1 ~
        long.var.name.2 + long.var.name.3 + long.var.name.4 + long.var.name.5))
}
par(opar) # reset par()s
}
\keyword{hplot}
\keyword{regression}