% File src/library/stats/man/Normal.Rd
% Part of the R package, http://www.R-project.org
% Copyright 1995-2014 R Core Team
% Distributed under GPL 2 or later

\name{Normal}
\alias{Normal}
\alias{dnorm}
\alias{pnorm}
\alias{qnorm}
\alias{rnorm}
% These concepts are for the last example
\concept{error function}
\concept{erf}
\concept{erfc}
\concept{erfinv}
\concept{erfcinv}
\title{The Normal Distribution}
\description{
  Density, distribution function, quantile function and random
  generation for the normal distribution with mean equal to \code{mean}
  and standard deviation equal to \code{sd}.
}
\usage{
dnorm(x, mean = 0, sd = 1, log = FALSE)
pnorm(q, mean = 0, sd = 1, lower.tail = TRUE, log.p = FALSE)
qnorm(p, mean = 0, sd = 1, lower.tail = TRUE, log.p = FALSE)
rnorm(n, mean = 0, sd = 1)
}
\arguments{
  \item{x, q}{vector of quantiles.}
  \item{p}{vector of probabilities.}
  \item{n}{number of observations. If \code{length(n) > 1}, the length
    is taken to be the number required.}
  \item{mean}{vector of means.}
  \item{sd}{vector of standard deviations.}
  \item{log, log.p}{logical; if TRUE, probabilities p are given as log(p).}
  \item{lower.tail}{logical; if TRUE (default), probabilities are
    \eqn{P[X \le x]} otherwise, \eqn{P[X > x]}.}
}
\value{
  \code{dnorm} gives the density,
  \code{pnorm} gives the distribution function,
  \code{qnorm} gives the quantile function, and
  \code{rnorm} generates random deviates.
  
  The length of the result is determined by \code{n} for
  \code{rnorm}, and is the maximum of the lengths of the
  numerical arguments for the other functions.  
  
  The numerical arguments other than \code{n} are recycled to the
  length of the result.  Only the first elements of the logical
  arguments are used.
  
  For \code{sd = 0} this gives the limit as \code{sd} decreases to 0, a
  point mass at \code{mu}.
  \code{sd < 0} is an error and returns \code{NaN}.
}
\details{
  If \code{mean} or \code{sd} are not specified they assume the default
  values of \code{0} and \code{1}, respectively.

  The normal distribution has density
  \deqn{
    f(x) =
    \frac{1}{\sqrt{2\pi}\sigma} e^{-(x-\mu)^2/2\sigma^2}}{
    f(x) = 1/(\sqrt(2 \pi) \sigma) e^-((x - \mu)^2/(2 \sigma^2))
  }
  where \eqn{\mu} is the mean of the distribution and
  \eqn{\sigma} the standard deviation.
}
\seealso{
  \link{Distributions} for other standard distributions, including
  \code{\link{dlnorm}} for the \emph{Log}normal distribution.
}
\source{
  For \code{pnorm}, based on

  Cody, W. D. (1993)
  Algorithm 715: SPECFUN -- A portable FORTRAN package of special
  function routines and test drivers.
  \emph{ACM Transactions on Mathematical Software} \bold{19}, 22--32.

  For \code{qnorm}, the code is a C translation of

  Wichura, M. J. (1988)
  Algorithm AS 241: The percentage points of the normal distribution.
  \emph{Applied Statistics}, \bold{37}, 477--484.

  which provides precise results up to about 16 digits.

  For \code{rnorm}, see \link{RNG} for how to select the algorithm and
  for references to the supplied methods.
}
\references{
  Becker, R. A., Chambers, J. M. and Wilks, A. R. (1988)
  \emph{The New S Language}.
  Wadsworth & Brooks/Cole.

  Johnson, N. L., Kotz, S. and Balakrishnan, N. (1995)
  \emph{Continuous Univariate Distributions}, volume 1, chapter 13.
  Wiley, New York.
}
\examples{
require(graphics)

dnorm(0) == 1/sqrt(2*pi)
dnorm(1) == exp(-1/2)/sqrt(2*pi)
dnorm(1) == 1/sqrt(2*pi*exp(1))

## Using "log = TRUE" for an extended range :
par(mfrow = c(2,1))
plot(function(x) dnorm(x, log = TRUE), -60, 50,
     main = "log { Normal density }")
curve(log(dnorm(x)), add = TRUE, col = "red", lwd = 2)
mtext("dnorm(x, log=TRUE)", adj = 0)
mtext("log(dnorm(x))", col = "red", adj = 1)

plot(function(x) pnorm(x, log.p = TRUE), -50, 10,
     main = "log { Normal Cumulative }")
curve(log(pnorm(x)), add = TRUE, col = "red", lwd = 2)
mtext("pnorm(x, log=TRUE)", adj = 0)
mtext("log(pnorm(x))", col = "red", adj = 1)

## if you want the so-called 'error function'
erf <- function(x) 2 * pnorm(x * sqrt(2)) - 1
## (see Abramowitz and Stegun 29.2.29)
## and the so-called 'complementary error function'
erfc <- function(x) 2 * pnorm(x * sqrt(2), lower = FALSE)
## and the inverses
erfinv <- function (x) qnorm((1 + x)/2)/sqrt(2)
erfcinv <- function (x) qnorm(x/2, lower = FALSE)/sqrt(2)
}
\keyword{distribution}