distribMode {modeest}R Documentation

Computing the Mode of Some Distributions

Description

These functions return the mode of the main probability distributions implemented in R.

Usage

  ## Continuous distributions
  betaMode(shape1, shape2, ncp = 0) # Beta
  cauchyMode(location = 0, ...) # Cauchy
  chisqMode(df, ncp = 0) # Chisquare
  expMode(...) # Exponentiel
  fMode(df1, df2) # F
  frechetMode(loc = 0, scale = 1, shape = 1, ...) # Frechet (package 'evd')
  gammaMode(shape, rate = 1, scale = 1/rate) # Gamma
  normMode(mean = 0, ...) # Normal (Gaussian)
  gevMode(loc = 0, scale = 1, shape = 0, ...) # Generalised Extreme Value (package 'evd')
  ghMode(alpha = 1, beta = 0, delta = 1, mu = 0, 
         lambda = 1, ...) # Generalised Hyperbolic (package 'fBasics')
  gpdMode(loc = 0, scale = 1, shape = 0, ...) # Generalised Pareto (package 'evd')
  gumbelMode(loc = 0, ...) # Gumbel (package 'evd')
  hypMode(alpha = 1, beta = 0, delta = 1, mu = 0, 
          pm = c(1, 2, 3, 4)) # Hyperbolic (package 'fBasics')
  logisMode(location = 0, ...) # Logistic
  lnormMode(meanlog = 0, sdlog = 1) # Lognormal
  nigMode(alpha = 1, beta = 0, delta = 1, 
          mu = 0, ...) # Normal Inverse Gaussian (package 'fBasics')
  stableMode(alpha, beta, gamma = 1, delta = 0, pm = 0, ...) # Stable (package 'fBasics')
  symstbMode(...) # Symmetric stable (package 'fBasics')
  rweibullMode(loc = 0, scale = 1, shape = 1, ...) # Negative Weibull (package 'evd')
  tMode(df, ncp = 0) # T (Student)
  unifMode(min = 0, max = 1) # Uniform
  weibullMode(shape, scale = 1, ...) # Weibull
  
  ## Discrete distributions
  bernMode(prob) # Bernoulli
  binomMode(size, prob) # Binomial
  geomMode(...) # Geometric
  hyperMode(m, n, k, ...) # Hypergeometric
  nbinomMode(size, prob, mu) # Negative Binomial
  poisMode(lambda) # Poisson

Arguments

shape1, shape2, ncp, location, df, df1, df2, loc, scale, shape,
rate, mean, alpha, beta, delta, mu, lambda, pm, meanlog, sdlog,
gamma, min, max, prob, size, m, n, k The different arguments are those of the corresponding distribution functions.
... Further arguments, which will be ignored.

Value

A numeric value is returned, the (true) mode of the distribution.

Note

Some functions like normMode or cauchyMode, which are related to symmetric distributions, are trivial, but are implemented for exhaustivity.

Author(s)

Paul Poncet paulponcet@yahoo.fr, except for hypMode and stableMode written by Diethelm Wuertz, see package fBasics.

See Also

mlv for the estimation of the mode; the documentation of the related distributions Beta, GammaDist, etc.

Examples

layout(mat = matrix(1:2,1,2))

## Beta distribution
curve(dbeta(x, shape1 = 2, shape2 = 3.1), xlim = c(0,1), ylab = "Beta density")
M <- betaMode(shape1 = 2, shape2 = 3.1)
abline(v = M, col = 2)
mlv("beta", shape1 = 2, shape2 = 3.1)
 
## Lognormal distribution          
curve(dlnorm(x, meanlog = 3, sdlog = 1.1), xlim = c(0, 10), ylab = "Lognormal density")
M <- lnormMode(meanlog = 3, sdlog = 1.1)
abline(v = M, col = 2)
mlv("lnorm", meanlog = 3, sdlog = 1.1) 

## Poisson distribution
poisMode(lambda = 6)
poisMode(lambda = 6.1)
mlv("poisson", lambda = 6.1)

layout(mat = matrix(1,1,1)) 

[Package modeest version 1.09 Index]