Gumbeldf: Difference between revisions

From Eigenvector Research Documentation Wiki
Jump to navigation Jump to search
imported>Jeremy
(Importing text file)
imported>Bob
 
(3 intermediate revisions by one other user not shown)
Line 1: Line 1:
===Purpose===
===Purpose===
Gumbel distribution.
Gumbel distribution.
===Synopsis===
===Synopsis===
:prob = gumbeldf(function,x,a,b)
:prob = gumbeldf(function,x,a,b)
===Description===
===Description===
Estimates cumulative distribution function (cumulative, cdf), probability density function (density, pdf), quantile (inverse of cdf), or random numbers for a Gumbel distribution.  
Estimates cumulative distribution function (cumulative, cdf), probability density function (density, pdf), quantile (inverse of cdf), or random numbers for a Gumbel distribution.  
This distribution is also known as the Type I extreme value distribution. It is an alternative to the Weibull distribution.
This distribution is also known as the Type I extreme value distribution. It is an alternative to the Weibull distribution.
 
====INPUTS====
::<math>f(x) = \frac { \Gamma \left [ \frac {a+b} {2} \right ] \left ( a/b \right )^{a/2} x^{\left ( a-2 \right ) /2}} {\Gamma \left ( \frac {a} {2} \right ) \Gamma \left ( \frac {b} {2} \right ) \left [ 1+ \frac {a} {b} x \right ] ^{\left ( a+b \right )/2}}</math>
 
====Inputs====
 
* '''function''' =  [ {'cumulative'} | 'density' | 'quantile' | 'random' ], defines the functionality to be used. Note that the function recognizes the first letter of each string so that the string could be: [ 'c' | 'd' | 'q' | 'r' ].
* '''function''' =  [ {'cumulative'} | 'density' | 'quantile' | 'random' ], defines the functionality to be used. Note that the function recognizes the first letter of each string so that the string could be: [ 'c' | 'd' | 'q' | 'r' ].
* '''x''' = matrix in which the sample data is stored, in the interval (-inf,inf).  
* '''x''' = matrix in which the sample data is stored, in the interval (-inf,inf).  
*  '''for''' function=quantile - matrix with values in the interval (0,1).
:: for function=quantile - matrix with values in the interval (0,1).
*  '''for''' function=random - vector indicating the size of the random matrix to create.
:: for function=random - vector indicating the size of the random matrix to create.
 
* '''a''' = mode/location parameter (real).
* '''a''' = mode/location parameter (real).
*  '''b''' = scale parameter (real and positive).
*  '''b''' = scale parameter (real and positive).
'''Note''': If inputs (x, a, and b) are not equal in size, the function will attempt to resize all inputs to the largest input using the RESIZE function.  
'''Note''': If inputs (x, a, and b) are not equal in size, the function will attempt to resize all inputs to the largest input using the RESIZE function.  
'''Note''': Functions will typically allow input values outside of the acceptable range to be passed but such values will return NaN in the results.  
 
'''Note''': Functions will typically allow input values outside of the acceptable range to be passed but such values will return NaN in the results.
 
===Examples===
===Examples===
====Cumulative:====
 
====Cumulative====
<pre>
>> prob = gumbeldf('c',0.99,0.5,1)
>> prob = gumbeldf('c',0.99,0.5,1)
prob =
prob =
Line 23: Line 40:
>> x    = [0:0.1:10];
>> x    = [0:0.1:10];
>> plot(x,gumbeldf('c',x,2),'b-',x,gumbeldf('c',x,0.5),'r-')
>> plot(x,gumbeldf('c',x,2),'b-',x,gumbeldf('c',x,0.5),'r-')
====Density:====
</pre>
====Density====
<pre>
>> prob = gumbeldf('d',0.99,0.5,1)
>> prob = gumbeldf('d',0.99,0.5,1)
prob =
prob =
Line 29: Line 48:
>> x    = [0:0.1:10];
>> x    = [0:0.1:10];
>> plot(x,gumbeldf('d',x,2),'b-',x,gumbeldf('d',x,0.5),'r-')
>> plot(x,gumbeldf('d',x,2),'b-',x,gumbeldf('d',x,0.5),'r-')
====Quantile:====
</pre>
====Quantile====
<pre>
>> prob = gumbeldf('q',0.99,0.5,1)
>> prob = gumbeldf('q',0.99,0.5,1)
prob =
prob =
     5.1001
     5.1001</pre>
====Random:====
 
====Random====
<pre>
>> prob = gumbeldf('r',[4 1],2,1)
>> prob = gumbeldf('r',[4 1],2,1)
ans =
ans =
Line 40: Line 63:
     2.3566
     2.3566
     4.2479
     4.2479
</pre>
===See Also===
===See Also===
[[betadr]], [[cauchydf]], [[chidf]], [[expdf]], [[gammadf]], [[laplacedf]], [[logisdf]], [[lognormdf]], [[normdf]], [[paretodf]], [[raydf]], [[triangledf]], [[unifdf]], [[weibulldf]]
 
[[betadf]], [[cauchydf]], [[chidf]], [[expdf]], [[gammadf]], [[laplacedf]], [[logisdf]], [[lognormdf]], [[normdf]], [[paretodf]], [[raydf]], [[triangledf]], [[unifdf]], [[weibulldf]]

Latest revision as of 06:15, 10 October 2008

Purpose

Gumbel distribution.

Synopsis

prob = gumbeldf(function,x,a,b)

Description

Estimates cumulative distribution function (cumulative, cdf), probability density function (density, pdf), quantile (inverse of cdf), or random numbers for a Gumbel distribution.

This distribution is also known as the Type I extreme value distribution. It is an alternative to the Weibull distribution.

Inputs

  • function = [ {'cumulative'} | 'density' | 'quantile' | 'random' ], defines the functionality to be used. Note that the function recognizes the first letter of each string so that the string could be: [ 'c' | 'd' | 'q' | 'r' ].
  • x = matrix in which the sample data is stored, in the interval (-inf,inf).
for function=quantile - matrix with values in the interval (0,1).
for function=random - vector indicating the size of the random matrix to create.
  • a = mode/location parameter (real).
  • b = scale parameter (real and positive).

Note: If inputs (x, a, and b) are not equal in size, the function will attempt to resize all inputs to the largest input using the RESIZE function.

Note: Functions will typically allow input values outside of the acceptable range to be passed but such values will return NaN in the results.

Examples

Cumulative

>> prob = gumbeldf('c',0.99,0.5,1)
prob =
    0.5419
>> x    = [0:0.1:10];
>> plot(x,gumbeldf('c',x,2),'b-',x,gumbeldf('c',x,0.5),'r-')

Density

>> prob = gumbeldf('d',0.99,0.5,1)
prob =
0.3320
>> x    = [0:0.1:10];
>> plot(x,gumbeldf('d',x,2),'b-',x,gumbeldf('d',x,0.5),'r-')

Quantile

>> prob = gumbeldf('q',0.99,0.5,1)
prob =
    5.1001

Random

>> prob = gumbeldf('r',[4 1],2,1)
ans =
    3.8437
    2.6508
    2.3566
    4.2479

See Also

betadf, cauchydf, chidf, expdf, gammadf, laplacedf, logisdf, lognormdf, normdf, paretodf, raydf, triangledf, unifdf, weibulldf