Statistics/Distributions/Gamma

From Wikibooks, open books for an open world
Jump to navigation Jump to search

Gamma Distribution[edit | edit source]

Gamma
Probability density function
Probability density plots of gamma distributions
Cumulative distribution function
Cumulative distribution plots of gamma distributions
Parameters
  • shape
  • scale
Support
PDF
CDF
Mean

(see digamma function)
Median No simple closed form
Mode
Variance

(see trigamma function )
Skewness
Ex. kurtosis
Entropy

The Gamma distribution is very important for technical reasons, since it is the parent of the exponential distribution and can explain many other distributions.

The probability distribution function is:

Where is the Gamma function. The cumulative distribution function cannot be found unless p=1, in which case the Gamma distribution becomes the exponential distribution. The Gamma distribution of the stochastic variable X is denoted as .

Alternatively, the gamma distribution can be parameterized in terms of a shape parameter and an inverse scale parameter , called a rate parameter:

where the constant can be calculated setting the integral of the density function as 1:

following:

and, with change of variable  :

following:

Probability Density Function[edit | edit source]

We first check that the total integral of the probability density function is 1.

Now we let y=x/a which means that dy=dx/a

Mean[edit | edit source]

Now we let y=x/a which means that dy=dx/a.

We now use the fact that

Variance[edit | edit source]

We first calculate E[X^2]

Now we let y=x/a which means that dy=dx/a.

Now we use calculate the variance

External links[edit | edit source]