scipy.stats.f

scipy.stats.f()

An F continuous random variable.

Continuous random variables are defined from a standard form and may require some shape parameters to complete its specification. Any optional keyword parameters can be passed to the methods of the RV object as given below:

Parameters:

x : array-like

quantiles

q : array-like

lower or upper tail probability

dfn,dfd : array-like

shape parameters

loc : array-like, optional

location parameter (default=0)

scale : array-like, optional

scale parameter (default=1)

size : int or tuple of ints, optional

shape of random variates (default computed from input arguments )

moments : string, optional

composed of letters [‘mvsk’] specifying which moments to compute where ‘m’ = mean, ‘v’ = variance, ‘s’ = (Fisher’s) skew and ‘k’ = (Fisher’s) kurtosis. (default=’mv’)

Methods:

f.rvs(dfn,dfd,loc=0,scale=1,size=1) :

• random variates

f.pdf(x,dfn,dfd,loc=0,scale=1) :

• probability density function

f.cdf(x,dfn,dfd,loc=0,scale=1) :

• cumulative density function

f.sf(x,dfn,dfd,loc=0,scale=1) :

• survival function (1-cdf — sometimes more accurate)

f.ppf(q,dfn,dfd,loc=0,scale=1) :

• percent point function (inverse of cdf — percentiles)

f.isf(q,dfn,dfd,loc=0,scale=1) :

• inverse survival function (inverse of sf)

f.stats(dfn,dfd,loc=0,scale=1,moments=’mv’) :

• mean(‘m’), variance(‘v’), skew(‘s’), and/or kurtosis(‘k’)

f.entropy(dfn,dfd,loc=0,scale=1) :

• (differential) entropy of the RV.

f.fit(data,dfn,dfd,loc=0,scale=1) :

• Parameter estimates for f data

Alternatively, the object may be called (as a function) to fix the shape, :

location, and scale parameters returning a “frozen” continuous RV object: :

rv = f(dfn,dfd,loc=0,scale=1) :

• frozen RV object with the same methods but holding the given shape, location, and scale fixed

Examples

>>> import matplotlib.pyplot as plt
>>> numargs = f.numargs
>>> [ dfn,dfd ] = [0.9,]*numargs
>>> rv = f(dfn,dfd)

Display frozen pdf

>>> x = np.linspace(0,np.minimum(rv.dist.b,3))
>>> h=plt.plot(x,rv.pdf(x))

Check accuracy of cdf and ppf

>>> prb = f.cdf(x,dfn,dfd)
>>> h=plt.semilogy(np.abs(x-f.ppf(prb,c))+1e-20)

Random number generation

>>> R = f.rvs(dfn,dfd,size=100)

F distribution

df2**(df2/2) * df1**(df1/2) * x**(df1/2-1)

F.pdf(x,df1,df2) = ——————————————–

(df2+df1*x)**((df1+df2)/2) * B(df1/2, df2/2)

for x > 0.