Package Biskit :: Package Statistics :: Module lognormal

[frames] | no frames]

Module lognormal

source code

lognormal distribution

Classes

[hide private]

Test
Test class

Functions

[hide private]

rand_log_normal(alpha, beta, shape)

ln(r, alpha, beta)

float erf(x)
Approximation to the erf-function with fractional error everywhere less than 1.2e-7

float logArea(x, alpha, beta)
Area of the smallest interval of a lognormal distribution that still includes x.

float logMean(alpha, beta)
Returns mean of the original lognormal distribution

float logSigma(alpha, beta)
Returns 'standard deviation' of the original lognormal distribution

float logMedian(alpha, beta=None)
Returns median of the original lognormal distribution

(float, float) logConfidence(x, R, clip=0)
Estimate the probability of x NOT beeing a random observation from a lognormal distribution that is described by a set of random values.

Variables

[hide private]

test = Test()

Function Details

[hide private]

rand_log_normal(alpha, beta, shape)

source code

ln(r, alpha, beta)

source code

erf(x)

source code

Approximation to the erf-function with fractional error everywhere less than 1.2e-7

Parameters:

x (float) - value

Returns: float: value

logArea(x, alpha, beta)

source code

Area of the smallest interval of a lognormal distribution that still includes x.

Parameters:

x (float) - border value
alpha (float) - mean of log-transformed distribution
beta (float) - standarddev of log-transformed distribution

Returns: float: probability that x is NOT drawn from the given distribution

logMean(alpha, beta)

source code

Parameters:

alpha (float) - mean of log-transformed distribution
beta (float) - standarddev of log-transformed distribution

Returns: float: mean of the original lognormal distribution

logSigma(alpha, beta)

source code

Parameters:

alpha (float) - mean of log-transformed distribution
beta (float) - standarddev of log-transformed distribution

Returns: float: 'standard deviation' of the original lognormal distribution

logMedian(alpha, beta=None)

source code

Parameters:

alpha (float) - mean of log-transformed distribution
beta (float) - not needed

Returns: float: median of the original lognormal distribution

logConfidence(x, R, clip=0)

source code

Estimate the probability of x NOT beeing a random observation from a lognormal distribution that is described by a set of random values.

Parameters:

x (float) - observed value
R ([float]) - sample of random values
clip (float) - clip zeros at this value 0->don't clip (default: 0)

Returns: (float, float): confidence that x is not random, median of random distr.

Variables Details

[hide private]

test

Value:

Test()