Scribd
Upload
14K views2 pages

Cauchy Distribution (From

The Cauchy distribution has a probability density function that depends on location parameter a and positive scale parameter α. It is useful because the distribution's moments are undefined. The cumulative distribution and survivor functions are given, as well as the hazard function and cumulative hazard function. The population median is the location parameter a, while the population moments are all undefined.

Uploaded by

Ravi Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
14K views2 pages

Cauchy Distribution (From

The Cauchy distribution has a probability density function that depends on location parameter a and positive scale parameter α. It is useful because the distribution's moments are undefined. The cumulative distribution and survivor functions are given, as well as the hazard function and cumulative hazard function. The population median is the location parameter a, while the population moments are all undefined.

Uploaded by

Ravi Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Cauchy distribution (from http://www.math.wm.edu/˜leemis/chart/UDR/UDR.

html)
The shorthand X ∼ Cauchy(a, α) is used to indicate that the random variable X has the Cauchy
distribution with positive scale parameter α and location parameter a. A Cauchy random variable
X with parameters a and α has probability density function
1
f (x) = −∞ < x < ∞
απ[1 + ((x − a)/α)2 ]
for α > 0 and −∞ < a < ∞. The Cauchy distribution is of interest because its moments are unde-
fined. The probability density function for various combinations of a and α is given below.

f (x)
1.4
1.2
a = 1, α = 0.25
1.0
0.8
0.6
a = 2, α = 0.5
0.4
0.2 a = 3, α = 1
0.0 x
−1 0 1 2 3 4 5 6

The cumulative distribution function on the support of X is


  
1 a−x
F(x) = P(X ≤ x) = π − 2 arctan − ∞ < x < ∞.
2π α
The survivor function on the support of X is
  
1 a−x
S(x) = P(X ≥ x) = π + 2 arctan − ∞ < x < ∞.
2π α
The hazard function on the support of X is

a − x −1
  
f (x) 2 2 2 −1

h(x) = = 2 α α − 2 xa + a + x π + 2 arctan − ∞ < x < ∞.
S(x) α
The cumulative hazard function on the support of X is
  
a−x
H(x) = − ln S(x) = ln (2π) − ln π + 2 arctan − ∞ < x < ∞.
α
The inverse distribution function of X is
F −1 (u) = a − α cot (πu) 0 < u < 1.

1
The population median of X is the location parameter, a.

The population moments of X are undefined. It follows that the population mean, variance, skew-
ness, and kurtosis of X are also undefined.
APPL verification: The APPL statements

X := CauchyRV(a, alpha);
CDF(X);
SF(X);
HF(X);
IDF(X);
Mean(X);
Variance(X);
Skewness(X);
Kurtosis(X);
MGF(X);

verify the cumulative distribution function, survivor function, hazard function, mean, variance,
skewness, kurtosis, and moment generating function.

You might also like