Scribd
Upload
181 views

Uniform Distribution: Function Is Given by

The uniform distribution describes a population that is evenly distributed over an interval. It has a constant probability density function between two points a and b. The expected value of a uniform distribution is the average of the interval, and the variance measures how far values are from the average. The uniform distribution is useful for modeling measurement errors and generating random numbers from other distributions.

Uploaded by

Fabricio GZ
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
181 views

Uniform Distribution: Function Is Given by

The uniform distribution describes a population that is evenly distributed over an interval. It has a constant probability density function between two points a and b. The expected value of a uniform distribution is the average of the interval, and the variance measures how far values are from the average. The uniform distribution is useful for modeling measurement errors and generating random numbers from other distributions.

Uploaded by

Fabricio GZ
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

U

⎧
0 ⎪
⎪ if x ≤ a
Uniform Distribution x−a ⎨
F (x) = if a < x < b
⎪ b−a
⎪
A uniform distribution is used to describe ⎩
1 otherwise .
a population that is uniformly distributed in
an interval. The expected value of a random variable
A random variable X is said to be uniformly that is uniformly distributed in an interval
distributed in the interval [a, b] if its density [a, b] is equal to:
function is given by:
⎧  b x b2 − a2 a+b
⎨ 1 E [X] = dx = = .
if a ≤ x ≤ b a b−a 2 (b − a) 2
f (x) = b−a
⎩
0 otherwise .
This result is intuitively very easy to under-
Because of the rectangular shape of its den- stand because the density function is sym-
sity function, the uniform distribution is metric around the middle point of the inter-
also sometimes called the rectangular distri- val [a, b].
bution. We can calculate
   b b2 + ab + a2
E X2 = x2 f (x) dx = .
a 3

The variance is therefore equal to:


  (b − a)2
Var (X) = E X 2 − (E [X])2 = .
12

Uniform distribution, a = 1, b = 3 The uniform distribution is a particular case


of the beta distribution when α = β = 1.
The uniform distribution is a continuous
probability distribution. DOMAINS AND LIMITATIONS
Applications of the uniform distribution are
MATHEMATICAL ASPECTS numerous in the construction of models for
The distribution function of a uniform physical, biological, and social phenomena.
distribution is the following: The uniform distribution is often used as
554 Unimodal Distribution

a model for errors of approximation dur- to 1, then its distribution function is


ing measurements. For example, if the length
of some objects is measured with a 1-cm F (x) = 1 − exp (−x) .
precision, a length of 35 cm can represent
Since F(x) = u, we have u = 1 − e−x .
all the objects with a length between 34.5
To find x, we search for F −1 :
and 35.5 cm. The approximation errors fol-
low a uniform distribution in the interval u = 1 − e−x ,
[−0.5, 0.5].
u − 1 = −e−x ,
The uniform distribution is often used to gen-
erate random numbers of any discrete or 1 − u = e−x ,
continuous probability distribution. The ln(1 − u) = −x ,
method used to generate a continuous distri- − ln(1 − u) = x .
bution is the following.
Consider X a continuous random variable Notice that if u is a random variable that is
and F(x) its distribution function. Suppose uniform in [0,1], then (1 − u) is also a ran-
that F is continuous and strictly increasing. dom variable that is uniform in [0,1].
Then U = F(X) is a uniform and con- By applying the aforementioned to a series of
tinuous random variable. U takes its values random numbers, we find a sample taken
in the interval [0,1]. We then have X = from X:
F −1 (U), where F −1 is the inverse function
U X
of the distribution function.
0.14 1.97
Therefore, if u1 , u2 , . . . , un is a series of ran-
0.97 0.03
dom numbers, then:
0.53 0.63
−1
x1 = F (u1 ) , 0.73 0.31
.. ..
x2 = F −1 (u2 ) , . .

... ,
FURTHER READING
xn = F −1 (un )
 Beta distribution
is a series of random numbers generated from  Continuous probability distribution
the distribution of the random variable X.  Discrete uniform distribution

EXAMPLES
Unimodal Distribution
If random variable X follows a negative
exponential distribution of mean equal See frequency distribution.

You might also like