Continuous Probability Distributions

In a continuous distribution, the random variable, X, can take up any value within the range of the
continuous random variable. The range may be either an infinite range, - < x <  or a finite range
with specified lower and upper limits, a < x < b. Thus, the possible values are uncountably infinite
and it is difficult to get the probability of a particular value of X. Here, we consider the probability
that the value will be within a particular interval in the range of the continuous random variable.

Probability for a discrete variable is defined at a point such as P(X= 2) or as a sum over a series of
points such as P(x  2) = P(X=0) + P(X=1) + P(X = 2). But when X is a continuous variable,
probabilities are defined as areas under a curve called the probability density function (P.D.F).
Probabilities for a continuous variable are defined on intervals such as P(5<X<10) or P(X<5) or
P(X>10).

Probability Density Function (P.D.F)

The probability distribution for a continuous variable is represented by the graph of a continuous
function, y = f(x), called the probability density function. A probability density function is a
mathematical function denoted by f(x) that describes the shape of a continuous probability
distribution. It shows how the values of a continuous random variable are distributed. For a
continuous variable, every x value on the x-axis has a corresponding height or frequency value. The
probability density function is a mathematical expression that shows the height of the curve f(x) at
each possible value of x.

Any continuous P.D.F must be non-negative and the area under the entire P.D.F must be 1. A P.D.F
may be presented graphically as follows:

f(x)

y = f(x)

0 a b x
The probability of the variable taking any value within a particular interval, say (a, b) equals the
𝑏
area under the curve between a and b. This is equal to the integral ∫𝑎 𝑓(𝑥 )𝑑𝑥, where f(x) is the
probability density function of x.
A probability density function must satisfy the following conditions:

(i) f(x)  0 for all values of x. This condition is necessary because probability cannot be
negative.
∞
(ii) ∫-∞ f(x)dx=1

This condition implies that the area under the curve over the whole range of the variable is 1. The
range of integration is written as - to + so that all possible values of x are covered. If x takes
positive values only in the interval (a, b), and a zero otherwise, the condition reduces to:
b
∫a f(x)dx=1

Page 1 of 6
The expression P(a < x < b) is the integral of the probability density function f(x) over the interval
from a to b. Because P(X = a) = 0, the expression P(a < x < b) is equal to P(a  x  b).

Expected Value (Mean) and Variance

The mean, variance and standard deviation depend on the PDF and its parameters. The mean, , of
the continuous random variable X which has a probability density function f(x) is:
∞
µ = E(X) = ∫-∞ xf(x)dx
The variance, 2 of a continuous random variable x which has the probability density function f(x)
and mean µ is:
∞
∫−∞ 𝑥 2 𝑓 (𝑥 )𝑑𝑥 − 𝜇2

Illustration 1
A random variable X has probability density function:
x
, 1≤x≤3
f(x) = {4
0, Otherwise

Find:
(a) The probability that X lies between 1 and 2
(b) The probability that X lies between 2 and 3
(c) The probability that X lies between 1 and 3
(d) The expected value of X
(e) The variance of X
(f) Sketch the probability density function.

Illustration 2
The random variable X has probability density function

2x
, 0≤x<3,
15
f(x) = {1 (5-x), 3≤x≤5
5
0 otherwise

Find:
(a) The probability that X lies between 0 and 2
(b) The probability that X lies between 2 and 4
(c) E(X)
(d) Var(X)

Illustration 3
The continuous random variable X has a probability density function given by

𝐾𝑥 2 , 0≤x≤2
f(x) = {
0, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
Find:
(a) K
(b) E(X)
(c) Var(X)
Page 2 of 6
Theoretical Probability distributions
(i) Uniform distribution
(ii) The normal distribution
(iii) Exponential distribution

Uniform Distribution
The continuous random variable X has a uniform distribution over the interval (a, b) if the P.D.F is
given by:
1
, a ≤ x ≤b
f(x) = { 𝑏−𝑎
0, 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒

The uniform probability distribution is rectangular in shape and is defined by a minimum value of
a, and a maximum value of b. The height of the distribution is constant or uniform for all values
between a and b. This implies that the values in the range are equally likely.

The mean of a uniform distribution is located at the middle of the interval between the minimum
and maximum values. It is computed as µ = a + b
2
The standard deviation of the uniform distribution is given by:

(𝑏−𝑎)2
𝜎= √ 12

Illustration
An accountant measures the time it takes him to travel from home to work and finds that the journey
takes between 20 and 25 minutes. Any journey time between these limits is equally likely.

Required
(i) Probability density function
(ii) Illustrate the P.D.F with a graph
(iii) Find the probability that the journey takes between 20.5 and 22.8 minutes.
(iv) Find the mean of the probability distribution
(v) What is the standard deviation of the distribution?

Normal distribution
A Normal probability distribution is a distribution of a continuous random variable that applies to
a large number of observations. For instance, if it were possible to measure exactly the heights of
all adult people in Kenya and construct a histogram, the histogram would approach a normal
distribution curve which is represented in the figure below.

Mean x

Example of variables that follow normal distribution include heights of people, weights of people,
body temperature of people, lengths of objects, weights of objects, ages of people etc. There is not

Page 3 of 6
just one normal probability distribution but rather a family of them. For example, probability
distribution of length of employee service in the public sector and private sector could follow a
normal distribution with different means and standard deviations.

If X is a random variable following normal probability distribution with mean  and standard
deviation , then its probability density function is given by:

1 𝑥−𝜇 2
1 − ( )
y = f(x) = 𝑒 2 𝜎
𝜎 √2𝜋

where y = f(x) is the vertical distance between the x-axis and the normal curve.

𝜎 is Standard deviation of the normal distribution

22
 = 7 = 3.1417
e is a natural number = 2.7183
 = mean of the random variable X
x = Specific value taken by the random variable.

The normal distribution is a two-parameter distribution and its 2 parameters are mean,, and
standard deviation 𝜎. It is convenient to use N(, 𝜎) as a label for the normal distribution with
mean  and standard deviation 𝜎.

Properties of Normal distribution

(i) The normal curve is bell-shaped and has a single peak at the centre of the distribution.

Mean x
(ii) The normal curve is symmetrical about the mean. Thus, half the area under the curve is to
the right of the mean and the other half is to the left of it. If a distribution is symmetrical,
mean = mode = median. This also means that the two areas under the curve between the mean
and any two points equidistant on either side of the mean are identical. A distribution is
symmetric when data values are evenly distributed about the mean.

(iii) The two tails of the normal distribution on both sides of x =  approaches but never touches
the horizontal axis. That is, the normal distribution is asymptotic to the x-axis at both
extremes.

(iv) The range of x is from - to +.

(v) The height of the normal curve is maximum at its mean value. This implies that the normal
distribution is unimodal.
(vi) The total area under normal curve is 1.

No variable fits a normal distribution perfectly, since a normal distribution is a theoretical

distribution. However, a normal distribution can be used to describe many random variables
because the deviations from a normal distribution are very small.

Page 4 of 6
Standard Normal Distribution
The probability density function for the normal distribution is a complicated mathematical function
which depends on the values of the mean  and standard deviation 𝜎 of the variable. This property
enables all normal distributions to be reduced to just one distribution; the standard normal
probability distributions with mean = 0 and standard deviation = 1.

Any normal distribution can be converted into a standard normal distribution by subtracting the
mean from each observation and dividing this difference by the standard deviation. The results are
called Z values, Z scores, Z statistics, the standard normal values or standard scores.
Z = x-
𝜎
Where x is the value of any particular observation,  is the mean of the observations and 𝜎 is the
standard deviation of the distribution.
A Z value expresses the distance between a particular value of X and the arithmetic mean in terms
of the standard deviations.
If we put Z = x -  in f(x), the probability density function for the standard normal distribution
𝜎
1 2
1
becomes g(z) = 𝑒 −2 𝑍 , -∞ < z < ∞
√2𝜋
𝑥− 𝜇
If X  N (, 𝜎), then transformation of each x value to z value using the equation 𝑍 = 𝜎 produces
the standard normal distribution expressed as Z  N(0, 1).

Area under Standard Normal Curve

The standard normal curve is symmetrical about Z = 0 as shown below:

-3 -2 -1 0 1 2 3 Z

The total area under the standard normal curve is equal to 1. The area between Z = 0 and Z = -1 is
equal to the area between Z = 0 and Z = 1. The area below Z = 0 is equal to the area above Z = 0
is equal to 0.5.
Once the values of a random variable are converted to the number of standard deviations from the
mean, the required probabilities may be found from the tables. The standard normal table lists the
probabilities for the standard normal distribution. The probabilities are tabulated for values of Z
from Z = 0 to Z = 3.5. The table shows the area between Z = 0 and any positive value of Z. Since
the distribution is symmetrical, the same figures can be used to give the probability of the variable
value being Z or more standard deviations below the mean. The area below Z = -1 is equal to that
above Z = +1. This in turn is equal to 1 – area below Z = +1. Area to the right of Z = 2 is equal to
0.5 – Area between Z = 0 and Z = 2.

ILLUSTRATIONS
(a) The average weekly food expenditure of families in a certain area has a normal distribution with
means Ksh.125 and Standard deviation Ksh.25. What is the probability that a family selected
at random from this area will have an average weekly expenditure of food in excess of Ksh.175?

Page 5 of 6
(b) In a sample of 120 workers in a factory the mean and standard deviation of wages were U.S
dollars 11.35 and 3.03 respectively. (i) Find the probability that a worker selected at random
earns between 9 and 17. (ii) Find the percentage of workers getting wages between 9 and 17 in
the whole factory assuming that the wages are normally distributed.

(c) The incomes of a group of 10,000 persons were found to be normally distributed with mean
equal to 750 and standard deviation equal to 50. What was the lowest income among the richest
250?

(d) In a large group of men, it is found that 5% are under 60 inches and 40% are between 60 and
65 inches in height. Assuming the distribution to be exactly normal, find the mean and the
standard deviation of height.

(e) A sample of 100 dry battery cells tested to find the length of life produced the following results:
𝑥̅ = 12 hours, 𝜎 = 3 hours. Assuming that the data are normally distributed, what percentage of
battery cells are expected to have life:
(i) More than 15 hours
(ii) Less than 6 hours
(iii) Between 10 and 14 hours.

All normal distributions have the same general shape as the one shown on page 3. However,
they can differ in their mean value and their variation depending on the situation being
considered. Every time you specify a particular combination of µ and , a different normal
probability distribution is generated.

The exponential distribution

A continuous random variable X has an exponential distribution if it has, for some  > 0, the P.D.F

f(x) = {
𝑒 −𝑥 , x≥0
0, 𝑥<0

The P.D.F has the graph shown in the figure below.

f(x)

1 2 3 4 5 x

Notice that x may tend to infinity.

Page 6 of 6