Continuous probability

distribution

Dr. Harriet Oboge

Introduction - Continuous probability distribution

• A continuous random variable X can assume any value x in an interval

on the real line or in a collection of intervals
• It is not possible to talk about probability of a random variable
assuming a particuler value x
• Instead we talk about the probability of the random variable
assuming a value within a given interval
• The probability of the random variable assuming value within some
given interval, from x1 to x2 is defined to be the area under the graph
of the probability density function between x1 and x2
• Nature and distribution of a continuous random variable shown in Figure 1, shows the
distribution of heights of students in a particular college from a hypothetical data which is
approximately normal distribution.
• Heights represent number of values of the variable falling between two specified points,
and the widths are distances between two specified points on the line (Reference;
descriptive statistics for categorical data)

Figure 1: a histogram resulting from data on heights of students attending college

• The intervals defined by any two consecutive specified points are called class
intervals.
• The subareas of a histogram correspond to the frequencies of occurrence of
values of the variable between the horizontal scale boundaries of these sub
areas. These provide a way through which relative frequency of occurrence of
values between any two specified points can be calculated.
• This involves getting the proportion of the histograms total area falling
between the specified points.
• If we were to connect the midpoints of the cells of the histogram in Figure 1,
we would have a much smoother curve. This curve represents a frequency
polygon.
• As the number of observations approaches infinity and the width of the
class intervals approaches zero, then the frequency polygon would
approach a smooth curve as shown in Figure 2.
• These smooth curves can be used to represent graphically the distribution
of continuous random variables. These have some important
consequences when we deal with probability distributions.

Figure 2. demonstration of the area under a curve

Normal probability distribution

• It is the most important distribution for describing a continuous

random variable
• It is widely used in statistical inference
• When a variable is influenced by many small independent factors,
none of which predominate , it is likely to be normally distributed
• Applications; IQ, height, scientific measurement (Antibody titres)
Standard Normal Probability Distribution

• Definition: A random variable having a normal distribution with a mean 0 and a

standard deviation of 1
• A random variable Y is said to be normally distributed if and only if its probability
density is given by:

• Where μ is the mean and is the standard deviation of the variable Y. The total
area under the curve defined by this function is one unity.
Important characteristics of a normal distribution
a. It is symmetrical about its mean μ, that is the curve on either side is a
mirror image of the other side
b. The mean, median, mode are equal (measures of central tendency)
c. The total area under the curve above the x-axis is one square unit, this
characteristic follows from the fact that the normal distribution is a
probability distribution, and because of the symmetry, 50% of the area
is to the right of a perpendicular erected at the mean and 50% is to the
left
d. If we erect perpendicularly a distance of one standard deviation from the
mean in both directions, the area enclosed by these perpendiculars, the
x-axis and the curve will be approximately 68% of the total area. If we
extend these lateral boundaries a distance of two standard deviations on
either side of the mean, approximately 95% of the total area will be
enclosed. And extending these perpendiculars a distance of three
standard deviations on either side of the mean will enclose
approximately 99.7% of the total area under the curve.
e. The normal distribution is completely determined by the parameters of
mean μ and standard deviation
• Different values of the mean will shift the graph of the distribution along the
x-axis
• Different values of the standard deviation will determine the degree of
flatness or peakedness of the graph of the distribution

Figure 3: effects of different values of mean on shifting the graph of the distribution along the X -axis

Figure 4: effects of different values of standard deviation on the degree of peakedness or flatness of distribution
• For the last characteristic of the normal distribution, a distribution with a mean of 0
and a standard deviation of 1 has been described. This is referred to us the unit
normal or standard normal distribution.
• A random variable that result from this standard normal distribution is denoted Z and
it is represented by the formula;

• We can think of Z as a measure of the number of standard deviations Y is from μ (take

each value of the data, subtract mean and divide by the standard deviation)
• Where Z is a standard normal variable whose probabilities have been calculated and
tabulated, Y is a normally distributed variable, μ is the population mean and is the
population standard deviation.
Z-Scores
• Often a standardized value
• It denotes the number of standard deviations a value is away from the
mean
• Measures the location in a distribution
• Note that probability increases as we move closer and closer to the mean but
decreases as we move further away on either side.
• If we made the class intervals smaller and smaller, we would eventually define a
smooth curve shaped like the cross-section of a bell.
• There are two important "parameters" that we need to know to calculate
probabilities from the normal probability density:
• (a) Mean (μ) - Locates the central position
• (b) Variance (²) or its square root, the standard deviation () - measures the
degree of "spread" about the mean
• If we know the mean and the variance of a normally distributed variable, we can
determine the probability that such a variable will take for a value that lies between two
points A and B.
• We can get the area under the curve between points A and B by integrating the normal
equation with respect to Y from point A to B.
• We can simplify the method of determining the probabilities for any normally
distributed variable by transforming the variable to a standard variable whose
probabilities have been calculated and tabulated.
• The standard variable is called the standard normal deviate and is denoted by the
letter Z.
• The standard normal variable Z is a normally distributed variable with a mean of 0
and a variance of 1.
• We transform the values of any normally distributed variable (Y) to a standard normal
deviate (Z) by subtracting the mean from the observation and dividing by the standard
deviation as shown below:
• We can use the probabilities associated with values of the standard normal
deviate to calculate probabilities of any normally distributed variable using
the relationship:
Example 1
• Rectal temperatures were taken for a cat over a 24-hour period. The mean temperature
(μ) was 39.1oC and the standard deviation (σ) was 0.18. What is the probability that that
the cat's temperature would be higher than 39.5?
• For P (Temp > 39.5), we calculate Z as:

• Z = (39.5 - 39.1)/0.18 = 0.04/0.18 = 2.22

• Therefore P (temp > 39.5) = P (Z > 2.22)
• Z value in statistical tables at 2.22 = 0.4868 (Value from half of standard curve)
• Z value in alternative table = 0.9868 (Value from full standard curve)
• Therefore P (Z > 2.22) = 0.5 - 0.4868 = 0.0132
• Or P(Z> 2.22) = 1 – 0.9868 = 0.0132
• Probability of Z > 2.22 = P(temp > 39.5) = 0.0132
Example 2
What is the probability that the temp is between 39.5 and 40?