SUBJECT: STATISTICS AND PROBABILITY MIXED TYPE RANDOM VARIABLE

TOPIC: RANDOM VARIABLES The way the discrete random variable is defined, we can say
that the range of values that can be assigned is confined to
RANDOM VARIABLE
the set of whole numbers. That is a discrete random variable
It is a quantitative variable that is derived from the outcomes may NOT take on non-integers. However, some multi-step
of a random experiment. It is usually denoted by English experiments may yield a different kind of random variable –
capital letters X, Y, and Z. The specific values of a random one that is neither discrete nor continuous – and is commonly
variable is denoted by small letters. referred to as a mixed-type random variable.

DISCRETE RANDOM VARIABLE EXAMPLE:

It is a random variable that can take only whole number Suppose a coin is tossed, and a number cube is rolled if the
values, outcomes that are countable. This type of variable is coin turns up a head.
associated with experiments for which there are a finite
In this experiment, a random variable of mixed-type, 𝒙 , could
number of possible outcomes.
be defined in the following way:
EXAMPLE 1:
Let 𝑋 = −1 if the coin turns up a tail
The number of children in a family is an example of a discrete
𝑋 =the number on the number cube if the coin turns up a
random variable. There can only be a finite number of children
head.
in each family, and this can be counted. The random variable
may take on the following values: 0, 1, 2, … That is, a family In this example, the possible values of 𝑋 are in the set
may have no child, one child, two children, and so on. The {−1,1,2,3,4,5,6}
upper limit of the set will depend on the data gathered, but it
is important to note that this variable can only take on integral
values. We wouldn’t want to report fractional parts of children. TOPIC: DISCRETE PROBABILITY DISTRIBUTIONS
CONTINUOUS RANDOM VARIABLE DISCRETE PROBABILITY DISTRIBUTION
It is a random variable that can take on non-integers as they A discrete probability distribution is a list of probabilities
take on values contained in an interval. This random variable for each of the distinct outcomes of a discrete random
is associated with experiments with infinitely many possible variable.
outcomes, and is commonly used for measurements such as
length, weight, and time. EXAMPLE 1:

EXAMPLE 2: In a box are 2 balls – one red and one blue. Two balls are
picked one at a time with replacement.
Ten children were asked to solve the Rubik’s cube. The time
it took for them to complete the puzzle is summarized in the There are 4 possible outcomes for this experiment:
table below. 𝑆 = {(𝑏𝑙𝑢𝑒, 𝑏𝑙𝑢𝑒), (𝑏𝑙𝑢𝑒 , 𝑟𝑒𝑑), (𝑟𝑒𝑑, 𝑏𝑙𝑢𝑒), (𝑟𝑒𝑑, 𝑟𝑒𝑑)}

Thus, 𝑛(𝑆) = 4

Let 𝑋 = the number of red balls drawn. Therefore, 𝑋 has the

possible values 𝑋 = {0,1,2}

One way to represent it is by creating a probability distribution

The time it takes for a child to complete the Rubik's cube is a table. Note that the probability distribution of 𝑋 can be written
continuous random variable, since a child could have finished as 𝑃(𝑋 = 𝑥) , where 𝑥 are the specific values of 𝑋.
the puzzle in 1.2 minutes, or 2.5 minutes, and so on.
HISTOGRAM Now, when we substitute the possible values of 𝑋 , we have

The information in a probability distribution may be presented 1 3 4

𝑃(1) + 𝑃(3) + 𝑃(4) = + + =1
in the form of a histogram, or a graph using bars to relate 8 8 8
variables on a horizontal and a vertical axis. The histogram is
Thus, the second property is satisfied.
constructed by listing all the possible values of X in an equally
𝑥
spaced scale in the x-axis and then locating their Since the two properties are satisfied, 𝑃(𝑥) = 8 for 𝑥 =
corresponding probability in y-axis. 1, 3, 4 is a discrete probability distribution.

PROBABILITY MASS FUNCTION (PMF)

For each possible value of a random variable 𝑥 there is a

corresponding probability. The probability mass function
(pmf) of 𝑋 is the function that gives the probabilities of the
possible events of the random variable.

EXAMPLE 4:

Suppose the numbers 1,2,3, and 6 are written cards that are
placed in a box. Two cards are picked from the box. Let 𝑋 be
PROPERTIES OF A DISCRETE PROBABILITY the random variable that gives the product of the two numbers
DISTRIBUTION drawn.
A discrete probability distribution has the following properties: a) Construct the probability mass function of 𝑋
1. The probability 𝑃(𝑥) for each possible value of 𝑥 is
0 ≤ 𝑃(𝑥) ≤ 1

2. The sum of all probabilities in the distribution is equal

to 1. That is, ∑ 𝑃(𝑥) = 1

EXAMPLE 2:

In the experiment in Example 1, what is the probability that at

least 1 red ball is drawn?

The probability that at least 1 red ball is drawn is equal to the b) Construct the histogram for the pmf
probability that either 1 red ball is drawn, or 2 red balls are
drawn. We consider the union of these two outcomes, so we
get the sum of their probabilities.

c) What is 𝑃(𝑋 = 6)?

EXAMPLE 3:
1
𝑥 𝑃(𝑋 = 6) =
Given the equation 𝑃(𝑥) = for 𝑥 = 1, 3, 4. Show that 3
8
𝑃(𝑥) describes a probability distribution. d) What is 𝑃(𝑋 ≤ 10)?
𝑥
For the first property, for 𝑥 = 1, 3, 4, the value of 8 is greater
1 3 4
than or equal to 0 but less than or equal to 1. Such as 8 , 8 , 8
. Thus, the first property is satisfied.
EXAMPLE TOPIC: MEAN AND VARIANCE OF A DISCRETE RANDOM
VARIABLE
The households of a local community were surveyed about
the number of occupants who are working. It was found out
MEAN OF A DISCRETE RANDOM VARIABLE
that 25 households have one occupant working, 18 have two
The mean of a probability distribution is given by
occupants working, 12 have three occupants working, and 5
have four occupants working. 𝜇 = ∑ 𝑥 ∙ 𝑃(𝑥)
where 𝑥 is a possible outcome and 𝑃(𝑥) is its probability
Let 𝑋 be the number of occupants working from a randomly
selected household.
VARIANCE AND STANDARD DEVIATION OF A
a) Create the probability distribution for the random DISCRETE RANDOM VARIABLE
variable 𝑋
Variance is a measure of how spread the data are, so instead
There are a total of 60 households, so the probabilities for
of multiplying each probability with a single data point, it is
the values of 𝑋 are shown in the table below.
multiplied by the sequence of the distance of each data point
from the mean.

The variance of a probability distribution is given by

𝜎 2 = ∑(𝑥 − 𝜇)2 ∙ 𝑃(𝑥)

EXAMPLE 1:
Suppose a ball was drawn 100 times. Find the mean and
variance of the given random variable that involves drawing
b) Draw the probability histogram a ball 100 times.

Find the mean and variance of the given random variable that
involves drawing a ball 100 times.
c) What is 𝑃(𝑋 = 3)? Mean:
𝑃(𝑋 = 3) = 0.20
𝜇 = ∑ 𝑥 ∙ 𝑃(𝑥)
d) What is 𝑃(𝑋 ≤ 4)?
𝜇 = 0(0.25) + 1(0.5) + 2(0.25)
𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) + 𝑃(𝑋 = 3) + 𝑃(𝑋 = 4)
0.42 + 0.30 + 0.20 + 0.08 𝜇=1
𝑃(𝑋 ≤ 4) = 1 Variance:

𝜎 2 = ∑(𝑥 − 𝜇)2 ∙ 𝑃(𝑥)

𝜎 2 = (0 − 1)2 (0.25) + (1 − 1)2 (0.5) + (2 − 1)2 (0.25)

𝜎 2 = 0.5
Note that the mean of a probability distribution does not take
into account the number of data points involved. Instead, it
considers the probability of each possible outcome. The mean
is also referred to as the expected value of 𝑿 denoted by 𝑬(𝑿).
EXAMPLE: We can now compute for the expected value.

A small study aims to see the correlation between having a tattoo 𝜇 = ∑ 𝑥 ∙ 𝑃(𝑥)
and cases of clinical depression. In one group of 12 people from the
same age bracket, 7 have 1 tattoo, 3 have 2 tattoos, and the rest 𝜇 = 480 ∙ (0.25) + [−20 ∙ (0.83)]
have 3 tattoos. If a person is randomly picked from this group and 𝜇 = 63.33
evaluated for depression, what is the expected number of tattoos
that the person will have? Since 𝑥 is a random variable representing Luis’ winnings, we can
say that the expected value 𝜇 represents his expected winnings.
SOLUTION: Our computation tells he is expected to win ₱63.33 for every
Let 𝑋 be the number of tattoos a student from the class has. The guesses he makes. If he makes 5 guesses, he is expected to win 5
probability distribution of 𝑋 is shown below. × 63.33 = ₱316.65 . Note that this amount is smaller than the prize
for making one correct guess. This is because there is much higher
5
probability that Luis will make an incorrect guess or 6 than a correct
1
one or 6.

What happens if Luis makes 10 guesses instead of 5? What

happens if makes 50 guesses? Or what if he makes 100 guesses?
As Luis makes more and more guesses, does he increase his
MEAN: chances of winnings? The Law of Large Numbers offers a possible
answer.
𝜇 = ∑ 𝑥 ∙ 𝑃(𝑥)
LAW OF LARGE NUMBERS
𝜇 = 1 ∙ (0.58) + 2 ∙ (0.25) + 3(0.17)
For a significantly large number of repeated trials in an
𝜇 = 1.59 experiment, the average of the results will be equal to the
Since the expected value of 𝑥 is approximately 1.59, then a expected value.
randomly chosen student is expected to have about 1.58 tattoos, or The Law of Large Numbers states that the more trials Luis gets, the
in whole number, 2 tattoos. closer he gets to his expected winnings, but not necessarily closer
to a higher amount of winnings.

EXAMPLE: As in the study of descriptive statistics, the standard deviation of the

random variable is computed by taking the square root of its
Miguel and Luis are playing a game. Miguel will roll a number cube variance. That is,
and Luis will guess the number that comes up. Luis pays ₱20 to
make a guess, and if he guesses correctly, Miguel pays him ₱500. 𝜎 = √∑(𝑥 − 𝜇)2 ∙ 𝑃(𝑥)
If Luis makes 5 guesses, how much money is he expected to win?

SOLUTION:

Let 𝑋 be the amount of money Luis wins. If he guesses correctly,

then he gets ₱500 less the amount he pays, which is ₱20. So if he
wins, 𝑥 = 480. If he does not guess correctly, he does not win
anything, and still needs to pay ₱20. Thus, if he does not guess
correctly, then 𝑥 = −20.
1
Since Luis can give just 1 number as his guess, there is a 6 chance
that he will win. Thus, the probability distribution for 𝑋 is shown
below.
TOPIC: NORMAL DISTRIBUTION CHARACTERISTICS OF NORMAL DISTRIBUTION

NORMAL DISTRIBUTION 1. The curve is symmetric with respect to the vertical line
passing through the mean
The normal distribution is a continuous probability distribution. It
allows us to make inferences about the whole population based on 2. It approaches the x-axis asymptotically on both sides
some characteristics of a sample.
3. The bell curve varies in shape depending on the mean
POSITIVELY SKEWED DISTRIBUTION and on the standard deviation. It can be narrow or wide.
It can be tall or short
A positively skewed distribution, also known as a right-skewed
distribution, is a type of asymmetric probability distribution in 4. The mean, median, and mode are all equal
which the tail on the right side (higher values) of the
STANDARD NORMAL DISTRIBUTION
distribution is longer or fatter than the tail on the left side (lower
values) The standard normal distribution is a normal distribution with a
mean of 60 and a standard deviation of 1. The corresponding
curve is shown below

NEGATIVELY SKEWED DISTRIBUTION

A negatively skewed distribution, also known as a left-skewed

distribution, is a type of asymmetric probability distribution in which CHARACTERISTICS OF STANDARD NORMAL DISTRIBUTION
the tail on the left side (lower values) of the distribution is longer or CURVE
fatter than the tail on the right side (higher values)
1. The area enclosed by the curve and the x-axis is equal to
1

2. Regions under the curve approximate probabilities that

random variables fall in particular ranges

3. The curve is symmetric. The area to the right of 0 is equal

to the area to the left of 0. That is, 50% of the area is to
the left of the mean and 50% of the area is to the right of
the mean.

SYMMETRICAL BELL CURVE 4. 4. About 68% of the values are within 1 standard
deviation of the mean. About 95% of the values are
A symmetrical bell curve refers to the shape of a normal distribution,
within 2 standard deviations of the mean. About 99.8% of
which is one of the most well-known probability distributions in
the values are within 3 standard deviations of the mean.
statistics. It is characterized by its balanced, symmetrical
appearance, resembling a bell 5. (Empirical Rule)

6. 5. Using the curve and the corresponding table entails

converting an observed value 𝑥 to its z-score. The z-
score measures how many standard deviations 𝜎 an
observed 𝑥 is from the mean 𝜇.
FORMULA FOR STANDARD SCORE AREAS UNDER THE STANDARD NORMAL CURVE
𝑥−𝜇 𝑥−𝑥̅ TABLE
𝑧= or 𝑧=
𝜎 𝜎
Study the following z-scores and their corresponding areas.
Positive values of z-score indicate the number of standard
deviations an observation is above the mean while a negative values
of z-score indicate the number of standard deviations an observation
is below the mean

EXAMPLE 1:

Consider 𝜇 = 30 and 𝜎 = 4 , study the table as follows:

EXAMPLE 2:

Given an observed score of 50, a population mean of 53, and a

standard deviation of 1.5, what is the conversion of 50 to its z-score?
𝑥−𝜇
𝑧=
𝜎
Note: The area indicates 𝑃(0 < 𝑧 < 𝑎)
50 − 53
𝑧=
1.5
𝑧 = −2
EXAMPLE 3: EXAMPLE 5:

EXAMPLE 4: EXAMPLE 6: