Dr. Romario Bhong P.
Ybaez
Research Director
St. Paul University Dumaguete
Descriptive statistics
Descriptive statistics summarize the distribution of
sample scores on a single variable
Measures of Central Tendency or
Averages
Measures of Dispersion
Measures of Location
Measures of Skewness
Measures of Kurtosis
Statistical properties of
the normal distribution
The Mean
The mean of a set of numerical values is the average of the
set of values.
Note: In the explanation of the mean, the numerical values
can be population values or sample values. Hence, we can
compute the mean for either population values or sample values.
Population vs Sample Mean
The term-population mean: If the values are from an entire
population, then the mean of the values is called a population
mean. It is usually denoted by (read as "mu").
Explanation of the term-sample mean: If the values are from
a sample, then the mean of the
values is called a sample mean. It is denoted by X (read as
"x-bar").
Question: Why do we use the mean as a
measure of the center of a set of values?
When the deviations on the left and on the right of the sample
means are added, disregarding the sign of the values, we see
that when the "balancing point is the sample mean, then these
sums are equal in absolute value.
Thus, the mean is that central point where the sum of the
negative deviations (absolute value) from the mean and the sum
of the positive deviations from the mean are equal. This is why
the mean is considered a measure of central tendency.
Measures of
Central Tendency
1. Mean (X) sum of all data values divided by the
number of values
n
i1
Xi s are the data values
i = 1, , n (n is the total number values)
Example:
The scores of 10 students in a Statistics
exam are 80, 92, 85, 87, 94, 83, 88, 91, 92,
and 80. Find the mean scores of the 10
students.
80908587948388919280 872
X
87.2
10
10
When to use the mean?
1. Interval and ratio types of data
2. No extreme values
3. Greatest reliability
Median
The median of a numerical data set is the numerical value in the
middle when the data set is arranged in order.
Rules:
1. When the values in the data set is odd, the median will be the
middle value of the ordered array.
2. When the values in the data set is even, the median will be the
average of the two middle value of the ordered array.
2. Median
Examples.
a) Consider the scores of 10 students:
80, 92, 85, 87, 94, 83, 88, 91, 92, and
80.
Array: 80, 80, 83, 85, 87, 88, 91, 92,
92, 94
Md = (87 + 88)/2 = 87.5
b) The final grades of 5 high school
graduating students are 90, 85, 86,
80, and 89. Find the median
grade.
Array: 80, 85, 86, 89, and
90.
Md = 86
Question: Why does the middle number in an
ordered data set measure central
tendency?
When the values from above and below the median are counted,
we see that if the "balancing point" is the sample median, then
the number of values above the median balances (equals) the
number of values below the median.
When to use the median?
at least ordinal (ranked) data
2. presence of extreme values
3. open-ended distribution
1.
.Mode
The mode of a numerical data set is the most frequently
occurring value in the data set.
Tips
1. If all the elements in the data set have the same frequency of
occurrence, then the data set is said to have no mode.
2. If the data set has one value that occurs more frequently than
the rest of the values, then the data set is said to be unimodal.
3. If two elements of the data set are tied for the highest
frequency of occurrence, the data set is said to be bimodal
3. Mode (Mo)
Kinds of Mode:
a. Unimodal
b. Bimodal
c. Trimodal
d. Polymodal
Examples:
1.) For the scores 80, 83, 85, 87, 88, 91, 92
and 94. No mode.
2.) 80, 80, 83, 85, 87, 88, 91, 92, and 94.
Mo = 80, unimodal
3.) For the scores 80, 80, 83, 85, 87, 88, 91,
92, 92 and 94.
Mo = 80 and 92, bimodal
When to use the mode?
1. nominal or categorical data
2. rough or quick estimate of a central
value
3. most popular or most typical case
Other Measures of
Central Tendency
1.
Midrange
(Max + Min) / 2
Example: Consider the daily allowances of 6 high
school students: P60, P50, P20, P65, P10, and
P15. Find the midrange of their allowances.
Array: P10, P15, P20, P50, P60, P65
Midrange = (65 + 10) / 2 = 37.5
2. Weighted Mean ( Xw)
k
W iX
i1
k
i1
where Wi are weights assigned to Xi and k is the
number of X values being studied
Example: Suppose a high school teacher has to compute the grade
of a student in a statistics subject with the following
requirements:
Periodic Exam
30%
Mastery Test
30%
Quizzes
20%
Assignment
15%
Attendance/Project
5%
If a student gets the following score: periodic exam 89%,
mastery test 88%, quizzes 85%, assignment 83%, and
attendance/project 90%. What is the weighted average score of
the student?
Xw
=
(89)30+88(30)+85(20)+83(15)+90(5)
100
= 87.05
[OR 89(0.30) + 88(.30) + 85(.20) +83(15) +90(0.05)]
3. Geometric mean
X i ... X k
where Xis are positive numbers
Example: A public health officer wants to
determine the concentration of Enterococci
bacteria in a certain swimming pool. The
officer gathers the following data on different
dates:
10 Ent./100 milliliter
15 Ent. /100 milliliter
1500 Ent. /100 milliliter
90 Ent./100 milliliter
100 Ent. /100 milliliter
Find the geometric mean concentration of
bacteria in that swimming pool.
Solution:
G
10 15 1500
90 100
= 78.80/100 milliliter
4. Harmonic Mean
H
k
k
i 1 X i
Example
A car travels at a rate of 50 kph from
Dgte. to Jimalalud and returns at a rate of
30 kph. What is the average speed for
the trip?
Solution:
2
1 1
50 30
37.5kph
Different Shapes of
Distributions
Source: http://faculty.vassar.edu/lowry/f0204.gif
