Unit 4:

Interpretation of
Assessment Results
What is expected of you?
•Use a variety of statistical tools to process and
manage assessment data;

•Interpret data using appropriate statistical tools

 Levels of Measurement

Nominal Level This is characterized by data that consist of names, labels, or categories only. The
data cannot be arranged in an ordering scheme. There is no criterion as to which
values can be identified as greater than or less than other values.

Example 1. In classifying the students in a university as male or female, no ranking can be

placed on the data.

2. Another example is classifying students according to their identification.

Although, numbers are assigned as identification of students, there is no
meaningful order.

This involves data that may be arranged in some order, but differences between
Ordinal Level
data values either cannot be determined or are meaningless.

Example Grading system involving the letters A, B, C, D, F

 This is the same as the ordinal level, with an additional property that we can
Interval Level determine meaningful amounts of differences between the data. Data at this
level may lack an inherent zero starting point.
Temperature is an interval measurement. There is a meaningful difference in one degree
Example between each unit such as 80 and 81 degrees. But a zero degree temperature does not mean
that there is no heat.

This is an interval modified to include the inherent zero starting point. The
Ratio Level
difference and ratios of data are meaningful. This is also the highest level of
measurement. A

Example
height, weight, or area, test scores

there is a meaning between values, and a true zero exists

 Measures of •Mean
• [Sum of all observations]/[Number of observations]
Central Tendency • It is the most commonly used measure of central tendency

for ungrouped data •Median

• the middle observation when all observations are arranged in
increasing/decreasing order Attitude
A well-chosen average consists of
•Mode
a single number about which a • the observation with the highest frequency or the most
given data are centered. frequently occurring observation
• A data can have more than one or none at all

Aspirations
Measures of Central Tendency for Ungrouped Data
The following are scores of 10 students in a Math
test:

Mean
37 37 24 28 43 44 36 41 33 27

Determine the average score.

Sol.
Mean =
 Example 1: The following scores were
recorded below.
Median 13 12 11 11 13 15 18

Sol. Arrange the data in order.

11 11 12 13 13 15 18

Select the middle value

 Example 2: The scores of eight students are
recorded as follows:
41 39 42 40 42 41 47 45

Median
Sol. Arrange the data in order.

39 40 41 41 42 42 45 47

Median =
 Example 2: The scores of eight students are recorded
as follows:

41 39 42 40 42 41
Mode
Most frequently
47 45
occurring score/s
Mode: 41 and 42 (bimodal)
 The scores clustered
around the mean
Measures of which means a
homogeneous group
Variability
Variability or dispersion is a
very important characteristic
of data. It can help you
create a mental picture of the The scores are
spread of the data. widespread which
means the group is
more heterogeneous
compared to the first
one
1. Range
Given the following scores of students in 100 item test:
the range, R, of a set of n 25, 35, 40, 60, 15, 55, 37, 42, 58, 70, 25, 30, 56, 42
measurements is defined
Calculate the range.
as the difference between
Range = Highest Observation – Lowest Observation
the largest and smallest
= 70 – 15
measurements.
= 55
 The variance of a population of N measurements is the
average of the squares of the deviations of the
measurements about their mean.

2. Variance
The variance of a sample of n measurements is the sum of
the squared deviations of the measurements about their
mean divided by (n-1).
 Example
5, 7, 1, 2, 4
 The standard deviation of a set of
measurements is equal to the positive square
root of the variance.

3. Standard deviation From the previously calculated variance, s 2 = 5.70

The more variable the data set is, the larger the value of s.
Remember:
Task:
Given the following data:
12, 14, 18, 27, 30. 25, 22, 19, 20, 18, 21, 25, 23, 32, 30, 27, 19, 19
Compute for the following:
a. Mean
b. Median
c. Mode
d. range
e. Variance
f. Standard deviation
 Arrange the data in increasing order:
4, 8, 9, 11, 11, 13, 16, 18, 20, 25
4. Interquartile 1st Quartile (Q1) = 0.25(n+1)th position
= 0.25(10+1)
Range = 0.25(11)
= 2.75th position
Since 2.75 is not integer, interpolate
The interquartile range (IQR) 2nd position + .75 (3rd position – 2nd position)
for a set of measurements is 8 + 0.75 (9 – 1) = 8+0.75 = 8.75
the difference between the
3rd Quartile (Q1) = 0.75(n+1)th position
upper and lower quartiles;
= 0.75(10+1)
that is, IQR = Q3 - Q1. = 8.25th position
Since 8.25 is not integer, interpolate
8th position + .25 (9th position – 8th position)
Example: Here are the scores 18 + 0.25 (20 – 18) = 18+0.50 = 18.5
of 10 students in 30-item test:
16, 25, 4, 18, 11, 13, 20, 8, IQR = 18.5 – 8.75
11, 9 = 9.75
 These are markers for specific portions of the
distribution of data points.

These include: Quartiles, Deciles, and

Measures of Location Percentiles. Whatever the size of the data points,
these measures of location allocate the entire set of
data into specific portions to give the data user a
clearer understanding of how the data behave.
 Quartiles are markers for every ¼ of the data points –
Q1, Q2, Q3 and Q4, the first, second, third and fourth
Measures quartile, respectively.

of Location Deciles are markers for every 1/10 of the data points –
D1, D2, D3, D4, …, D10, the first, second, third, fourth,
…., and tenth decile, respectively.

Percentiles are markers for every 1/100 of the data

points – P1, P2, P3, P4, …, P100, the first, second, third,
fourth, …., 100th percentile, respectively.
 Rules:
When the measurements are arranged in
Quartiles order of magnitude (increasing or
This is a measure of relative decreasing)
standing.
Q1 = 0.25 (n + 1)
Q2 = 0.50 (n + 1)
Q3 = 0.75 (n + 1)
 Find Q1, Q2 and Q3 of the following set of data.
19, 12, 16, 0, 14 9, 6, 1, 12, 13, 10, 19, 7, 5, 8
Sol. Arrange the data from lowest to highest.
0, 1, 5, 6, 7, 8, 9, 10, 12, 12, 13, 14, 16, 19, 19
Example: Using the formula,
Q1 = 0.25(15 + 1) = 0.25(16) = 4 , 4 th data is 6
Q2 = 0.5(15 + 1) = 0.5(16) = 8, 8 th data is 10
Q3 = 0.75(15 + 1) = 0.75(16) = 12, 12 th data is 14
 Rule:

Percentile The percentile corresponding to a given value x is

computed by using the formula
Percentiles are position
measures used in educational Percentile = (number of values below x) + 0.5 x 100%
and health-related fields to Total number of values
indicate the position of an
individual in a group.
 Find the percentile rank of a test score of 49
in the data set.

Example1: 12, 28, 35, 42, 47, 49, 50

Arrange from lowest to highest
Percentile = 5 + 0.5 x 100%
7
= 78.57%
 The following are scores in a Statistics test:
2, 3, 5, 6, 8, 10, 12, 15, 18, 20
Find the value corresponding to the 25th percentile.
Arrange the data from lowest to highest.
Compute c = np/100, where n is the number of values
and p is the percentile
Example 2: C = 10(25)/100
= 250/100
= 2.5
Since c is not a whole number, round it up to the next
whole number ; in this case c = 3, so the 25th percentile
is the third value which is 5.
 Find the value corresponding to the 60 th percentile for the
given data set.
80, 68, 53, 58, 76, 73, 85, 88, 91, 79
Sol. Arrange the data from lowest to highest.
53, 58, 68, 73, 76, 79, 80, 85, 88, 91
Using the formula, c = np/100

Example 3:
(10)(60)/100 = 6
Since the value of c is a whole number, use the value halfway
between 6 and (6 + 1) values when counting from the lowest
value
6th value = 79, 7th value = 80
The value halfway between 79 and 80 is 79.5. Hence, 79.5
corresponds to the 60th percentile.
 Deciles divide the distribution into tenths or 10
equal parts. This is denoted by D1, D2,
D3, ...D9. To obtain the deciles, divide the data
set into tenths and determine the number dividing
the tenths.
Deciles D1 = (n+1)/10 th item
D2 = 2(n+1)/10 th item
D9 = 9(n+1)/10 th item
 20, 28, 29, 30, 36, 37, 39, n = 7
Calculate D2, D3 and D7
D2 = 2(7+1)/10
= 2(8)/10
Example = 1.6 item from below
th

The value of the 1 item is 20 and the second

st

item is 28. Thus the second decile is a value

0.6th of the way between 20 and 28. The 2 nd
decile will be 20 + 0.6(8) = 24.8
How to interpret Measures of Central Tendency
The value that represents a set of data will be the basis in determining
whether the group is performing better or poorer than the other groups.

How to interpret the Standard Deviation

•The result will help you determine if the group is homogeneous or not
•The result will also help you determine the number of students that fall
below and above the average performance
Points above mean + 1sd = range of above average
Mean + 1sd give the limits of an average ability
Mean – 1sd
Points below mean – 1sd = range of below average
Grouped Data
Example: These data represent the scores of 60 students in a 50 item test.
48 32 28 27 26 23 19 45 41 36
25 31 30 42 39 32 16 15 20 23
20 27 28 32 30 28 21 25 28 24
29 30 42 49 46 42 41 40 38 21
21 22 29 28 32 39 30 22 29 18
20 18 19 32 36 40 42 43 49 42
Construct a grouped frequency distribution for numerical data following the steps below.
Step 1: Determine the classes.
a. Find the highest and lowest values and get the range: HS – LS = 49 – 15; R = 34
b. Select the number of classes desired ( between 5 and 20). 7 is arbitrarily chosen.
c. Find the class width by dividing the range by the number of classes: 34 / 7 = 4.86,
round up; 5
d. Select a starting point (lowest value or any convenient number less than the lowest
value; add the width to get the lower limits); 15, 20, 25, …
e. Subtract 1 from the lower limit of the second class to get the upper limit of the first
class. Then add the width to each upper limit to get all the upper limits.
20 -1 = 19, 24, 29, 34, 39, …. The first class is 15 - 19, second class is 20 –
24, ..
f. Find the class boundaries by subtracting 0.5 from each lower class limit and adding
0.5 to each upper class limit. 14.5 – 19.5; 19.5 – 24.5, etch.
Step 2: Tally the data.
Step 3: Find the numerical frequencies from the tallies.
 48 32 28 27 26 23 19 45 41 36
25 31 30 42 39 32 16 15 20 23
20 27 28 32 30 28 21 25 28 24
29 30 42 49 46 42 41 40 38 21
21 22 29 28 32 39 30 22 29 18
20 18 19 32 36 40 42 43 49 42

Class Limits Class boundaries Tally Frequency > Cumulative < cumulative
frequence frequency
45 – 49 44.5 – 49.5
40 – 44 39.5 – 44.5
35 – 39 34.5 – 39.5
30 – 34 29.5 – 34.5
25 – 29 24.5 – 29.5
20 – 24 19.5 – 24.5
15 – 19 14.5 – 19.5
Measures of Central Tendency for Grouped Data
References:

1. Mendenhall, W., Beaver, R. & Beaver, B. (2009 ). Introduction to Statistics and

Probability. 13th Edition. Cengage Learning
2. Alferez, M. And Duro, M. (2006). Statistics and Probability . MSA Academic
Advancement Institute