1

Chapter IV
Analysis and Interpretation of Assessment Results

Overview
This chapter focuses on the Analysis and interpretation of assessment results. It
presents discussion on Descriptive Statistics and Correlation.

Time Allotment: 15 hours (Week 11-15)

Discussion

A. The Nature of Statistics

Statistics is defined in two ways:

1. Singular: it is a branch of science that deals with the processes of

gathering, describing, organizing, analyzing and interpreting numerical or
statistical data as well as with drawing valid conclusions and making
reasonable decisions on the basis of such analysis.
2. Plural: it means data or information

Fields of Statistics

1. Descriptive Statistics- concerned with collecting and describing a set of

data so as to yield meaningful information.
2. Inferential Statistics – concerned with the analysis of a subset of data
leading to predictions or inferences about the entire set of data.

Variables- a characteristic that can take on different values. It is the object of

description or inference. It is usually denoted by capital letters.

Variables can be grouped in different ways: Qualitative and Quantitative

A qualitative variable is one, which describes a characteristic.

Examples: small, wide, attractive

A quantitative variable is one, which can be given a numerical value.

Classification of Variables According to Continuity of Values

1. Continuous – values or levels that can take form of decimals.

Examples: Weight, length, height

 2

2. Discrete or discontinuous- values or levels that can’t take the form of

decimals.

Examples: No. of students, no. of houses, size of the family

Classification of Variables According to Scale of

Measurement

1. Nominal – observations belong to respective classes or categories

Ex: ethnicity, religion, sex
2. Ordinal – the classes or categories where the observations belong can be
ranked.
Ex: shirt size, socio-economic status
3. Interval – allows one to make statements of equality of intervals.
Ex. Height, weight, temperature, test scores
4. Ratio – a true zero of the measured distance exists
Ex. temperature, velocity

B. Descriptive Statistics
-the first step in data analysis is to describe, or summarize the data using
descriptive statistics.

I. Measures of Central Tendency

The measure of central tendency is the point about which scores tend to
cluster, a sort of average in the series. It is the center of concentration of scores in
any set of data. It is a single number which represents the general level of
performance of a group.

The three measures of central tendency in common use are: Mean,

Median and Mode.

Mean – known also as arithmetic mean is defined as the sum of the values in the
data group divided by the number of values.

Median – is the center, or middle score within a distribution.

Mode – is the most frequent score within a distribution.

When to use the mean

1. when the scores are distributed symmetrically around a central point

2. when the measure of central tendency having the greatest stability is
wanted
3. when other statistics like standard deviation, coefficient of correlation, etc.
are to be computed later, since the statistics are based upon the mean.
 3

Calculating the Mean from Ungroup data

Formula: χ = ∑χ where: χ = score or other measure

N N = no. of measures
∑ = The sum of
Example:
Last summer, the six salesmen in an Air-conditioning Firm sold the following
number of air-condition units: 16, 9, 11, 6, 10 and 8. Find the mean number of units sold.

Formula: χ = ∑χ
N
= 60
6
=10 units

Calculating the Mean from grouped data

Formula: χ = ∑fM where: f = class frequency

N N = sum of frequencies
M = class midpoint
∑ = The sum of

Example: Compute the mean of the scores of 50 students on a Filipino test.

Class Interval Midpoint Class frequency fM

(score) (M) (f)
57-59 58 1 58
54-56 55 1 55
51-53 52 0 0
48-50 49 3 147
45-47 46 3 138
42-44 43 5 215
39-41 40 3 120
36-38 37 4 148
33-35 34 7 238
30-32 31 6 186
27-29 28 4 112
24-26 25 5 125
21-23 22 5 110
18-20 19 3 57
N=50 ∑fM= 1709
Formula: χ = ∑fM
N
= 1,709
50
= 34.18
 4

Computation of Weighted Mean (WM) in case the researcher is using 5,4,3,2,1 scales
(weights).

Ex: Data on Pupil’s Attitudes toward Science

Choices Weighted
Mean
Descriptive
Rating
Statements Strongly
Agree (5)
Agree
(4)
Undecided
(3)
Disagree
(2)
Strongly
Disagree
(WM) (DR)
(1)
I prefer science 45 30 20 25 15 3.48 Undecided

than other subjects.

I consider science 48 32 25 12 18 3.59 Agree
learning an
interesting and
exciting experience.
I feel that science 30 49 21 10 25 3.36 Undecided

concepts and skills

answer a lot of
problems I
encounter
Legend: 1.00-1.49 Strongly Disagree
1.50-2.49 Disagree
2.50-3.49 Undecided
3.50-4.49 Agree
4.50-5.00 Strongly Agree

Formula for weighted mean:

Formula: χ = ∑fM
N
χ = ∑ (45)(5)+(30)(4)+(20)(3)+(25)(2)+(15)(1)
135

= 3.48 – this means that the pupils are undecided whether they
prefer science than other subjects.

Note: follow same process to compute the mean of the second and third
statements.

Median (Mdn) – the middle score in a distribution or the middle most score of
the distribution. Unlike the mean, the median is not sensitive to extreme scores; hence,
it is very appropriate when there are values which are relatively large or relatively small
compared to most of the scores.

When to use the median:

1. when the exact midpoint of the distribution is wanted, the 50% point
2. when there are extreme scores which would markedly affect the mean.
Extreme scores do not disturb the median
 5

3. when it is described that certain scores should influence the central

tendency, but all that is known about them is that they are above or below
the median

Median of Ungrouped Data

To calculate the median, just arrange the scores from smallest to largest (or from
largest to smallest) and then count up to the middle score

Ex: Find the median of the given set of scores.

10, 14, 16, 16, 19, 23, 27 (already arranged in order of size)

The median would be the fourth score as there are seven scores. The median of
the scores is 16.

Ex: Find the median for the following set of scores.

27, 19, 23, 10, 14, 30

Arrange the scores: 10, 14, 19, 23, 27, 30

The median would be half way between the third and fourth scores as there are
six scores, (19+23)/2 = 21, so the median is 21.

Median of Grouped Data

Mdn = L + N/2 - F (i)
f

Where: Mdn = Median

L = exact lower limit of interval containing the median class
f= frequency of interval containing the Median class
F= cumulative frequency below L
N = no. of cases
i= class interval width

Ex: Determine the median of the data below:

Age bracket Frequency Cumulative
frequency
21-25 4 4
26-30 14 18
31-35 6 24
36-40 7 31
41-45 22 53
46-50 8 61
51-55 3 64
Total: 64

Determine first the median class by computing N/2.

64/2 =32. 32 falls on cumulative frequency 53. Therefore, the median class is the class
interval 41-45.
 6

Mdn = L + N/2 - F (i)

F
= 40.5 + 64/2 -31 (5)
22
Mdn = 40.73

Mode (Mo) – most frequently occurring value in a distribution

Mode of Ungrouped Data

The mode for the ungrouped data is the specific score, which has the higher
frequency. We can identify this value by inspection.

Ex: The ages of a group of students are 17,17,17, 18,18,18,18,19,19,20,20,21,21. By

inspection, 18 is the most frequently occurring age. Therefore, 18 is the mode.

Sometimes two figures tie for “most popular”, as with the ages
17,17,17,18,18,18,19,19,20,20,21. The modes are 17 and 18. This is referred as
bimodal.

Mode of Grouped Data

Ex: Find the mode of the data in the table below:

Age bracket Frequency
21-25 4
26-30 4
31-35 6
36-40 7
41-45 2
46-50 10
51-55 7
56-60 4

The Modal class is 46-50 because it is the interval class with highest
frequency. The lower limit of the modal class is 46 and the upper limit is 50.
The formula in finding the mode of the grouped data:

Mode= lb(mo)+ D1 i
D1 + D2
lb(mo)- lower boundary of the modal class 46-0.5 = 45.5
D1- the highest frequency minus the frequency of the next lower
Class 10-2 = 8
D2- the highest frequency minus the frequency of the next upper
Class 10-7 = 3
i- the class width is the difference between two consecutive
lower limits 46-41 = 5

Mode= lb(mo)+ D1 i
D1 + D2
= 45.5 + 8 5
 7

8+3

Mode = 49.14

II. Measures of Variation

In order to describe more fully a distribution, it is necessary to present the

mean or any of the measures of central tendency with some measure that would
indicate how the scores are spread out along the scale of the distribution. These
measures of spread are more popularly known as measures of variations or
measures of dispersion.

A measure of dispersion is a method of measuring the degree by which

numerical data or values tend to spread from or cluster about a central point of
average.

The measures of variability we will consider are the range, the variance,
and the standard deviation.

A. RANGE

The range (R) is defined as the difference between the highest value (HV)
and the lowest value (LV) in the data.

R = HV-LV

Ex: James took 7 math tests in one marking period. What is the range of his
test scores?
89, 77, 95, 65, 90, 94, 70
R= 95-65= 30

The range of these test scores is 30 points.

Consider the following two sets of scores:
Set A: 4, 5, 6, 7, 8
Set B: 2, 4, 6, 8, 10
We can see that the means for these two sets of scores are the same which
is 6. Although these two sets of scores have the same Mean, they differ in how
spread out the scores are.
The scores in Set A vary over a smaller set of values (4 through 8) than
does Set B which varies over score values from 2 through 10.
Range of Set A is 4 while the Range of Set B is 8.

B. VARIANCE
Variance also indicates a relationship between the mean of a distribution and the
data points.

Sample Variance:
s2= n∑ X2 – (∑ X)2
n(n-1)
 8

Ex: Calculate the sample variance of the following data.

8, 9, 10, 12, 17, 18, 18, 19, 20, 21
X X2
8 64
9 81
10 100
12 144
17 289
18 324
18 324
19 361
20 400
21 441
∑ X = 152 ∑ X2= 2,528
n=10

s2= n∑ X2 – (∑ X)2
n(n-1)
= 10 (2,528) – (152)2
10(9)
= 24.18

Population Variance:

σ2 = ∑ (X – µ)2
N
Where: σ2= (sigma squared), Population variance
(X – µ)2 = square of the differences
∑ (X – µ)2 = sum of squared differences
N = number of cases

Ex.: Calculate the variance for 7 scores.

X X–µ (X – µ)2
5 1 1
3 -1 1
4 0 0
4 0 0
3 -1 1
4 0 0
5 1 1
Mean (µ)= ∑ (X – µ)2 = 4
28/7 = 4

σ2 = ∑ (X – µ)2
N
=4
7
= 0.57
 9

C. STANDARD DEVIATION
If the scores are grouped closely around the mean of a distribution, the
standard deviation of that distribution will be small; but if the scores are spread
out from the mean, the standard deviation will take on a large value. Conversely,
if the standard deviation computed from a set of data is small, the values are
concentrated near the mean; and if the standard deviation is large, the values are
dispersed widely about the mean.
Standard Deviation (SD) is the square root of the variance. This
calculation is useful because it allows for the same flexibility as variance
regarding further calculations and yet also expresses variation in the same units
as the original measurements.
The standard deviation is equal to the principal square root of the
variance.

Standard Deviation Formulas:

For a sample:

s= n∑ X2 – (∑ X)2
n(n-1)
Ex: Calculate the sample standard deviation of the following data.
8, 9, 10, 12, 17, 18, 18, 19, 20, 21

X X2
8 64
9 81
10 100
12 144
17 289
18 324
18 324
19 361
20 400
21 441
∑ X = 152 ∑ X2= 2,528
n=10

s= n∑ X2 – (∑ X)2
n(n-1)

= 10 (2,528) – (152)2
10(9)

= 24.18 = 4.92
 10

For a population:

σ = ∑ (X – µ)2
N
Ex.: Calculate the Standard deviation for 7 scores.
X X–µ (X – µ)2
5 1 1
3 -1 1
4 0 0
4 0 0
3 -1 1
4 0 0
5 1 1
Mean (µ)= ∑ (X – µ)2 = 4
28/7 = 4

σ= ∑ (X – µ)2
N

= 4
7

= 0.57 = 0.755

Sample questions about variations:

1. Which set of scores has the least variability?

a. Set A: 0, 5, 10, 15, 20
b. Set B: 25, 30, 35, 40, 45
c. Set C: 0, 2, 8, 12, 15
d. Set D: 501, 502, 503, 504, 505

Least variable means the scores are clustered.

2. Standard deviation is to variability as mode to _________.

a. correlation
b. discrimination
c. central tendency
d. level of difficulty

3. Two sections have the same mean but the standard deviation of
Section 2 is higher than Section 1. Which of the two sections is more
homogenous?
a. Section 1 c. Both A and B
b. Section 2 d. None of these

Lower standard deviation means the scores are clustered. If the

scores are clustered, then the scores are closed to the mean. This
means the group is homogeneous.
 11

C. CORRELATION
Correlation is a measure of relationship between two variables. Coefficient
of correlation determines validity, reliability and objectivity of an examination
prepared. It also indicates the amount of agreement or disagreement between
group of scores, measurements, or individuals. Correlation ranges in value from
+1.00 through 0.00 up to -1.00.

Correlation tests are used to determine how strongly the scores of two
variables are associated or correlated, for instance, whether a correlation exists
between Accounting students’ pre-board examination scores and their scores in
the CPA board examination.

Correlation denotes positive or negative association between variables in a

study.

Examples:

1. An example of a strong positive correlation would be the correlation

between age and job experience. Typically, the longer people are alive, the
more job experience they might have.
2. An example of a strong negative relationship might occur between the
strength of people’s party affiliations and their willingness to vote for a
candidate from different parties. In many elections, Party XXX are
unlikely to vote for Party ZZZ, and vice versa.

Interpretation of ranges:

0.00 No correlation
+0.01-+0.20 Negligible correlation
+0.21-+0.40 Low correlation
+0.41-+0.70 Moderate correlation
+0.71-+0.90 High correlation
+0.91-+0.99 Very high correlation
+1.00 Perfect correlation

PEARSON PRODUCT-MOMENT CORRELATION COEFFICIENT

The most widely used type of correlation coefficient is Pearson r also

called linear or product-moment correlation.

The Pearson r is used to find the correlation between interval data.

Formula:

r= N∑XY - ∑X∑Y

[N∑X2 – (∑X)2][N∑Y2-(∑Y)2]

where: N = number of cases

∑XY= sum of the products of X and Y
 12

∑X= sum of X
∑Y = sum of Y
∑X2 = sum of the squares of X
∑Y2 = sum of the squares of Y

Example: Solve for the coefficient of correlation of the scores of 12 students in

Science Exam which was administered twice. (X- scores in the first
administration of the test; Y- scores in the second administration of
the test)

Student X Y XY X2 Y2
1 21 27 567 441 729
2 22 28 616 484 784
3 28 27 756 784 729
4 27 10 270 729 100
5 48 30 1440 2304 900
6 22 21 462 484 441
7 27 27 729 729 729
8 6 21 126 36 441
9 11 21 231 121 441
10 12 28 336 144 784
11 16 30 480 256 900
12 28 21 588 784 441
Total 268 291 6601 7296 7419

r= 12(6601)-(268)(291)

[12(7296)-(268)2][12(7419)-(291)2

r = 0.15. This means that there is negligible correlation between the

scores of 12 students in the first and second administration of the test.

SPEARMAN RHO COEFFICIENT OF CORRELATION

- It is used for ordinal data.
- It is a measure of the linear relationship between two variables. It
differs from Pearson’s correlation only in that the computations are
done after the numbers are converted to ranks.
Formula:

rho = 1 - 6 ∑D2
N(N2 -1)
where: 1 is constant ∑D2 = sum of D2
6 is constant N = sum of pairs of scores or measures
 13

Example: Solve for the coefficient of correlation of the scores of 12 students in

English (X) and Science (Y) using Spearman rho.

Student X Y Rx Ry D D2
1 21 27 8 6 2 4
2 22 28 6.5 3.5 3 9
3 28 27 2.5 6 -3.5 12.25
4 27 10 4.5 12 -7.5 56.25
5 48 30 1 1.5 -0.5 0.25
6 22 21 6.5 9.5 -3 9
7 27 27 4.5 6 -1.5 2.25
8 6 21 12 9.5 2.5 6.25
9 11 21 11 9.5 1.5 2.25
10 12 28 10 3.5 6.5 42.25
11 16 30 9 1.5 7.5 56.25
12 28 21 2.5 9.5 -7 49
∑D2= 249

rho= 1 - 6(249)
12(122 -1)
rho = 0.13. This means that there is negligible correlation between the
scores of 12 students in English and Science.

D. Distributions of Data

a. Normal Distribution or bell-shaped curve

b. Skewed distributions
 14

Normal Distribution:
Mean = Median = Mode
Negatively skewed distribution:
Mode > Median > Mean
Positively skewed distribution
Mean > Median > Mode

Stanine scores – standard scores that tell the location of a raw score in a specific
segment in a normal distribution which is divided into 9 segments, numbered from a
low of 1 through 1 high of 9.

Stanines 1, 2 and 3 reflect below average performance.

Stanines 4, 5 and 6 reflect average performance.
Stanines 7, 8 and 9 reflect above average performance.

How is stanine calculated?

Stanine is calculated by first giving each score a ranking from lowest score to highest
score. The scores are organized in the following groups:

Score Bottom 7% 12% 17% 20% 17% 12% 7% Top

Ranking 4% 4%
Stanine 1 2 3 4 5 6 7 8 9
score

What is a stanine used for?

Stanine is a method of scaling test scores on a nine-point scale. The nine-point
scale ranges from 1 to 9, and it can be used to compare test scores to one another
in a group of test scores.

Example: There are 100 scores that have been ranked in ascending order as:
5 5 6 8 10 11 12 14 15 15
16 17 17 19 20 20 22 24 24 25
25 25 27 28 28 28 29 29 30 30
30 31 31 32 32 33 33 33 34 34
35 35 35 35 36 36 37 37 37 37
37 38 38 38 38 38 39 39 39 39
40 40 41 41 41 42 42 42 42 42
43 43 43 43 44 44 44 45 45 45
45 46 46 46 46 46 46 46 46 47
47 47 47 47 48 48 49 49 49 50

5-8 has a stanine score of 1. These students have a below average performance.
10-16 has a stanine score of 2. These students have a below average performance.
17-27 has a stanine score of 3. These students have a below average performance.
28-34 has a stanine score of 4. These students have an average performance.
35-39 has a stanine score of 5. These students have an average performance.
40-44 has a stanine score of 6. These students have an average performance.
45-46 has a stanine score of 7. These students have an above average performance.
47-48 has a stanine score of 8. These students have an above average performance.
49-50 has a stanine score of 9. These students have an above average performance.

Percentile Rank – reflect the percentage of students in the norm group surpassed at each
raw score in the distribution.
 15

Sample questions:

1. In a positively skewed distribution, the following statements are true

except
a. Median is higher than the Mode
b. Mean is higher than the Median
c. Mean is lower than the Mode
d. Mean is not lower than the Mode
2. What is the performance of a student in the National Achievement Test
(NAT) if he obtained/got a stanine score of 5?
a. Between average and above average
b. Between average and below average
c. Below average
d. Average
3. Based on the figure, which is true about the distribution?
a. Mean = 55, Median = 48, Mode = 34
b. Mode = 40, Median = 40, Mean = 40
c. Mean = 46, Mode = 44, Median = 37
d. Median= 50, Median = 45, Mode = 40

4. In a negatively skewed distribution, which of the following statements is

true?
a. Mode is lower than the mean.
b. Mean is lower than the mode.
c. Median is higher than mode.
d. Mode is lower than the median.
5. Miss Cortez administered a test to her class and the result is positively
skewed. What kind of test do you think Miss Cortez gave to her pupils?
a. Posttest b. Pretest c. Mastery Test d. Criterion-referenced Test

6. The result of the test given by teacher A showed a negatively skewed

distribution. What kind of test did teacher A give?
a. The test is difficult.
b. It is not too easy nor too difficult.
c. It is moderately difficult.
d. It is easy.

7. When the distribution is skewed to the right, what kind of test was
administered?
a. Difficult b. Easy c. Moderately difficult d. Partly easy-partly
difficult

8. In a negatively skewed distribution, what kind of students does Teacher B

have?
a. Very good b. Very poor c. Average d. Heterogeneous
 16

9. In a positively skewed distribution, the students are

a. Very good b. Very poor c. Average d. Normally distributed

10. Bernard obtained a 97 percentile rank in an aptitude test. This means

a. she answered 97% of the items correctly.
b. She belongs to the 97% of the group who took the test.
c. 79% of the examinees did better than her on the test.
d. she surpassed 97% of those who took the test.

11. Precy performed better than 65% of the total number of examinees in the
District Achievement Test. What is her percentile rank?
a. P35 b. P65 c. P66 d. P75

12. Which is implied by a positively skewed scores distribution?

a. The mean, the median, and the mode are equal.
b. Most of the scores are high.
c. Most of the scores are low.
d. The mode is high.

KUDER-RICHARDSON FORMULA 20

-often abbreviated KR-20, is used to measure the internal consistency reliability

of a test in which each question only has two answers: right or wrong.

FORMULA:

KR-20 = (k/(k-1))*(1-∑pjqj/var)

Where: k - total no. of questions

pj - Proportion of individuals who answered question j correctly

qj -proportion of individuals who answered question j incorrectly

var – variance of scores for all individuals who took the test

The value for KR-20 ranges from 0 to 1, with higher values indicating
higher reliability.

KR-20 Reliability Coefficients

Less than 0.50 - low

Between 50 to 80 - moderate

Above 0.80 - high

 17

Example:

Suppose we administer a test with 7 questions to selected 10 students.

The results of the test are listed below, with 1 indicating a correct answer
and 0 indicating an incorrect answer.

Student Q1 Q2 Q3 Q4 Q5 Q6 Q7 Total
Correct
1 0 1 1 0 1 1 1 5
2 1 1 1 1 0 0 0 4
3 1 1 1 1 0 1 1 6
4 1 1 0 0 1 1 0 4
5 0 1 1 1 1 0 1 5
6 1 0 1 0 1 1 0 4
7 1 1 0 0 0 0 0 2
8 1 1 0 1 0 1 0 4
9 0 0 1 1 0 0 0 2
10 1 1 1 0 1 0 1 5
p 0.7 0.8 0.7 0.5 0.5 0.5 0.4
q 0.3 0.2 0.3 0.5 0.5 0.5 0.6
pq 0.21 0.16 0.21 0.25 0.25 0.25 0.24

K=7 variance = 1.6556 (Note: Use the formula for sample variance)

∑pq=1.57

KR-20 = (7/6)[1- (1.57/1.6556)]

= 0.0603

The KR-20 value turns out to be 0.0603. Since the value is extremely low. This
indicates that the test has low reliability. This means the questions may need to
be re-written or rephrased in such a way that the reliability of the test can be
increased.
 18

References

Bueno, David C. 2016. Introduction to Statistics. Concepts and Applications in

Research. Great Books Trading.

Subong, Pablo E. 2005. Statistics for Research. Applications in Research, Thesis

and Dissertation Writing, and Statistical Data Management Using SPSS
Software. Rex Book Store,Inc.

Professional Education(A Reviewer for the Licensure Examinations for

Teachers). Philippine Normal University. Manila.

Disclaimer

This module is prepared for instructional purposes only based on our course syllabus.
The teacher who prepared this does not claim ownership of this module but patterned
the ideas from different authors.