Statistical Organization of Scores
Statistical Organization of Scores
Statistical Organization of Scores
ORGANIZATION OF SCORES
RAW SCORES BY
THEMSELVES ARE
USELESS
The raw score of Gina in a test is 45. What
does it mean?
A. She is better than 45% of her
classmates.
B. She ranked number 45 in her batch.
C. She got 45% correct answer in the test.
D. She got 45 correct answers.
Raw scores by themselves are
useless.
INORDER TO GENERATE
INFORMATION FROM RAW
SCORES THEY MUST BE
SUBJECTED TO STATISTICAL
TREATMENT
Types of Data/Level of
Measurement
The type of data you
have generated or
gathered determines the
statistical scores you
may apply.
Types of Data
1. Nominal Data. The data that are used to
label, classify or categorize.
( the lowest type of data)
Examples: Course, Religion,Year
Level, Nationality
Numbers can also be nominal
data but they don’t have less than or
greater than relationship
RESPONDENT SEX
A 0
B 1
C 1
D 0
E 0
F 0
Types of Data
2. ORDINAL DATA. The data that tell
less than or greater than relationship.
The difference however is not
equidistant that numbers here could not
be subjected to mathematical
computations.
Examples: Sibling Rank, Honor Rank
Sibling Ranks
First Child
9 1
8 1
7 1
6 1
5 1
4 1
Types of Data
4. RATIO DATA. The highest type of data
that combine the characteristics of other
data. There is greater than and greater
relationship and the gap is equidistant. The
difference between and ratio and interval
data is in the zero. The zero in ratio data
is absolute.
Example: income, weight gain, Kelvin
temperature scale.
Other classification of data
1. DISCRETE
2. CONTINUOUS
REMEMBER THESE PAIRINGS
DATA MEASURES OF MEASURES OF
CENTRAL TENDENCY VARIABILITY
3. MEAN STANDARD
INTERVAL DEVIATION
31-35 3 33 30 3
26-30 7 28 27 10
21-25 10 21 20 20
16-20 6 18 10 26
11- 15 4 13 4 30
Tabular Data Representation:
Frequency Polygon
MEASURES OF CENTRAL
TENDENCY
In an array of scores, can a teacher pick
up a score that can represent the enter
set of scores?
Consider these scores:
0, 1, 1, 2,2,3,3,3,5,5,6,6,6,7,7,7,8,8,8,9,10
MCT Defined
Scores which are usually found at the
center of the distribution that can
stand in behalf of the scores of the
distribution. They are the averages
and they are used to compare
performance
Consider the example below.
Which is the best performing class?
CLASS MEAN
CLASS A 45
CLASS B 46
CLASS C 43
What about this?
STANDARD
CLASS MEAN DEVIATION
A 35 4
B 35 3
C 35 2
THE MEAN
A teacher conducted 100-item tests in the
Subjects Mathematics, Science and English
in his class. The means of the class are as
follows: English- 46, Mathematics- 53 and
Science- 60. Is it a correct conclusion to
say that the class performed the best in
Science?
Characteristics of the Mean
1.The most stable & reliable measure of
central tendency.
2.The most widely used.
3. The balanced point of the distribution.
4. Affected by extreme measure.
5. Used when data are interval & ratio.
6. Paired with standard deviation
The mean is used to measure and
compare performance of two
groups that are normally
distributed, when the distribution
is symmetrical.
Sample exercises: The Mean
1. What is the mean of this data set?
14, 15, 16, 17, 18, 19, 20
2. In a certain science high school, in the
computation of the GWA, 2x and 3x
weights are given to Mathematics and
Science respectively. What is the GWA
of John if his grades are: English-87,
Filipino-83, Science- 92, Math- 93 and
Makabayan- 85?
What is the highest possible
value that a score could take if
the mean of the five scores is
8.? There is no duplication of
scores.
A. 25 C. 30
B. 15 D. 22
MEDIAN
The positional average. The
measure of central tendency that
tells position. It is a score that
bisects the distribution into half.
Characteristics:Median
1. It tells position or location.
2. Divides the distribution into half.
3. Not affected by extreme measure.
4. Used when the data are ordinal
5. Paired with quartile deviation
6. Necessitates the arrangement of data.
7.Used to describe performance if
the data are badly skewed or where
there are many scores that are very
high or very low or when the scores
cluster in the tail of the curve.
Sample Exercises:
1. What is the median of this
data set?
5, 7, 9, 10, 12
What about is 12 in the data above is
120? Would that change the median.
3. What is the median?
1, 0, -2, 5, 4
4. Where can you find the
median of 21 scores?
Consider this question:
The following represent the scores of
students in a 100-item test:
99, 98, 94, 90, 90... 18, 8, 4, 3, 1
SET A = 1, 4, 5, 6, 9
SET B = 3, 4, 5, 6, 7
Compare the data sets in terms
of the mean, median & mode.
Limitation of the MCT
The MCTs do not give an accurate
description of the data sets. It cannot
describe the data in terms of distance,
variability or dispersion.
Are the scores close? Are they widespread?
Homogeneous? Heterogeneous? Only the
Measures of Variability or Dispersion can
answer these questions.
The Measures of Variability
◦1. Range
◦2. Average Deviation
◦3. Quartile Deviation
◦4. Standard Deviation
◦5.Variance
INTERPRETATATION
THE HIGHER THE VALUE
DERIVED FROM ANY MEASURE
OF VARIABILITY, THE MORE
WIDESPREAD THE SCORES
ARE. THE LOWER THE VALUE,
THE CLOSER THE SCORES ARE.
Example:
WHICH OF THE FOLLOWING
STANDARD DEVIATION VALUES YOU
CAN FIND SCORES WHICH ARE
WISESPREAD?
A. s=0.9 C. s= 0.6
B. s=0.5 D. s= 0.3
THE RANGE
1. The SIMPLEST and the FASTEST
Measure of variability. Can be
determined by simple
inspection.
It is the also the crudest
measure of variability.
Consider this:
SET A: 1, 4, 5, 6, 9
SET B: 3, 4, 5, 6, 7
WHAT IS THE RANGE?
0, 2, -3 , 4, 5
2. The Q
Quartile Deviation,sometimes called as the
Semi-interquartile range measures the gap
between the Q3 and the Q1 divided by 2.
Q = Q3 - Q1
2
THE AVERAGE DEVIATION
2 4 6 8 10
Consider this:
5 , 5, 5, 5, 5, 5,
A
9 7 10 6 8 8
B
7 7 9 8 9 8
Consider the data below:
CLASS MEAN STANDARD
DEVIATION
CLASS A
45 6
CLASS B 45 3
CLASS C 45 5
5. The VARIANCE.
The square of the standard
deviation is the variance.
Q: What is the variance of the
data with a standard deviation
of 6?
Standard deviation Variance
10 100
49
25
11
9
If 5 points are added to every score in the
distribution, how would change the:
1. Mean
2, Median
3. Mode
4. Range
5. Standard Deviation
THE NORMAL
DISTRIBUTION
An assumption that most of the
members of the population are
average. The normal distribution is
represented by the normal curve, a
bell-shaped figure.
PROPERTIES OF NORMAL
CURVE
1. The curve is symmetrical and bell-
shaped.
2. The number of cases, N, is infinite.
3. The three measures of central
tendency, mean, median and mode
coincide at one point.
4. The height of the curve indicates the
frequency of cases expressed as
probability, proportion or
percentage.
5. The basic unit of measurement is
expressed in sigma units or standard
deviations along the baseline
6. Two parameters are used to describe the
curve.
7. There are three standard deviation units
to the left and to the rights of the curve
before the tail appear to touch the
baseline.
1. A distribution has a mean of 50
and standard deviation of 5. What
do you expect to be the highest
score assuming normality of the
distribution?
In a test, the mean of the class is 85 and
the standard deviation is 10. Assuming
normal distribution,
A. What is the highest score?
B. What is lowest score?
C. What are the scores of the average
students?
3. A test has produced a group mean of
50 and standard deviation of 7. What
adjectival rating would you give to a
student with a score of 48?
A. Average C. below Average
B. Above Average D. Poor
The Standard Scores
The standard scores are
transformed raw scores. Because
they are transformed scores, they
can be compared even though
they come from different sources,
subjects or even from test with
different number of items.
Z = score - mean
standard deviation
SCORES MEAN OF STANDARD
DEVIATION
OF JOHN THE
SUBJECTS CLASS
English 68 70 2
35 30 3
mathematics
59 64 5
science
JOHN’S MEAN OF STANDAR
SCORE THE D
SUBJECTS SCORE DEVIATIO
N
FILIPINO
100 110 5
HISTORY 90 110 7
MAPEH 75 70 2
SCORES OF MEAN OF SD
LANZ THE
SUBJECTS CLASS
PHILOSOPHY 25 25 3
HUMANITIES 40 35 2
RELIGION 60 70 5
VALUES 45 48 1.5
EDUCATION
SKEWNESS
Refers to the asymmetry of the
distribution. A distribution is skewed
is the scores clusters at the either
side of the tail. The curve is not
balanced.
Example:
1. Skewed to the right or positively
skewed- the tail extends to the right
side of the curve, while the scores
clusters on the right, thus, most values
are low, test is difficult.
the mean is the highest value followed by
the median and the mode.
2. Skewed to the left- the tail
extends to the left, but the scores
cluster in the right side, thus, most
values are high.
- the mode is the highest value,
followed by the median and the
mean.
Skewed Left
Tell whether the following are skewed
to left or skewed to the right.
1. salaries of janitors
2. weight and height of malnourished
children
3. height of PBA players
4. Scores of students in easy test
5. Grades of students in Calculus
6. NAT performance of students in special
science class
7. LET ratings of the topnotchers.
8. mean = 56, median = 50
9. marrying age of people in the
mountainous areas.
10. Average height of the Filipinos
taken in a census
KURTOSIS