The Basic Mathematics of

Measurements
• Variable:
• Any characteristics or quality which has
the ability to vary or has at least two points
of measurement. It is the trait that changes
from one case or condition to another. OR
Variable is a Characteristic or attribute
that can assume different values
• Frequency:
• Frequency may be defined as the number
of occurrences of any given value or set of
data.
• Frequency Distribution:
• A frequency distribution describes the
number of observations for each possible
value of a variable.
• Ungrouped frequency distribution This
gives number of observations of
each value of a variable.
• Grouped frequency distribution This gives
the number of observations of each class
interval of a variable.
• Cumulative frequency distribution This gives
the sum of the frequencies less than or equal
to each value or class interval of a variable.
• Example For the following set of scores of 20
students, draw ungrouped frequency table
with cumulative frequency. 45, 45, 50, 50,
50, 45, 35, 65, 60, 60, 60,75, 80,85,90, 45,
45, 50, 50, 35.
• Solution; We arrange the data in order
• 35, 35, 45, 45, 45, 45, 45, 50, 50, 50, 50, 50,
60, 60, 60, 65, 75, 80,85,90,.
Table of frequency distribution
Score Frequency Cumulative Rel cumulative
Frequency freq
35 2 2 0.1
45 5 7 0.35
50 5 12 0.6
60 3 15 0.75
65 1 16 0.8
75 1 17 0.85
80 1 18 0.9
85 1 19 0.95
90 1 20 1
 Making Grouped frequency
table
• Calculate the range (Highest – lowest)
• Decide interval width
• Calculate class intervals
• Count frequencies in each class.
• We can use L ≤ x ˂ u where l is the lower
limit and u is the upper limit
 Graphing Frequency
Distribution
• There are different ways of graphing
frequency distributions. Examples of these
are pie charts, bar charts, histograms and
line graphs
• A pie chart is a circle that’s divided into
one slice for each value. The size of the
slices shows their relative frequency.
Pie chart
 Bar Chart
• Bar chart of scores of 20 students
Normal distribution
• The normal curve provides us with an
umbrella under which most students fall.
Predictably, more students will fall toward
the center of the umbrella than the ends,
which is what gives the curve its 'bell'
shape.
Measures of Central tendency

Sum.of .all.scores
Mean 
Number.of .scores
 Mean 
 f x  f x

f N

Score (x) Frequency f fxx

5 3 15
6 4 24
7 2 14
8 5 40
9 3 27
Total 17 120
• Mean is useful for distributions containing
ordinal, interval and ratio scales.
• The mean is essential to the definition and
calculation of other descriptive statistics
• The mean it is the value that produces the
lowest amount of error from all other
values as it includes every value in your
data set as part of the calculation
Mean has a disadvantage that it is sensitive
to extreme scores (outliers) . These tend
to pull the mean in their direction. For
example scores 3,4,4,5,6,7 and 39.
The mean is 9.7 which does not lie near the
centre of the distribution.
3, 4, 4, 5, 6, 7, 39
This tendency of the mean is more
problematic when population is small.
 Median
• The median is a point that divides a set of
scores into two halves. This is the score
that rank in the middle.
• To find the median rank the scores in
ascending order. If N is odd median is the
middle number. If N is even he median is
the average of the two middle scores
• For the data 3,4,4,5,6,7 and 39 Median = 5
Like mean median is useful for distributions
containing ordinal, interval and ratio scales.
 Mode
• Mode is the most frequently occuring
score in the distribution. On a histogram it
represents the highest bar.
• For frequency distribution, mode is given
by the score with highest frequency

• Example
Score (x) Frequency f
5 3
6 4
7 2
8 5
9 3
Total 17

• Mode = 8
However, one of the problems with the
mode is that it is not unique, so it leaves
us with problems when we have two or
more values that share the highest
frequency
An advantage of the mode is that it can be
used with the nominal data as well as
ordinal, interval and ratio scales.
 Which measure of central
tendency is most useful?
For calculating other statistics mean is
essential
For descriptive purposes the median is most
useful
When the distribution is skewed the mean
tends to undermine its usefulness.
In a normal distribution mean, mode and
median are the same
Relationship among Mean ,
Median and Mode

Source
https://www.cuemath.com/data/relation-
between-mean-median-and-mode/
 3. MEASURES OF VARIABILITY
• The range: This is the distance between
smallest and largest score in the
distribution.
• Range = highest score – lowest score
• Eg 17,19,25,26,30,38,40,45
• Range = 45 -17 = 28
 The Percentile rank
Percentile rank is an example of ordinal scale.
It gives a relative position in a group in terms of
percentage of scores lower than it.
• Quartiles: The values which devide the
data into four equal parts are called
quartiles
• Example: 5, 8, 4, 4, 6, 3, 8
• Put them in order: 3, 4, 4, 5, 6, 8, 8

Quartile 1 (Q1) = 4
Quartile 2 (Q2), which is also the Median, = 5
Quartile 3 (Q3) = 8
• Example: 1, 3, 3, 4, 5, 6, 6, 7, 8, 8

• In this case Quartile 2 is half way between 5 and 6:

• Q2 = (5+6)/2 = 5.5
• And the result is:
• Quartile 1 (Q1) = 3
• Quartile 2 (Q2) = 5.5
• Quartile 3 (Q3) = 7
• The Quartile deviation. The middle 50% of a set of
scores is called the interquartile range. Half of this
is called the quartile deviation or semi interquartile
range.

• The middle 50% is bounded by 75 th percentile and

25th percentile.
• The quartile deviation is given by
• Q=(Q3-Q1)/2The value gives a better estimate of
the spread of the distribution since it is not greatly
affected by extreme scores.
 Stanine
• Stanine: This term literally means
'standard nine,' and test scores on most
standardized tests will fall into one of nine
stanines.
• Scores from the fourth through sixth
stanines are considered average, with
lower scores being below average and
higher scores falling in the above-average
ranges. Grouping scores into stanines is
just a handy way of letting you know how
your students scored on a scale of one to
nine.
 Variance and Standard
deviation
• Over two thirds of students will fall
between one standard deviation on either
side of the center of that curve, meaning
that the majority of students can be
considered pretty much 'average' when it
comes to taking a standardized test.
Variance shows the spread or dispersion. It shows
a tendency for any set of observation to depart
from a central point.
The sum of deviation from the mean is zero.
To avoid getting zero we square the deviations
and find their average.
 2 
( x  x )2
N
The square root of variance is known as standard
deviation.

 (x 2
x)
N
This is a measure of average distance that the
scores vary from the mean of the distribution.
x 2 4 5 6 6 7 30
-3 -1 0 1 1 2 0
9 1 0 1 1 4 16
 Steps in calculating standard
deviation
1. Calculate mean
2. Subtract each score from the mean. Sum
of these is zero. Square each of these.
3. Sum all the squared differences
4. Devide the sum by the number of scores.
This is the varience.
5. Find the square root of varience
 Significance of standard
deviation
• The larger the standard deviation the more
the scores differ from the mean the more
variability there is in the distribution. If the
scores are close to the mean the standard
deviation will be small.
Raw score. The raw score represents the
number of questions that were answered
correctly.
 Derived score
• This is a numerical result of test
performance on a scale that has well
defined characteristics and yields a
normative meaning. Examples of derived
score are percentile rank, and standard
score
 Standard score
• The number of standard deviations away
from the mean represents individuals
standard score or z score.
x x
z

For example if the mean is 70 and the standard deviation is 4,
for a score of 78 78  70
z 2
4
.This means that the score is 2 standard deviations above the mean.
For a score of 64, 64  70
z  1.5.
4
The score is 1.5 std deviations below the
mean.
• Almost 100% of all score in a normal
distribution fall within 3 s.d’s in both
directions. Thus the highest z score in a
normal distribution is always +3. The
average z score is zero and the lowest z
score is -3
• Why z- scores are used
1. Consistency: z-score is the same
regardless of distribution.
2. Helps to compare score obtained using
other scales.
• Almost 100% of all score in a normal
distribution fall within 3 s.d’s in both
directions. Thus the highest z score in a
normal distribution is always +3. The
average z score is zero and the lowest z
score is -3
• Why z- scores are used
1. Consistency: z-score is the same
regardless of distribution.
2. Helps to compare score obtained using
other scales.
 The T-score
• Raw scores are not always in normal
distribution. They can be negative skewed
or positive skewed.
• Raw scores are turned to be normally
distributed by changing them to T score
• T = 10z+50
Class Exercise: The following are the scores
of 30 students in English subject. 25, 26,
27, 29, 34, 40, 95 40, 43, 45, 46, 88, 55, 57,
58, 58, 65, 67, 59, 69, 70, 71, 71, 74, 75,
77, 87, 90, 31, 92.
a ) Classify the scores into stanines
b) Calculate the mean, the mode(s) the
range and the standard deviation. In the
scores given in a) above find the
i) Standard score of 77 and T score of 45.
Explain the meaning of the statement “
Said’s standard score is +1.5”.