Cps3 –UNIT 4

QUANTITATIVE ANALYSIS AND

INTERPRETATION OF TEST SCORE
 Origin and growth of statistics

 The word statistics seems to have been derived

from the Latin word ‘STATUS’ or the Italian
word ‘STATISTA’ – statement or the German
word ‘STATISTIK’ -political state.
 MEANING OF STATISTICS

• The word ‘statistics’ is used to refer,

• Numerical facts, such as the number of people
living in particular area.
• The study of ways of collecting, analyzing and
interpreting the facts.
 DEFINITION BY CROXTON AND
COWDEN

Statistics may be defined as the science of

collection, presentation, analysis and
interpretation of numerical data from the
logical analysis.
 Measures Of Central
Tendency

mean MEDIAN MODE

AM GM HM
 MEAN (M)
(ungrouped (raw) data):
M= , = sum of all the observations
n= total number of observations
MEAN (grouped data):
M= ; = mid-point of the class interval,
f= respective frequency
n= total number of frequency
Mean (grouped data – short method):
M= A+ *i ; A= assumed mean
i= class interval
f= respective frequency of the mid-values of
the class intervals,
’= (X-A) / i
 Examples
=
 For raw data : 9,14,8,13,10,10,11,12,10 ; M

ANS:97/9=10.8
 For grouped data : method 1
For grouped data : method2 (short method)
 Median (M ) d

• Raw data:
• When N is odd: (N+1)/2th item
example : 34,56,66,89,93

• When N is even: The value of (N/2)th item+ The value of {(N/2)+1}th item
2
example : 34,56,62,66,89,93 ; 62+66=128/2
=64
Grouped data:
Md =L+[ ((N/2)-F)/ f] * i
L= Exact lower limit of the median class.
F= Total frequencies before in the median class.
f= Frequency of the median class.
i= class interval
N =total of all the frequencies.
 Median
 For grouped data: Md =L+[ ((N/2)-CF)/ f] *i
Scores f Cf

65-69 1 50 = 39.5+[((50/2)-
60-64 3 49 15)/11]*5
55-59 4 46
= 44.05
50-54 7 42
45-49 9 35
40-44 11 26
35-39 8 15
30-34 4 7
25-29 2 3
20-24 1 1
total 50
 Mode (Mo)
Un grouped data: occur most frequently
example : 25,29,24,56,25,89,21
Mo= 25.
Grouped data:
method 1: Mode= 3Median- 2Mean
method 2: mode = )*i
L= lower limit of the model class.
= frequency of the class adjacent to the model class for which lower
limit is greater than that for the modal class.
= frequency of the class adjacent to the model class for which lower
limit is lesser than that for the modal class.
i= class interval
 Mode
 Grouped data:
Scores f Cf mode = )*i
65-69 1 50
60-64 3 49
55-59 4  46 = 39.5+( 9/9+8) *5
50-54 7 42
 =42.15
45-49 9 35
40-44 11 26
35-39 8 15
30-34 4 7
25-29 2 3
20-24 1 1
total 50
 Problems: Find mean, median and mode
1. 1. 20,14,12,14,19,14,18,14
Score f
2. 135-144 1
125-134 2
115-124 8
105-114 22
95-104 33
85-94 22
75-84 9
65-74 2
55-64 1
 Quartiles: divides data into 4 equal parts.
 Deciles: divides data into 10 equal parts.
 Percentiles: divides into 100 equal parts.

0th 25th 50th 75th

100th
D0
D1 D2 Q1 D3 D4 Q2 D6 D7 Q3 D8 D9

D10

D5
 Formula for Quartiles and percentiles
 1ST quartile Q1=*i
 2nd quartile Q2=* i
 3rd quartile Q3=* i
 1st percentiles P1=* i
 10th percentiles P10=* i = D1
 25th percentiles P25=* i=P25=* i

 50TH percentiles P50=* i = D2=Q2=M d

 =*i

 75TH percentiles P75=*i

 =* i
scores f cf

70-79 3 24 Q1=*i
60-69 2 21 = 19.5+ (6-5/4)*10
=22
50-59 (Q3) 2 19

40-49 3 17 Q3=* i
30-39 5 14 first : =18
second ?
20-29 (Q1) 4 9
= 54.5
10-19 3 5

0-9 2 2

Total 24
 Measures of variability
 RANGE (R)= HIGHEST-LOWEST
 QUARTILE DEVIATION(QD)= (Q3-Q1)/2
 AVERAGE DEVIATION (AD)= (RAW
DATA)
= (grouped data)
 STANDARD DEVIATION (SD)
 QUARTILE DEVIATION(Q)= (Q3-Q1)/2

 RAW DATA Q1=(N+1)/4TH POSITION

Q3=3(N+1)/4TH POSITION (ARRANGE
ASCENDING ORDER)
 EXAMPLE:
23,24,25,26,27,28,29,30,34,33,35,36
 Q1=11+1/4=3 rd position=25; Q3=? ……Q=(Q3-Q1)/2

 GROUPED DATA:
Q1=*i Q3=* i
 AVERAGE DEVIATION (AD)
 AVERAGE DEVIATION (AD)= (RAW
DATA)
= (grouped data)
 Raw data: first find mean
Score X-M=x |x|
Scores f Mid fX x=X- fx |fx|
s(X)
grouped data point(
 X)
110-
114
 STANDARD DEVIATION (SD)

 Ungrouped data :
 Grouped data: short method
 i- class interval

IQ f X mid x’ =(X-A)/i x’2 fx' fx’2

SCORE point
 Workout part 2
Find SD and QD
125- 120 115- 110- 105- 100 95-99 90-94 85-89 80-84
129 - 119 114 109 -
124 104
1. 1 5 7 6 9 9 6 4 1 1

2. 30,35,36,39,42,44,46,38,34,35
NORMAL DISTRIBUTION
 NORMAL DISTRIBUTION AND ITS
PROPERTIES
Characteristics and properties of a normal curve
 Mean, median and mode are the same.
 The normal curve is bell shaped and it is symmetrical about the mean.
 The curve is asymptotic. It approaches but never touches the base line at

the extreme.
 The normal distribution curve is unimodal.
 In a standard normal distribution; the mean=0,SD=1
 The point of inflection on the cure are 1 SD away from the mean.
 The normal curve involves a continuous distribution.
 The value of skewness is 0 and the value of kurtosis is 0.263.
 The curve extends from -3σ to +3σ covering a total area of
10,000(taken arbitrarily).
 68.26% of this area falls within the limits + σ to -σ, 95.44 of this area

falls within the limits + 2σ to -2σ, 99.74 of this area falls within the
limits + 3σ to -3σ.
 The deviation or divergence from normality
tends to vary in two ways, In terms of
skewness and kurtosis.
 Skewness:
 Lack of symmentry. If the curve is shifted to the left or to the right,
it is said to be skewed.
 Negatively skewed –scores are higher than the average score of the
group. positive skewed –scores are lower than the average score of
the group.
 FORMULA FOR SKEWNESS

SK =3(M-Md )/SD

In case when percentiles are known,

SK =[(P90 + P10 )/2]- P50
 Kurtosis
 The term Kurtosis refers to the peakeness or flatness of a
frequency distribution as compared with the normal (Garrete
1981).

 Platykurtic. A frequency distribution is said to be playkurtic, when

it is flatter than the normal.
 Leptokurtic. A frequency distribution is said to be leptokurtic,
when it is more peaked than the
 normal.
 Mesokurtic. A frequency distribution is said to be mesokurtic,
when it almost resembles the
 normal curve (neither too flattened nor too peaked).
 Formula : Ku= Q/(P90 –P10)
CORRELATION
 Example:

Ans: 0.029
CORRELATION 2: spearman rank
Types of correlation
 GRAPHS
 It is the geometrical image of a set of data
 It is a diagram that exhibits a relationship,
often functional, between two sets of numbers
as a set of points having coordinates
determined by the relationship.
 TYPES OF GRAPHS
 LINE GRAPHS
 A line graph is used in displaying data or information that
changes continuously over time.
 The point on a line graph are connected by a line.
 Line chart –other name of line graaphs.
 BAR GRAPH
A bar graph is a chart that uses either horizontal or
vertical bars to show comparisons among categories.
 Pie Chart
• It is a circular statistical graphic, which is divided into
slices to illustrate numerical proportion.
=(freq/total freq)*360
 PICTOGRAM
 Numerical data of statistics may be represented
by means of a pictogram.
HISTOGRAM
The frequency polygon
Cumulative frequency curve (ogives)