Module XI : Data Analysis
To do:
- Measures of Central Tendency (Mean, Median, Mode)
- Measures of dispersion, range, and standard deviation
- Concept of Correlation and Regression
Univariate, Bivariate and Multivariate Analysis
Univariate – 1 Variable
Bivariate – 2 Variable
Multivariate – More than 2 variables
FORMULA
I) Measures Of Central Tendency
Central tendency is the middle point of a distribution
a. Mean
Average = Total / No. Of Participants
Ungrouped Grouped
εx
X= εfx f - frequency
n X=
εf m - midpoint
b. Median (Descriptive - Ordinal)
Interval Ratio of effective value
Median is the middle value of a series in ascending / descending order
Ungrouped Grouped
[ ]
n = odd ( n+1) (n+ 1)
Median= −(f +1)
2 2
n n
Median= w+ Lm
( )+( + 1) fm
n = even 2 2
Median=
n - total number of items 2
f - sum of all frequencies up to but not including the median class
f m - frequency of median class
w - class interval width
Lm- lower unit of median class interval
c. Mode (Descriptive - Non Ordinal)
Mode is the value with the max frequency
Grouped
Mode=L+
[ f 1 −f 0
2 f 1−f 0−f 2
L - lower frequency limit of the middle class
]×h
f 1 - frequency of modal class
f 0 - frequency of class before modal class
f 2 - frequency of class after modal class
h - class interval of the modal class
Measures Of Dispersion
The degree to which the numerical data tend to spread about around the average value is
called dispersion
Mode, Median – Range
Mean (likert) – Standard Deviation
Range
Ungrouped
Range = Maximum Value – Minimum Value
Standard Deviation
Ungrouped Grouped
√ √
2
ε ( x−x )
2 ε f ( x−x )
σ= σ=
n εf
σ – standard deviation
x – each value in data set
x – mean of all values in data set
n – number of values in data set
Correlation / Regression
Coefficient range from -1 to +1
strong moderate weak moderate strong
-1 -0.75 -0.25 0 0.25 0.75 1
Negative No Positive
Correlation Correlation Correlation