Sei sulla pagina 1di 84

Data Analysis

Prepared by: xxx First Prepared on: xx-xx-xx Last Modified on: xx-xx-xx
Quality checked by: xxx
Copyright 2004 Asia Pacific Institute of Information Technology
Research Methods for
Degree Study
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Topic & Structure of the lesson
Introduction
Qualitative Analysis
Quantitative Analysis

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Learning Outcomes
A the end of this topic, You should be able
to:
Have a better understanding of both
qualitative and quantitative ways to analyse
your statistical data.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Qualitative vs. Quantitative Analysis
An intelligent way of differentiating Qualitative
research from Quantitative research is: that
largely
1.Qualitative research is exploratory, while
Quantitative research is conclusive.

2.Quantitative data is measurable while
Qualitative data can not be put into a context that
can be graphed or displayed as a mathematical
term.


Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Introduction

Data Classification


Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Time series data :
A set or ordered data values observed at
successive points in time
Cross sectional data:
A set of data values at a fixed point in time
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Qualitative / Categorical
Nominal
Classification based on some defined characteristics.
Example: sex, color of eyes/hair, ethnic background, makes
of car and so on.
No inherent orders in categories
Data categories are mutually exclusive (an object can
belong to only one category)
In general, it is simply classification without order.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Ordinal
Data categories are mutually exclusive
Categories have inherent orders
Job grades, age groups, course grades
Binary
2 categories- special case of above
Fail/pass

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Quantitative data:
Interval Data
If the distance between two data items can be measured on
some scale and the data have ordinal properties (e.g.
temperature)
Data categories are mutually exclusive.
The point zero is just another point on the scale.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Ratio Data
Data that have all the characteristic of interval data but also
have a true zero point that reflects an absence of the
characteristic measured. (at which zero means none).
(e.g. weight, score, income)



Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Quick Review Question
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

What factors determine the most appropriate
statistical techniques?
Research objectives / questions / purpose of your
study
Measurement scales you used in your research
instrument
Research design of your studies.
Nature of your data meeting normally and / or
equality of variance assumptions for parametric
tests.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

A 7-point Likert Type Ordinal Scale


Scales of Measurement
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Continuum of Awareness



Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Continuum of Agreement



Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Table for selecting Descriptive measure based on
Scales of measurement



Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Qualitative Analysis
The process of interpreting data collected during the course of
qualitative research
The analysis of data depends on its type.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

The process of presenting and interpreting
numeric data collected during the course
of quantitative research
Often contain descriptive statistic and
inferential statistic.

Quantitative Analysis
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Descriptive statistics summarize, simply
and describe a large number of
measurements.
It include measures of central tendency
(averages mean, median and mode)
and measures of variability about the
average ( range and standard deviation).
These give the reader a picture of the
data collected & used in the research
project.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Inferential statistics are the outcomes of
statistical tests helping deductions to be
made from the data collected, to test
hypothesis set and relating findings to the
sample or population.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis

Organizing Data
Two important groups of descriptive
procedures
Frequency distribution
Graphical representation
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Charting Frequency Distribution
Bar Chart
Histogram
Frequency curve
Ogive
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Sales Performance of ABC Company
0
2000
4000
6000
8000
10000
12000
1989 1990 1991 1992
Year
S
a
l
e
s
Simple Bar Chart

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Component Bar Chart

Assets of the company 1988 - 1992
0
200
400
600
800
1000
1200
1400
1988 1989 1990 1991 1992
Year
A
s
s
e
t
s

(
'
0
0
0
)
Cash
Debtors
Stock & Work-in-
progress
Plant & machinery
Property
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Multiple Bar Chart

Assets of the company 1988 - 1992
0
100
200
300
400
500
600
1988 1989 1990 1991 1992
Year
A
s
s
e
t
s

(
'
0
0
0
)
Property
Plant & machinery
Stock & Work-in-
progress
Debtors
Cash
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Percentage Component Bar Chart

Defective Electrical Appliance Returned
0%
20%
40%
60%
80%
100%
Jan Feb Mar Apr May
Month
P
e
r
c
e
n
t
a
g
e

R
e
t
u
r
n
e
d
Product C
Product B
Product A
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Percentage Multiple Bar Chart

Defective Electrical Appliance Returned
0
10
20
30
40
50
60
70
80
Jan Feb Mar Apr May
Month
P
e
r
c
e
n
t
a
g
e

R
e
t
u
r
n
e
d
Product A
Product B
Product C
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
They can be drawn with vertical or horizontal bars,
but must show a scaled frequency axis.
They are easily adapted to take account of both
positive and negative values.
Two bars can be placed back-to-back for
comparison purposes
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
0 50 100 150 200 250 300 350 400
Number of holidays
1981
1982
1983
1984
1985
1986
Y
e
a
r
Holidays booked through a travel agent
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Balance of payments for a country
-1500
-1000
-500
0
500
1000
1500
1991 1992 1993 1994 1995 1996 1997
Year
$

m
i
l
l
i
o
n
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Monthly Expenses For Family B
Food
Rent
Clothing
Education
Savings
Miscellaneous
Food
Rent
Clothing
Education
Savings
Miscellaneous
Monthly Expenses for Family A
34%
22%
14%
12%
10%
8%
Food
Rent
Clothing
Education
Savings
Miscellaneous
Pie Chart

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Monthly Profits in $,000 of 100 Shops
0
5
10
15
20
25
30
0-50 50-100 100-150 150-200 200-250 250-300
Profit in $,000 per shop
N
o
.

o
f

S
h
o
p
s
Histogram

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
It shows three general types of information
It provides a visual indication of where
the approximate center point along the
horizontal axes in the histograms.
We can gain an understanding of the
degree of spread (or variation) in the
data. The more the data cluster around
the center, the smaller the variation in
the data.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
We can observe the shape of the distribution. Is
it reasonably flat, is it weighted to one side or
the other, is it balanced around the center, or is
it bell-shaped ?
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Summary Measures
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Characteristics of Distribution
Before data can be effectively used or analysed it
is normal to group or arrange the raw data into
manageable form.
Array
Frequency distribution
Simple
Grouped

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Measures of Central Tendency
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Mean
It is the arithmetic average of data values
and usually denoted by
For a set of values
mean,

For a simple frequency distribution,
mean ,


x
n
x
x

=

=
f
fx
x
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
For grouped frequency, it is impossible to
find the total values of the items, which
means, in effect that, it is impossible to
calculate the mean exactly. However, it
is possible to estimate it.

mean,

where x = class mid-point

=
f
fx
x
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
it might be distorted by extremely high or low
values.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Median
it is the value of the middle member of a
distribution or array ( or the value of that item
which lies exactly half way along the array).
median for a set of data
median for a simple frequency distribution
median for grouped frequency distribution
estimated by
graphical method
interpolation method

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Advantages
it is unaffected by extremely high or low
values.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
can be used when certain end values of a set
or distribution are difficult, expensive or
impossible to obtain, particularly appropriate
to life data.
can be used with non-numeric data if
desired, providing the measurements can be
naturally ordered.
will often assume a value equal to one of the
original data.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Mode
the mode of a set of data is that value
which occurs most often, or, equivalently ,
has the largest frequency.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
mode for a set of data
mode for a simple frequency distribution
mode for grouped frequency distribution
estimated by
graphical method
interpolation method

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Which measure of location is the best?
Mean is generally used, unless extreme values
(outliers) exist
Then median is often used, since the median is
not sensitive to extreme values.
Example: Median home prices may be reported
for a region less sensitive to outliers
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Measures of Dispersion (Variation)
A measure of the degree or dispersion of data
Range
Standard deviation
Variance
Quartile deviation
Mean deviation
Needed for two basic purposes.
To asses the reliability of the average of the data
To serve as a basis for control of the variability

Measures of variability
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Standard deviation
it is a measure of the extent to which
data for a particular random variable (x)
is spread about the mean.
The higher the standard deviation the
greater the amount of scatter.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Comparing standard deviation
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
standard deviation for a set of values is
calculated as follows:
For population


( )

N
2
x


= o
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
For sample


( )

1 - n
2
x x


= s
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Standard deviation for simple frequency
distribution
For sample:



For Population:


where x = class mid-point
( )

=
1 f
x x f
s
( )


=
f
x f

2
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Another formulation which is convenient
when a calculator is being used is as
follows:



2
f
fx
f
2
fx
|
.
|

\
|

= o
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
The Empirical Rule
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Variance
it is a measure of the extent to which
values in a data set vary around the
mean.
if most values cluster closely around the
mean, the variance will be a small figure.
if, however, most values are widely
dispersed around the mean, the variance
will be a large figure.
variance = (standard deviation)
2

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Coefficient of variation
also known as coefficient of dispersion
Ratio of the standard deviation of a distribution to
the mean of the distribution.

Coefficient of variation =


% 100
x
o
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Comparing coefficient of variation
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Skewness is the statistical term for
asymmetry or lop-sideness
Measure of skewness summarises to what
extent the items are symmetrically
distributed.
If the frequency distribution is
symmetrical, then the mean, median and
mode are identical.
Measure of Skewness
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Data which are not symmetrical may be
either positively or negatively skewed.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Data which are not symmetrical may be
either positively or negatively skewed.
Two measures of skewness
Pearsonian measure of skewness, Psk
Quartile measure of skewness, Qsk
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Pearsonian Measure of Skewness, Psk

Psk =

=

Quartile measure of skewness

Qsk =
deviation standard
mode mean
deviation standard
median) 3(mean
1
Q
3
Q
2
2Q
1
Q
3
Q

+
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Measures of relationship
Correlation analysis is used to
measure strength of the association
(linear relationship) between two
variables
Only concerned with strength of the
relationship
No causal effect is implied

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Measures of correlation
Product moment correlation coefficient
Spearman rank correlation coefficient
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Product moment correlation
coefficient, r
It measures the extent to which two
variables move in sympathy with or in
opposition to one another.

( ) ( )( )
( ) ( )
(

=
2
y
2
y n
2
x
2
x n
y x xy n
r
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
The correlation coefficient, r lies between
0 and 1.
When r = 0, it signifies there is no
correlation present
When r = 1, it signifies perfect positive
correlation
When r = -1, it signifies perfect negative
correlation
The further away r is from 0, the stronger
is the correlation.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Spearman rank correlation coefficient,
r
s

It can be used:
as an approximation to the product moment
coefficient
With non-numeric data that can be ranked


Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Procedure for obtaining r
s
Rank the x values, r
x

Rank the y values, r
y

For each pair of ranks, calculate d
2
=(r
x
r
y
)
2
Calculate d
2

The value of the rank correlation coefficient
can then be calculated as below:


( ) 1
2
n n
2
d 6
1
s
r

=
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Statistical Inference
Process of drawing conclusion about some
measure or attribute of a population based
upon analysis of sample data.
Estimation
Hypothesis Testing
Parametric testing
Non-parametric (chi-square test)

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Introduction
Deals with the estimation of population
characteristics from sample statistics
The distribution of sample means follows a
normal curve.
Estimation
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
A point estimate is a single number,
a confidence interval provides additional
information about variability
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Introduction
Alternatively called significance testing.
Is testing a belief or opinion by statistical
methods.
In decision making, we make an assumption, called
hypothesis, then we collect some sample data,
produce sample statistics and use this information to
decide how likely it is that our hypothesized population
parameter is true.
Commonly used for testing sample means &
proportion

Hypothesis Testing
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
In hypothesis testing, we must stated the
assumed or hypothesized value of the
population before we begin sampling.This
assumption is called the null hypothesis.
The Null hypothesis (H
o
) usually assumes there is
no difference between the observed and
believed values.
If our sample results fail to support the null
hypothesis, then the conclusion that we do
accept is called the alternative hypothesis, H
1
.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Non-parametric Tests
Introduction
The significance tests covered so far
depend, to greater or less extent, on the
assumption, or presence of the normal
distribution
They are also concerned with the
parameters of the distribution e.g. mean,
proportion. Hence given the mean of
parametric tests.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
However, on occasions, the data are not normal,
or contain extreme values or not enough is
known to be able to make any assumption
about the type of distribution. Then non-
parametric or distribution free tests may be used.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Chi-square (_
2
) Distribution
used when it is wished to compare an
actual, observed distribution with a
hypothesized, or expected distribution.

_
2
=

where O = the observed frequency of any value
E = the expected frequency of any value
( )


E
2
E O
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
The obtained value from the formula is
compared with the value from _
2
table for a
given significance level and the number of
degrees of freedom.
Degrees of freedom = (Rows-1)(Columns 1)
If _
2
calculated is > _
2
from table, the null
hypothesis is rejected.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Use broadly for
Test of goodness of fit (for one way classification or for
one variable only)
Can also be used to determine how well empirical
distributions I.e. those obtained from sample data fit
theoretical distributions such as the Normal, Poisson
and Binomial
Test of independence (for more than one row or
column in the form of a contingency table covering
several attributes.)
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Summary of Main Teaching Points
Statistics are tools that help researchers to
interpret the results of studies. Some
statistical procedures (descriptive statistics)
describe data from a study. These include
measures of central tendency, measures of
variability and correlations. Others
(inferential statistics) are designed to help
to interpret the data.

Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
The appropriate statistic (s) will depend on
the nature of the data and on the nature of
the questions. Inferential statistics help
researchers to make decisions about
populations on the basis of samples drawn
from those populations, but these
procedures are not perfect and decision
errors are possible.
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
What do you aspect to obtain from the question and
this should relate to your project objectives
Fundamental Question
The most fundamental question one should ask is:
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Identify at least ONE (1) qualitative analysis which you
may apply for your project and why?
Exercise
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Q & A
Question and Answer Session
Module Code and Module Title Title of Slides
Research Methods for Degree Study
Introduction to Research
Data Analysis
Next Session
GOOD LUCK!!!

Potrebbero piacerti anche