ICT615

Information Technology Research

Methods

Topic 6
Data Analysis
Acknowledgement
of Country
We acknowledge the Binjareb people of the Noongar nation as
the traditional custodians of this country and its waters and that
Murdoch University stands on Noongar country.

We pay our respects to Noongar elders, past and present and

acknowledge their wisdom and advice in teaching and cultural
knowledge activities.
COVID-19
student protocols.
Personal If you’re unwell don’t come
Visit MyMurdoch Student Portal to stay up-to-date. to campus. Stay home, get
Health tested and see a doctor.

If you’re diagnosed with

Please wipe down all
Computer COVID-19 or have been in close

Labs
surfaces after you have Reporting contact with a confirmed case,
used them. stay home and let your unit
coordinator know.

Be kind, respectful and

Behaviour supportive to people in Physical Stay 1.5 metres apart
at all other times.
our University community. Distancing

Leave space for people Wash your hands with

Entering soap and water regularly,
+ Exiting
when entering and Hygiene and cough and sneeze
leaving buildings.
into your elbow.
Readings and resources

Required reading:
• Oates Chs 17 & 18
Other readings:
• Cornford, T. and Smithson, S. (1996) Chapter 7: Analyzing research data. Project
Research in Information Systems. MacMillan Press
• Page, C. & Meyer, D. (2000). Data analysis: Making sense of the words and
pictures. In Applied Research Design for Business and Management (pp. 123 –
142). McGraw-Hill.

4
Learning objectives
After completing this topic you should be able to:
• Describe the common types of quantitative data:
nominal, ordinal, interval and ratio
• Describe some of the measures and visual aids
commonly used in descriptive statistics
• Describe the difference between descriptive and
inferential statistics
• Recognise research situations in which the following
statistical tests can used: chi-square test, correlation, t-
test
• Describe the nature of qualitative data analysis

5
Experiments are a research strategy or approach

6
What is data analysis?

Data analysis is the process of using the data you have

collected to answer your research questions.
• In quantitative data analysis the focus is on numbers –
descriptive and inferential statistics are used to
answer the research questions.
• In qualitative data analysis non-numerical data is
analysed – e.g. text and other media

7
 Types of quantitative data - nominal

Nominal data – describes categories. Analysis involves counting and comparing

frequencies. For example, gender:
Q1. What is your gender?
Male → 1
Female → 2
Might be reported in this way:
Approximately 80% of IT professionals in Australia are male and 20% female

8
Types of quantitative data - ordinal

Ordinal data – is measured on a scale with order, but the

intervals are not equal. For example:

Student grades
1= N, 2 = P, 3 = C, 4 = D, 5 = HD

Likert scales
Strongly Strongly
disagree agree
1 2 3 4 5
6 7

9
Types of quantitative data – interval & ratio

Interval data – is like ordinal data but the difference

between points on the scale are equal sized. For example:
• Temperature in degrees Celsius
• Time on a 12 hour clock

Ratio data – is like interval data

but there is a true zero point to the scale. E.g.:
• Age in years
• Temperature in degrees Kelvin

10
Question

For each of the following types of scales, think of an example of a variable that
would be measured using it:
• nominal
• ordinal
• interval
• ratio

11
Descriptive statistics

Descriptive statistics – are used to describe and summarise information about the
sample
Graphical descriptive methods include: pie charts; bar charts; line charts; and
box plots.

12
Box plot example

13
Descriptive statistics

Numerical descriptive methods include:

• Measures of central tendency – mean (average), median (centre value if all are
listed in increasing order), and mode (most frequent value)
• Measures of variability – range (diff between maximum and minimum),
quartiles (top 25%, next 25%, etc), standard deviation - average distance of
each data value from the mean

14
Question
ID Score
1 10
Participants take a quiz to test
2 10
their knowledge as part of an
3 15 experiment on e-learning
4 15
5 20 1. What is the mean score?
6 25
7 30 2. What is the median?
8 30
3. What is the mode?
9 30
10 85 4. What is the range?
Total 270
15
Inferential statistics

Inferential statistics (tests of significance) – are used to make predictions or

inferences about population characteristics from information contained in a sample.
They give us an estimate of the likelihood that an apparent relationship is due to
chance.

When testing a hypothesis, you accept or reject the hypothesis based on

information from the sample. As any sample will vary somewhat from its population,
you must have a way of judging whether these differences are statistically
significant or insignificant.

16
 Example - testing a hypothesis using statistics

H1: Users who receive training on how to remember passwords will create stronger
passwords
H0: Users who receive training on how to remember passwords will not create stronger
passwords (null hypothesis)

If you find that passwords from the treatment group are stronger than those from the
control group, how likely is it that the same would be true for the population?
A common convention is to say that if the probability of the difference occurring by
chance is less than 5% (p<=0.05) you can accept that the difference is ‘real’ or
significant

17
Inferential statistics

The type of statistical test you use depends upon the hypothesis and the type of
data you have (and whether it meets the assumptions of the test). Common tests
include chi-square, correlation and t-test.

Software such as Excel and SPSS (

http://www-01.ibm.com/software/au/analytics/spss/products/statistics/ ) can help

18
Inferential statistics – chi-square

Chi-square – use to test for differences between the observed

distribution of data among categories and the expected
distribution (based upon null hypothesis).

E.g. to answer a research question such as:

Are males more likely than females to own a Raspberry Pi?

19
Example – Gender preference for learning
Is there a difference?
Pearson Chi-Square = 0.474, p = 0.485

20
Inferential statistics

Correlation - used to measure how variables or rank orders are related.

E.g. is there a relationship between mathematical ability and programming

ability?
• R represents strength and direction of relationship (-1 to 1)
• P represents probability that the relationship is significant (AKA Sig.)

21
 Inferential statistics - correlation

How is age related to TV

watching?

22
Inferential statistics – t-test

t-test - can be used to compare:

• Whether the mean of a single variable differs from a specified constant

• means for 2 groups – e.g. user satisfaction M vs F.
• means of 2 variables for a single group – e.g. before & after

23
Does gender influence intention to comply with password
guidelines?
GENDER N Mean Std.
Deviation
IntentionComply 169 5.5863 1.26089
Male
231 5.8737 1.17296
Female

t-test for Equality of Means

t df Sig. (2-tailed) Mean 95% Confidence Interval
Difference of the Difference

Lower Upper
-2.345 398 .020 -.28740 -.52836 -.04644

24
Qualitative data analysis
• Qualitative data includes all non-numeric data – e.g. from interview
recordings, company documents, websites and developers’ models
• Generated commonly in interviews, case studies and action
research
• Qualitative data analysis is about abstracting themes and
patterns that are relevant to the research topic/question
• There are no fixed rules about how to do it
• Software such as NVivo can help:
http://www.qsrinternational.com/products_nvivo.aspx

25
Creating a hierarchical structure of nodes in NVivo

26
Analysing textual data
• Data preparation:
- Data is often from interview recordings or from unstructured field
notes.
- Transcribe, index, re-format…

• Analysis:
- Initial categorisation: into irrelevant, descriptive (facts), and
related to research questions.
- Categorise each unit of data according to themes, refining
categories as proceed. Categories can be: deductive (based on
existing theories) or inductive (based on the collected/generated
data).
- Draw conclusions: linking to existing or new theories.

27
Example - qualitative analysis of student comments about m-
learning

28
Example themes from qualitative analysis of
student comments about m-learning

29
Advantages and disadvantages of qualitative analysis

Advantages:
• Close involvement of researcher in the situation under study
facilitates insight.
• Research situation provides flexibility in data collection.

Drawbacks:
• Hard to generalise because of small number of cases.
• Because of richness, data is usually open to number of
interpretations.
• Lack of accepted techniques for analysis.

30
Learning objectives revisited

• Give an example of each of the following types of

quantitative data: nominal, ordinal, interval and ratio.
• What are common descriptive statistics?
• What kinds of data can the following statistical tests can
used with: chi-square test, correlation, t-test?
• What are some of the advantages and disadvantages of
qualitative analysis?

31
Thank you