0% found this document useful (0 votes)
4 views9 pages

Research Methodology: Quantitative vs Qualitative

The document outlines key concepts in research methodology, including paradigms, ontology, epistemology, and methodology, emphasizing the differences between quantitative and qualitative research. It discusses various research methods, data collection techniques, and statistical analysis, including hypothesis testing and correlation. Additionally, it addresses ethical considerations in research and the importance of data saturation in qualitative methods.

Uploaded by

k9x5jh9fbj
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
4 views9 pages

Research Methodology: Quantitative vs Qualitative

The document outlines key concepts in research methodology, including paradigms, ontology, epistemology, and methodology, emphasizing the differences between quantitative and qualitative research. It discusses various research methods, data collection techniques, and statistical analysis, including hypothesis testing and correlation. Additionally, it addresses ethical considerations in research and the importance of data saturation in qualitative methods.

Uploaded by

k9x5jh9fbj
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd

Week 2 – 1 Feb 2022 - Lecture 2 - Tools

SPSS – for quantitative data


LucidChart Diagram – create conceptual model, frameworks

The Research P.O.E.M.

Paradigm – Your belief and principles towards conducting research.


 How do you view the world?
 Are you a realist, a relativist or a critical realist?
 Defines the nature of the world through your own eyes

Paradigm Choices
1. Positivism- one truth, can be measured, objective, quantitative research
2. Interpretivism – more truths, cannot be measured, subjective, qualitative research
 These 2 above are advisable for your thesis
3. Post-positivism

Ontology – Your Perspective toward existence, representing what you believe to be “real”.
 Describe your position as a researcher towards the research you are undertaking
 What is your research really about?
 Are you focusing on people, feelings, attitudes?

1. Realism – External, objective, independent


2. Critical realism – social conditioning, objective, independent
3. Relativism- Socially constructed, subjective, changeable, multiple

Epistemology – The relationships between the knower and the known, representing what
you count as knowledge.
 It helps you to express what you view as representing knowledge and/or evidence of
the “social reality”

The Nature of knowledge and meaning


1. Objectivism – Observable phenomena only
2. Constructionism
3. Subjectivism – Observable phenomena (and/or) subjective meanings

Methodology – The actual methods you use, the most suitable methods to address the
positions and perspectives outlined by the previous factors.
 This will be determined by the P.O.E.(M) to date
 Inductive and deductive approaches
 Primary and secondary data
 Quantitative and qualitative methods

How are they related?


Ontology > Epistemology > Theoretical perspective > Methodology > Methods > Sources
(see slide)
An overview of a research P.O.E.M. (see slide)
Triangulation – viewing a phenomenon from more than one perspective.
 Quantitative
 Qualitative
 Mixed methods

Deductive reasoning
General principle  special case
Theory > use SPSS, test the hypothesis it the theory is applicable or not

Inductive reasoning
Special case  general principle

Primary data collection


 The collection of new information

Secondary data collection


 Data that already exists

Quantitative is statistics, uses numbers, and statistical analysis, numerical evidence to test
hypothesis.
 Personal interviews
 Self-completion questionnaires

Qualitative focuses on collecting rich information.


 In-depth interview
 Focus group
 Observation
 Case study approach

Download SPSS
[Link]
Week 3 – 8 Feb 2022

Quantitative data vs Qualitative data


Quantitative data Qualitative data
 Numeric form  Textual form
 Deductive reasoning  Inductive reasoning
 Focuses testing theories and  Minimum guidelines about how
hypothesis people should answer in interviews
 Key terms: testing, measurement,  Key terms: understanding, context,
objectivity, replicability complexity, subjectivity
 Involve numbers, graphs, and tables  Involves verbal, behavioural, and
 Statistics used to analyse data observational data
 A large sample  Collecting “rich” information
 Closed questions  A small sample
 Open-ended questions

Quantitative research
 Use quantitative research if you want to confirm or test something (a theory or
hypothesis).
 Deductive reasoning – moving from general to specific. Example: hypothesis. Theory
> hypothesis > observation test > confirmation rejection
 Data collection methods: survey, experiment, structured observation, document
reviews.

Surveys:
Avoid double-barrelled questions
Avoid leading questions
Avoid social desirability questions

Average survey response based on survey methods


Highest: in person survey

Probability sampling = each item has an equal right of being selected.


- Simple random sampling
- Systematic random sampling
- Stratified random sampling
Non-probability sampling = all items do not have an equal right of being selected (AVOID).

Quantitative Research Design


- Descriptive
- Correlational
- Causal comparative
- Experimental

 Descriptive and correlational quantitative research is commonly used in business


research.
 Large sample (50 – 1000+ participants).
Qualitative research
 Use qualitative data if you want to understand concepts thoughts, experiences.

Week 3 – 9 Feb 2022 – Workshop 3

Words (categorizer)
- Nominal (groups without any logic: gender, department)
- Ordinal (groups with an order and logic: education level, breakfast lunch and dinner,
hot hotter and hottest.

Numbers (numerical)
- Ratio (age, salary)
- Interval (can be negative: temperature)

Statistics = making sense of numbers


A collection of mathematical techniques that help analyse and present data to get answers
to important questions.

 Descriptive statistics (describe or summarise a dataset)


- Measures of central tendency
- Measures of Dispersion

 Inferential statistics (test hypothesis)


o T Test, ANOVA, etc.
o Correlation & regression

Number (n_ is the total amount of elements (numbers)


Mean = (sum of the numbers) + n
Median = Middle number(s)
Mode = most common number
- There may be more than one mode

Standard Deviation (SD) indicates how much diversity there is within a variable
- Scores are grouped closely around the mean produce a low(er) standard deviation
- Scores that depart (deviate) more from the mean, produce a high(er) standard
deviation
Big standard deviation means high diversity.

Variance = (Standard Deviation)2

Range = difference between the maximum and the minimum


Inferential statistics
- You want to compare your sample data to other samples or to previous research
- We try to draw conclusions from the collected data by means of hypothesis
- A hypothesis is a testable statement that predicts what you expect to find in your
data.
- Based on the results of our statistical analyses, we either confirm or falsify the
hypotheses.

Steps of hypothesis testing


1. State the two hypothesis H0 and H1
2. Collect sample data
3. Calculate a sample statistic (p value)
4. Using the sample statistics, evaluate the hypothesis

P < 0.05  reject H0 and accept H1


P > 0.05  accept H0
0.05 = 5% is the most common standard

t Test – compares two groups of continuous variables to determine if one group statistically
significantly outperformed the other.

Pre-test checklist
- Normality (check before t Test run) (histogram should be comparable to the bell
curve)
- n quota (for each group at least 30 people or equal
- Homogeneity of variance (check after t Test run)

Check t Test on SPSS


Normality curve check
N quota = 35

One way ANOVA (homogeneity of variance test)


Dependent = time
Factor = group
Options > check descriptive, homogeneity of variance test

Based on mean number is higher than 0.05 which means pre-test is fully checked.

Conclusion
P = 0.010 (ANOVA table between groups ) < 0.05  H1 is true

Since p <0.05 we can conclude that text with illustrations (sigma = 92.00) statistically
significantly outperformed Text (sigma = 97.63).
Exercise Chapter 1A
Normality = its comparable, some are higher than the curve
N quota = 35

Analyze > nonparametric tests > legacy dialogs > two independent samples

Less then p < 0.05 means it’s true or there is a difference.

Statistic When to use


Descriptive Statistics Any continuous or categorical variable
t Test & Mann – Whitney U Test Two groups with continuous variables
ANOVA & Kruskal – Wallis Test Similar to t Test, except used when there
are more than two groups with continuous
variables
Paired t Test & Wilcoxon Test Compare pretest versus posttest
(continuous variables within 1 group)
Correlation and Regression One group wherein each record contains
two continuous variables
Chi-Square Two categorical variables

HOMEWORK WEEK 4
Chapter 6 – Example 01 – ANOVA and Kruskal-Wallis Test

ANOVA and Text Text with Video


Kruskal-Wallis Test illustrations
Normality Yes Yes Yes
N quota Yes (N = 35) Yes (N = 35) Yes (N=35)
Homogeneity of Yes Yes Yes
variance

Based on Mean: Sigma = 0.122


ANOVA Between Groups: p = 0.001 and is <0.05. So, we can conclude that video (sigma =
89.77) statistically outperformed text with illustrations (sigma = 92.00) and text (sigma =
97.63).

Chapter 7 – Example 01 – Paired t Test and Wilcoxon Test

Paired t Test and Pretest Posttest


Wilcoxon Test
Normality Yes Yes
N quota Yes (N = 64) Yes (N = 64)
Homogeneity of Yes Yes
variance
We can conclude that posttest (sigma = 86.56) statistically outperformed pretest (sigma
88.31).

Week 4 – 16 Feb – Workshop 4 - Correlation and Regression

Pearson correlation efficient


R closer to 1 data is closer to the line
If R is not close to 1, data is more scattered and is more widespread
0 = cloud of data without any direction

Positive correlation is the same


Negative correlation is always the opposite

P < 0.05  there is a statistically significant relationship


P > 0.05  there is no significant relationship

Normality – should be similar to the histogram curve


Linearity
Homoscedasticity – should not be widespread

Graph > Chart builder > Scatter/Dot > Double click Scatter Plot, Time on X-ax, Grade on Y-
axe > OK > double click on graph and add reference line.

Analyze > Correlate > Bivariate > move variables to the right

If conditions are satisfied, we used Pearson (is the most popular)


If at least one condition is not satisfied, we used Spearman.

Chapter 8 – Example 01 – Correlation and Regression – Pearson


R = 0.815
P = <0.001

We have a strong correlation or is statistically significant as p <0.05

 Pearson (used for numbers)


 Spearman (used for both number and words)
 Chi-Square (always used for words)
Example Ice cream flavour preferences

Week 5 – 1 Mar 2022 – Research Ethics

Questions to evaluate potential ethical concerns


- What is the purpose of asking this question?
- What will be the implications of asking it?
- What type of data will you need to collect to answer it?
- How will you collect these data?
- What are the implications for those whom you ask to participate in the research?
- How might the research be used with what consequences?

Ethical Risk – Low, Medium, High. Part of the ethical process to fill in the ethics form.

Ethical Form
Week 6 – 9 Mar 2022 – Qualitative Research Methods Workshops

Data saturation point in interviews.


Use a semi-structured interview

Planning
Preliminary stages
Define or justify the people for your sample
Recruit people for your sample
Aware of what we need to do to keep them safe, part of ethics.
Develop a flexible interview guide so you can add to the questions or rephrase them

Probing questions
- Elaborate
- Clarification
- Completion

What students think are the difference between the dissertation and consultancy project?

You might also like