See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/305992543

Introduction to Quantitative Research

Presentation · October 2016

DOI: 10.13140/RG.2.1.2786.5847

CITATIONS READS

0 5,540

1 author:

Guido Benny
Taylor's University
45 PUBLICATIONS   98 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

An Indigenous Framework for Southeast Asian International Relations Theory Development View project

All content following this page was uploaded by Guido Benny on 08 August 2016.

The user has requested enhancement of the downloaded file.

KURSUS PERSEDIAAN IJAZAH DOKTOR FALSAFAH
INSTITUT TADBIRAN AWAM NEGARA (INTAN)

Introduction to
Quantitative Research

Dr. Guido Benny,

Universiti Kebangsaan Malaysia,
guidobenny@ukm.edu.my
1
 RESUME

Guido Benny obtained his Doctorate in Strategic and Security Analysis

from Universiti Kebangsaan Malaysia in 2013. Previously, he has been
studying a Bachelor of Administrative Studies (1994-1998) and
Master in Management Science at the University of Indonesia (2001-
2003).

Currently, he works as a senior lecturer at the School of History,

Politics and Strategy, Universiti Kebangsaan Malaysia as well as the
managing editor of Jebat: Malaysian Journal of History, Politics and
Strategy at FSSK UKM.

His research interests are security issues and regional integration

initiative in East and Southeast Asia (ASEAN). He has written several
scholarly publications in English, Bahasa Malaysia and Bahasa
Indonesia, including 20 articles in ISI, Scopus and peer reviewed
journals, 13 working papers and proceedings, and 6 books.
Today’s MATERIALS can be downloaded at:
http://www.researchgate.net/profile/Guido_Benny/publications
KURSUS PERSEDIAAN IJAZAH DOKTOR FALSAFAH
INSTITUT TADBIRAN AWAM NEGARA (INTAN)

Contents

1.1. Quantitative Research Design

1.2. Measurement in Quantitative Research
1.3. Sampling
1.4. Survey

4
KURSUS PERSEDIAAN IJAZAH DOKTOR FALSAFAH
INSTITUT TADBIRAN AWAM NEGARA (INTAN)

1.1. Quantitative Research

Design

5
Research Design

A Research Design is the strategy for achieving the

desired research objectives. Research strategy
includes:
1. Research approach.
2. Development of instruments.
3. Data collection method.
4. Data analysis methods.
Research strategies – quantitative
and qualitative research
A common distinction is made between two different
strategies in research, the one using quantitative
methodology and the other using qualitative
methodology.

Apart from the simple distinction of the use of

measurement or description as the main approach to
collecting and analysing data, there is seen to be an
underlying epistemological difference in the two
approaches.
Research strategies – quantitative
and qualitative research
Bryman (2004, pp. 19–20) lists three characteristics
in each that make the point:
QUANTITATIVE
RESEARCH
Orientation Uses a deductive approach
to test theory
Epistemology is based on a positivist
approach inherent in the
natural sciences.
Ontology objectivist in that social
reality is regarded as
objective fact.
QUALITATIVE
RESEARCH
Uses an inductive approach
to generate theory
it rejects positivism by
relying on individual
interpretation of social
reality.
constructionist, in that social
reality is seen as a
constantly shifting
product of perception.
Qualitative “vs.” Quantitative?
Research question guides the choice
Choice of methods is situational
Complementary
 Research more complete with both
Each requires resources and time
 Can be amended for rapid analysis

9
Qualitative and Quantitative Approaches
Qualitative Quantitative
(Usually) Non-probability based Typically a probability-based
sample sample
Non-generalizable Generalizable
Answers Why? How? Answers How many? When?
Where?
Formative, earlier phases Tests hypotheses, latter
phases
Data are “rich” and time- Data are more efficient, but
consuming to analyze may miss contextual detail
Design emerge as study unfolds Design decided in advance
Researcher IS the instrument Various tools, instruments
10
employed
What is quantitative
research?
Burns & Grove (1987)
“... a formal, objective, systematic process
in which numerical data are utilized to
obtain information about the world" and
"a research method which is used to
describe and test relationships and to
examine cause-and-effect
relationships".

11
Quantitative Research

Typically involves counting or measuring

Often statistical tests are applied to
detect or confirm trends
Purpose is to get clear-cut, precise and
accurate results, factually reflecting the
situation under study
Questionnaire is one of the popular tools
for the quantitative research

12
Elements of quantitative
research
Gathering numerical data objectively

Results lend themselves to statistical analyses

Evaluation of results confirm or refute the original

hypothesis

Tests and experiments under controlled conditions

Cause and effect relationships

13
 Quantitative Research Designs
1. Exploratory -- It is a good starting point to get
familiarized with some insights and ideas (e.g. identify
the dependent and independent variables).

2. Descriptive – “The mapping out of a circumstance,

situation, or set of events” (McNabb). Research
Question: What is X, Y and Z?

3. Correlational – looking for relationship of two or more

variables. RQ: Is there a relationship between X and Y?

4. Causal—experimenting (statistically speaking) to asses

cause and effect. RQ: Does a change in X cause a
change in Y?
14
 Descriptive analysis...
No of events: 219 Natural disaster occupancy reported 1980-2009

No of people killed: 191,344 Storm 102

Average killed per year: 6,598 Flood 63

No of people affected: 317,454,534 Epidemic 27

Average affected per Heat 18

10,946,708
year: Earthquake 7

Economic Damage (US$ Drought 2

16,802,500
X 1,000): 0 20 40 60 80 100 120

Percentage people died in different natural disasters

1980-2009
Storm Flood Heat wave Epidemic

87% 6%
2%
5%

15
 Descriptive analysis...
Forced migration due to natural disasters
80
70
Number of migrants

60
50
40
30
20
10
0
1988 2005 2006 2007 2008 2009 2010
Climatic hazrds introduce forced migration
1%

3% 4% River erosion
23% Cyclone (SIDR)
Cyclone (Aila)
34%
Flood
Soil salinity
Both Aila and Soil Salinity
Both Sidr and Salinity
2%
32% Water logging16
1%
 Descriptive analysis...
Reason of migration

1% 5% Lost everything in origin

Not much hope to start in

origin
38%
I want to keep the families
56% in safe place
We could have better life in
City

Distance of migration destination

50

40

30

20

10

0
100 Km 80 Km 60 Km 40 Km 20 Km

Migrants 17
Hypothesis
Hypothesis = an idea that will be tested through
systematic investigation

A researcher’s prediction of what outcomes will occur

More clearly stated in research of 10 years ago than

now

Fits correlational / experimental research, also called

“Hypothesis Testing”

18
Hypothesis
H0 = Null hypothesis
No significant difference
No significant relationship / effect

Ha = Alternative hypothesis
Significant difference exists
There is significant relationship / effect
19
Correlational Research

To find if the data has an observable

relationship that can be further
specified in terms of magnitude and/or
an increase or decrease.

20
Characteristics of Correlational
Research

Correlation indicates the strength and

direction of a linear relationship
between variables.

21
Correlation and Significance
Is there a These relationships
relationship between may show any
two variables/data? tendency for the
What is the direction variables to vary
of the relationship? consistently.
What is the Pearson’s product
magnitude? moment coefficient
correlation: -1.0 to
+1.0

22
23
X ----- Y

Nationalism ------------ Support AEC

Independent var Dependent v.

 Optimism
 Moderating variable

24
KURSUS PERSEDIAAN IJAZAH DOKTOR FALSAFAH
INSTITUT TADBIRAN AWAM NEGARA (INTAN)

2. Measurement in
Quantitative Research

25
Measurement Fundamentals

Measurements of the different concepts should be valid

or match as much as possible the “real” world

What is a concept?
 “A mental construct that represents phenomena in the
real world”. (Pollock 2005:7)

The challenge is to transform concepts into concrete

terms (preferable that can be measured).

26
Pollock’s
model CONCEPT

CONCEPTUAL
DEFINITION

OPERATIONAL
DEFINITION

VARIABLE
(A STATE THAT TAKES
DIFFERENT ATTRIBUTES
O VALUES)
27
 A variable should be:
Exhaustive -- Should include all possible
answerable responses. (Schooling: No
Schooling, Elementary, Middle, HS,
College)
Mutually exclusive -- No respondent
should be able to have two attributes
simultaneously (e.g. Female Male ).

28
Some Definitions
VARIABLE DEVELOPMENT

ATTRIBUTE ATTRIBUTE DEVELOPED DEVELOPING

29
 How do we construct
quantitative variables?

In order to “Operationalize” our

variables we must first define them and
then select a means to construct them.
We do this by connecting concepts to
observations.

This requires choosing a level of

measurement.
30
The Levels of Measurement

Nominal
Ordinal
Interval
Ratio

31
 Nominal Measurement
Nominal: These variables consist of categories that
are non-ordered. Examples: gender, race, religion,
food group, or place of residence.

A simple categorical variable is binary or dichotomous

(1/0 or yes/no). For example, did a councilwomen
vote for the ordinance change or not?
 When used as an independent variable, it is often

referred to as a “dummy” variable.

 When used as a dependent variable, the outcome
of some phenomenon is either present or not.

32
 Ordinal Measurement
Ordinal: When the numbers are used to order a list of
things.
These variables are also categorical, but we can say that
some categories are higher than others. However, we
cannot measure the distance between categories, only
which is higher or lower.
 Hence, we cannot say that someone is twice as educated
as someone else.
 Can also be used as a dependent variable.

 When attributes can be rank-ordered.

33
 Ordinal Measurement
Distances between attributes do not have any meaning, for
example, code Educational Attainment as
0=less than High School
1=High School
2=Bachelor degree
3=Master degree
4=Doctoral degree
Is the distance from 0 to 1 the same as 3 to 4?

34
 Interval Measurement
 Interval: Variables of this type are called
scalar or index variables in the sense they
provide a scale or index that allows us to
measure between levels.
 We can, not only measure which is higher or
lower, but how much so.
 Distance is measured between points on a
scale with even units.
 Good example is temperature based on
Fahrenheit or Celsius.

35
 Interval Measurement
 When distance between attributes has
meaning, for example, temperature (in
Fahrenheit) -- distance from 30-40 is same as
distance from 70-80.
 Note that ratios don’t make any sense -- 80
degrees is not twice as hot as 40 degrees
(although the attribute values are).

36
 Ratio Measurement
Ratio: Similar to interval level
variables in that it can measure the
distance between two points, but
can do so in absolute terms.

 Ratio measures have a true zero,

unlike interval measures.
 For example, one can say that
someone is twice as rich as someone
else based on the value of their assets
since to have no money is based on a
starting point of zero.

37
Measurement Hierarchy
RATIO STRONGEST

INTERVAL

ORDINAL

NOMINAL
WEAKEST

38
KURSUS PERSEDIAAN IJAZAH DOKTOR FALSAFAH
INSTITUT TADBIRAN AWAM NEGARA (INTAN)

3. Sampling

39
40
Terms

Population - All possible subjects

Sample -A subset of subjects

Element - One subject

41
What do we sample?
People (e.g. subjects)

Places (e.g. hospitals,

units, cities)

Time (e.g. season, am

vs. pm shift )

42
Types of Probability Sampling
Probability sampling can be done only if we have
sampling frame (list of names, addresses, and
contacts of those in population list).

Simple random sampling – using a random table of

numbers
Stratified random sampling – divide or stratify by
gender and sample within group
Systematic random sampling – take every 10th name
Cluster sampling – select units (clusters) in order to
access patients or nurses

43
Types of Non-probability sampling
Convenience – first person to walk through the
door

Purposive (setting criteria for respondents) –

persons who have higher education background

Quota – equal numbers of men & women,

educational background, etc.

44
Sample Size Calculations

Depend on: Ratio of subjects to

variables in correlational
Type of design
analysis. 3:1 up to 30:1
Accessibility of subjects to variables. A
participants study with 30 items
Statistical tests questionnaire requires 90
planned to 900 subjects.
Review of the Chi square – can’t work if
literature less than 5 subjects per cell
Cost (time and
money)

45
Sample Size
• For survey research
200 individuals Census Sampling

Approximately 400 50%

Approximately 1,000 20%
Large population 5,000 350 – 500 are usually
or more sufficient
• For correlational studies), number of respondents
should be more than 30.
• For experimental research studies, usually we need at
least 30 participant for each group.
• This is based on the study of Krejie and Morgan (1970)
referred by many researchers for sample size.

46
 SAMPLE SIZE TABLE (KREJCIE DAN MORGAN, 1970)

Populasi Sampel Populasi Sampel Populasi Sampel Populasi Sampel

10 10 140 103 460 210 2,000 322

15 14 150 108 480 214 2,200 327
20 19 160 113 500 217 2,400 331
25 24 170 118 550 226 2,600 335
30 28 180 123 600 234 2,800 338
35 32 190 127 650 242 3,000 341
40 36 200 132 700 248 3,500 346
45 40 210 136 750 254 4,000 351
50 44 220 140 800 260 4,500 354
55 48 230 144 850 265 5,000 357
60 52 240 148 900 269 6,000 361
65 56 250 152 950 274 7,000 364
70 59 260 155 1,000 278 8,000 367
75 63 270 159 1,100 285 9,000 368
80 66 280 162 1,200 291 10,000 370
85 70 290 165 1,300 297 15,000 375
90 73 300 169 1,400 302 20,000 377
95 76 320 175 1,500 306 30,000 379
100 80 340 181 1,600 310 40,000 380
110 86 360 186 1,700 313 50,000 381
120 92 380 191 1,800 317 75,000 382
130 97 400 196 1,900 320 100,000 384 47
KURSUS PERSEDIAAN IJAZAH DOKTOR FALSAFAH
INSTITUT TADBIRAN AWAM NEGARA (INTAN)

4. Survey

48
49
 Why do a survey?

The survey is an appropriate means of gathering

information under three conditions:

 when the goals of the research call for

quantitative and qualitative data,

 when the information sought is specific and

familiar to the respondents and;

 the researcher has prior knowledge of the

responses likely to emerge.

50
 Types of data collected

There are six basic types of data that

you might collect:

 Attitudes
 Opinions
 Beliefs
 Behavior
 Attributes (demographic characteristics)
 Preferences

51
 Survey - Steps
1. Define the problem/ survey topic
2. Use previous studies & expert advice
Mail
3. Define research questions/ objectives
4. Define study population and sample
size Web-based
5. Develop a preliminary questionnaire
Question-
6. Pretest the questionnaire (similar naires Group
subjects)
7. Cover letter (Introducing the study, E-mail
deadline for return, guarantees for data
anonymity) Interview

8. Stamped & self-addressed envelop

9. Follow-up letter for non-respondents
52
 Use of Surveys by study design
Descriptive research
 Describe phenomena and summarize them.
 The goal of using surveys for descriptive research is to
get a precise measurement of specific concepts i.e.
knowledge, supports, perception.

Causal explanation
 Measure associations i.e. knowledge and support.
 The data from surveys can provide a causal explanation to
phenomena such as why there are more supports among
educated public for regionalism initiative.

Evaluation
 Efficacy of a program

Prediction
 Predict future events

53
 Survey - Advantages
Broad coverage (local, national, international)
Frank and anonymous answers
Economical for large population
Less Time consuming
Quantitative data (easy to analyze)
Filling at a convenient time
Easy to respond (fixed responses)
Good for sensitive & ego-related Qs.
Original hard-to-obtain data

54
 Survey - Disadvantages
No clarification for ambiguous questions
Inadequate motivation to respond
Poorly worded or direct questions
Unattractive style and format
Low response rate
Inaccurate responses – no verification
Limited fixed responses
Cannot uncover causes or relationships for attitudes,
beliefs, actions

55
 56
View publication stats