Research Methodology - Midterm Notes

Chapter 1)

What is research

+ Research is, among other things, an intensive activity that is based

on previous works and generates new ideas and questions

+ A systematic process of collecting and analyzing information to increase our

understanding of the studied phenomena

High Quality Research

• is based on the work of others

• can be replicated
+ The same results should be obtained under the same conditions
+ It should be possible to recreate the same conditions
• is generalizable to other settings
• is based on some logical rationale and tied to theory
• is doable
+ Poses a question that can be answered, and then answers it in a timely fashion
• generates new questions or is cyclical
+ Today’s research questions provide the foundation for research questions
• is incremental
+ Contributions are usually made in small, definable chunks
+ All studies in an area come together to produce a foundation for further research
+ Each new research not only informs us but also offers a fresh perspective on other findings
• is an apolitical activity that should be undertaken for the betterment of society.
+ Should be conducted for society’s betterment and avoid unethical practices
Asking the Question

Our first and most important step is asking a question or identifying a need that arises from
curiosity, which necessitates an answer.

Questions arise from personal experience and imagination (of science, art, music, and
literature)

Questions can be as broad or as specific as demanded. Regardless, questions are the first step
in any scientific endeavour

Factors that should be considered for inquiry

In general, you should select factors that
• have not been investigated before
• will contribute to the understanding of the question being asked
• is investigatable
• interests you personally or professionally
• is cyclical (comes from previous questions and produce new questions)

Hypothesis: express the relationships between variables in a statement

Theory: A theory was defined as a set of statements that predict things that will occur in
the future and explain things that have occurred in the past.

Differences

• A hypothesis is a testable statement about a relationship between two variables and is

specific to one research question.

• A theory represents a body of related works

Research method types differ primarily on three dimensions:

• the nature of the question
• the method used to answer
• the degree of precision of the method utilised
Nonexperimental research examines the relationship between variables, without any
attention to cause-and-effect relationships.

Descriptive research focuses on events that occur in the present.

(E.g. The population of Vietnam in 2020)

Correlational research examines the relationship between variables

E.g. The relationship between academic achievements and job salary
The correlation between depression and suicide

Qualitative research studies phenomena within the social and cultural context in which they
occur.
E.g. Common beliefs about cheating in online exams among high school students

Experimental research examines the cause-and-effect relationship between variables.

True experimental research examines direct cause-and-effect Relationships.

Quasi-experimental studies also focus on cause and effect, using preassigned groups. (aka.
post hoc or after-the-fact research)
EX Question: Can Google Translate improve our translation skills? The effect of using Google
Translate on translation skills Treatment (IV) Outcome (DV)

Chapter 2)

Variable)
represents a class of outcomes that can take on more than one value. • A variable is a concept
— a noun that stands for variation within a class of objects, such as a chair, gender, eye color,
achievement, motivation, or running speed

A dependent variable represents the measure that reflects the outcomes of a research
study.

Eg: Effect of reading English magazines

Possible dependent variables:

IELTS reading band score (0 – 9.0)
English reading speed (words per minute)

Independent variables (treatment variables)

• The independent variable is manipulated or changed to examine its effect on the dependent
variable.

• Independent variables must take on at least two levels or values

1. The effects of gender differences (independent variable) on language development
(dependent variable) 2 levels: Male and Female
2. The effectiveness of Facebook in improving English writing 2 levels: Using Facebook and Not
using Facebook

• An independent variable represents the treatments or conditions that the researcher has a
degree of control over to test their effects

Eg:
Effect of reading English books on students’ EFL reading skills
Independent Variable: Reading English magazines
INDEPENDENT variable(s) (the cause) affects DEPENDENT variable(s) (the result)

Factorial designs are experiments that include more than one independent variable
A control variable is a variable that can potentially influence the dependent variable; must be
removed or controlled.

E.g.: the relationship between reading speed and reading comprehension needs to control for
differences in intelligence, topic familiarity

An extraneous variable is a variable that has an unpredictable impact on the dependent

variable (independent variables that have not been controlled)

A moderator variable (Interacting variable) is a related variable to the variables of interest (such
as the dependent and independent variable), masking the true relationship between the
independent and dependent variable.
The null hypothesis is a statement of equality (stating that there is no
differences/relationships) between two population parameters

Null hypotheses can’t be directly tested

A research hypothesis is a definite statement of the relationship between two variables

A directional hypothesis indicates the specific direction (such as higher, lower, more, or less)
that a researcher expects to emerge in a relationship.

A nondirectional hypothesis does not make a specific prediction about what direction the
outcome of a study will take

Good hypotheses
Complete and well-written hypotheses should:
• be stated in declarative form
• posit a relationship between variables
• reflect a theory or a body of literature upon which they are based
• be brief and to the point
• be testable.

A sample in a research study is the group on which information is obtained. The larger group
to which one hopes to apply the results is called the population.
• E.g. All 9th-graders (pop) 50 ninth-graders in a school (sample)
Our goal is to select a sample from a population that most closely matches the characteristics of
that population's representative sample

Statistical significance
• Significance is a measure of how much risk we are willing to take when concluding about the
relationship between variables.
• Significance level is the risk associated with not being 100% confident that the difference is
caused by what you think and may be due to some unforeseen factor
Chapter 3
Selecting a problem

+ Choose an area of your interests

• Be ready to accept change
• Do something that is doable
• Do something that is worth doing
• Personal experiences and firsthand knowledge
• The literature
• Link the experiences and the literature
• Talk to your adviser

From idea to research question

• Ideas are composed of higher thinking: beliefs, conceptions, suppositions, assumptions, what-
ifs, guesses

• Research questions are the articulation most often done in writing, of those ideas with a
semblance of relationship between variables

A well-written hypothesis:
1. is stated in declarative form
2. posits a relationship between variables
3. reflects a theory or body of literature upon which it is based
4. is brief and to the point
5. is testable
Good questions are
+ Feasible ( Costing reasonable effort and resources)
+ Clear (Common definition can be agreed on)
+ Significant (Contributes important information)
+ Ethical (Will not involve harm to subjects)

Writing the literature review

• Read other literature reviews on the topic(s)
• Work out the thematic units of your review
• Structure your review (e.g. chronological organization)
• Work out an outline (headings, subheadings, …)
• Connect different sections of your review
• Plan your writing and start writing

Ethics in Research: Principles

• Protection from harm: doing NO harm
• Maintenance of privacy: anonymity
• Voluntary participation: do not force people to participate
• Informed consent: let the participants know the nature of the research
• Confidentiality: keep the data in strict control
• Debriefing: let the participants know the results
• Sharing benefits: every participant should receive the treatment, if it is beneficial.

Chapter 4)

Key terms
• A Population is a group of potential participants to whom you want to generalize the results
of a study.
• A Sample is a subset of a population.
• Generalisability: When results are generalizable, they can be applied to different
populations with the same characteristics in different settings.

• Probability sampling: the likelihood of any one member of the population being selected is
known

• Nonprobability sampling: the likelihood of selecting any one member from the population is
not known.

Random sampling & non-random sampling

Random sampling: control extraneous/confounding variables; eliminate selection bias

Simple Random Sampling

• Each member of the population has an equal and independent chance of being selected to be
part of the sample
• Table of random numbers

Stratified Random Sampling

• Stratified sampling takes into account the different layers or strata that characterize a
population and allows you to replicate those layers in the sample.
• Stratified sampling is useful when the factors that distinguish population members from one
another (such as race, gender, social class, or degree of intelligence) are related to what you
are studying

Cluster Random Sampling

• Cluster sampling: units/groups of individuals are selected rather than individuals themselves.

Convenience Sampling
• Nonprobability sampling
• Convenience

RQ: Is your marriage happy? Convenience sampling: first 100 replies from the mail-out surveys

Purposive Sampling
• Purposive sampling is different from convenience sampling in that researchers do not simply
study whoever is available but rather use their judgment to select a sample that they believe,
based on prior information, will provide the data they need

RQ: What do Vietnamese people buy at shopping malls? Purposive sampling: Ask 10
customers at 8:00am, 10 customers at 12am, and 10 customers at 8:00pm

Quota sampling
• Quota sampling selects people with the characteristics you want (such as first-grade, rural
children) but does not randomly select from the population a subset of all subjects
Task: Interview 30 twelve-graders (The population is 500) Quota sampling: select the first 15
females, 15 males in the list (given gender is a relevant factor and the distribution of
male/female is approximately 50/50)
Sampling error
• Sampling error: the difference between a measure of the characteristics of the sample and a
measure of the characteristics of the population from which the sample was selected

• The larger the sample is (within reason), the smaller the sampling error will be
• If you are mailing out surveys or questionnaires, increase your sample size by 40% to 50% to
account for lost mail and non-responders.
• Remember that big is good, but accurate and appropriate are better

You will need a larger sample when:

The amount of variability within groups is greater
The difference between the two groups gets smaller

Sample size: Some magic numbers

• Descriptive studies: 100
• Correlational studies: 50
• Experimental/comparative studies: 30 each group
• Qualitative studies: 1 to 20