Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                

Module 2

Download as ppt, pdf, or txt
Download as ppt, pdf, or txt
You are on page 1of 64

 The foundation of the research process

 It all begins with a question


 From where ???????
◦ Curiosity
◦ Information Gaps
◦ Controversy
◦ Replication
◦ Literature Review
◦ Other People
◦ ...???
 Conceptualize that a research study can ask
three types of questions:
◦ Descriptive question
◦ Relationship question
◦ Difference question
 This general classification scheme helps not only
with the design of the study, but also in
choosing the type of data analysis procedure
 Seeks to describe phenomena or characteristics
of a particular group of subjects being studied
◦ Answers the question “what is”
 Asking questions of the research participants
 Testing or measuring their performance
◦ Survey research

 Example
◦ What are the attitudes of rural parents toward the
inclusion of sexuality education in the school
curriculum? (Welshimer & Harris, 1994)
 Investigates the degree to which two or more
variables are associated with each other
◦ Does not establish “cause-and-effect”
◦ Only identifies extent of relationship between
variables

 Example
◦ Is there an association between self-esteem and
eating behaviors among collegiate female swimmers?
(Fey, 1998)
 Seeks to make comparisons between or within
groups of interest
◦ Often associated with experimental research
 Is there a difference between the control group and the
experimental group?
◦ Comparison of one group to another on the basis of
existing characteristics

 Example
◦ Does participation in Special Olympics affect the
self-esteem of adults with mental retardation?
(Major, 1998)
 Personal Exp.
 Practical Exp.
 RoL
 Social Issue
 GD
 Consultation with the Experts
 Interest
◦ Most important
 Significance
◦ Theoretical value
◦ Practical value
◦ Timeliness
◦ External review
 Manageability
◦ Expertise, time, resources
◦ Free from personal bias
 The process of refining the question or idea
into a problem and making it sufficiently
specific so that it is amenable to investigation
 This process should lead to the development

of a “statement of the problem” that is clear,


concise, and definitive
 A very specific statement which clearly
identifies the problem being studied; will
usually identify the key variables as well as give
some information about the scope of the study
 May be in either question or declarative form
 May include inherent sub-problems, if
appropriate
 Formulation of problem statement takes place

after an initial review of related literature and


the distillation process
 “The problem of this study was to …”
 “This study was concerned with …”
 “This study is designed to …”
 “The purpose of this investigation is to …”
1.The problem was to investigate the effects of exercise
on blood lipids among college-age females.
2.This study was designed to determine the relationship
between stability performance and physical growth
characteristics of preschool children.
3.The present study was designed to identify those
characteristics which differentiate between students
who drink sprite and those that do not.
4.The problem of the study was to determine is there is
a relationship between self-efficacy and self-reported
alcohol usage among middle-aged adult females.
Do’s and Don’t in Selecting the Problem
The research problem might be classified as simple or
complex.
Simple problems are those that are easy to understand and
the components and identified relationships are linear,
e.g., the relationship between cigarette smoking and
lung cancer.
Complex problems on the other hand, deal with the
interrelationship between multiple variables,
e.g., the impact of social networking sites like
Facebook and online shopping sites like Flipkart on consumer
purchase behaviour in shops and markets.
The impact might also further differ in terms of males and
females. Other influencing factors on the buying behaviour
could be a person’s lifestyle, age and education.
Complex problems such as these deal with multiple variables.
Thus, they require a model or framework to be developed to
define the research approach.
Research Question should be focused.
Unfocused: What is the effect on the environment from
global warming?

Focused: How is glacial melting affecting penguins in


Antartica?

Eg:
specific cause (glacial melting)
specific place (Antarctica)
specific group affected (Penguin)
Activity

Select a research problem, list the variables in


the problem and formulate a theoretical
framework to demonstrate the link between
the variables under study.
 Delimitations define the scope of the study. That
is, they set the boundaries of the study
 Normally under control of the researcher
 Examples include

◦ number and kinds of subjects


◦ treatment conditions
◦ tests, measures, instruments used
◦ type of equipment
◦ location, environmental setting
◦ type of training (time and duration)
 Limitations are very similar to delimitations, but
they tend to focus on potential weaknesses of
the study
 Examples include

◦ sampling problems (representativeness of subjects)


◦ uncontrolled factors and extraneous variables
◦ faulty research design and techniques
◦ reliability and validity of measuring instruments
◦ compromises to internal/external validity
 Possible shortcomings of the study . . .
usually cannot be controlled by the
researcher
◦ the researcher will, of course, try to eliminate
extremely serious weaknesses before the study is
commenced
 May be a result of assumptions not being met
 No study is perfect; the researcher recognizes

the weaknesses
In other words, limitations are what the
researcher cannot do (elements outside of their
control) and delimitations are what the
researcher will not do (elements outside of the
boundaries they have set).
Literature review

24
A systematic analysis and interpretation of
available information about a topic of study

It is an excellent opportunity to develop


professional confidence in the field of study

25
 To know more about a problem
 To avoid duplication of information
 To learn the gaps in the arena of study
 To learn various methods that others

used
 To forecast challenges that might be

faced in the conduct of study

26
 Library (published information)
 Electronic search engines (internet)
 Gray literature (Unpublished ones)

27
Three steps in writing review of literature

 Consider your analysis of the problem


 Organize notes based on factors
 Decide the order (you have three options)

◦ From broader to specific


◦ From global to local
◦ From past to present

28
This is distortion of available information to
reflect unreal situation

Common types of bias in literature


 Playing down controversies & differences
 Restricting to supporting references
 Drawing far-fetched conclusions from

small studies
 Using rhetoric rather than reasoning

29
 Search widely
 Evaluate relevance of an information to your

study
 Include information directly relevant to your

study
 Mention sources for all bold statements
 Write a coherent discussion in your own

words

30
Literature review should be
 Adequate
 Relevant and
 Critical

It must answer the questions:


 How much is known about a topic?
 What is not known about the topic?
 What should be done on what is lacking?

31
Formulation of research
objectives

32
1. Estimation objectives
◦ Estimates magnitude of an event
2. Association objectives
◦ Analyses factors associated with an event
3. Evaluation objectives
◦ Evaluates associations

33
 General objective:
◦ Summarizes what is to be achieved by the study
◦ Should be clearly related to the statement of the
problem
For example, your general objective could be,
"Determine how work environment affects
performance."

34
 Specific objectives
◦ Logically connected parts of the general objective
◦ Focus the study on the essentials
◦ Direct the design of investigation
◦ Orient collection, analysis & interpretation of data

For example , specific objectives might be,


"Determine whether sunlight improves
performance," and "Measure how performance
changes when work environment changes”.
It is because research objectives:

 Focus the study


 Avoids unnecessary information
 Facilitates organizing of the study

36
A research study designed to assess the
accessibility and acceptability of the Voluntary
Counselling and Testing (VCT) Services for HIV
infection in Mumbai had the following general
and specific objectives:

 General objective: To identify factors that affects


the acceptability of VCT services and to assess
community attitudes towards comprehensive
care and support for people living with
HIV/AIDS.
 Specific objectives:
To assess the knowledge, attitude and
practice of the community towards HIV/AIDS
and VCT services.
To identify barriers and concerns related to
VCT and its uptake.
To assess the awareness and perception of
the study community regarding
comprehensive care and support for people
living with HIV/AIDS.
We do have three possible ways:

As positive statements
As research questions
As a hypothesis

A hypothesis is a prediction of relationships


between one or more factors and the problem
under study that can be tested

39
Research objectives should be
 Focused, each covering a single point
 Ordered in a logical sequence
 Realistic and feasible to answer
 Operational using action-verbs
 Measurable in terms of outcomes at the

end

40
Action-verbs
To determine To compare To verify
To calculate To describe To asses
To explore To test To establish
To identify

Non-action verbs
To appreciate To understand To show
To share To believe to study

41
Objectives transform these questions
into behavioral aims by using action-
oriented words (verbs) such as
 'to find out',
 'to determine',
 'to ascertain' and
 'to examine‘,
 ‘to measure’,
 ‘to explore’.
 Examples:
◦ To describe the infant attachment patterns in
China
◦ To explore the perceptions of people on
Gender based violence in Zambia.
◦ To ascertain the impact of article reviews of
MA students’ ability to consume scientific
literature
◦ To explore the infant attachment patterns
existent in India
◦ To compare these attachment patterns to
other normative samples
◦ To examine gender differences in these
infant attachment patterns
Objectives are simply research questions paraphrased!!!!
Objectives must be SMART
Specific
Measurable
Achievable
Realistic / Relevant
Time-bound

44
Specific: Be specific about your desired outcomes. Your objectives
should be clearly written and leave no room for confusion. This can
help you keep them narrow and focused.

Measurable: Making your objectives measurable is essential to


achieving them. You can create metrics to measure your progress
toward achieving your objectives.

Achievable: Be sure to create objectives that you can realistically


achieve to help you avoid getting overwhelmed by unrealistic
expectations. Make sure you have the resources and budget to
accomplish your objectives.

Relevant: Make your objectives relevant to your research and your


overall goals. This can help you stay motivated and on track
throughout your research project.

Time-based: You can establish deadlines to help you keep your


research process on track. You can set a major deadline for your
entire project as well as smaller deadlines for each objective.
46
Formulating the Research Hypotheses
The problem identification process ends in the
hypotheses formulation stage. Any assumption
that the researcher makes on the probable
direction of the results that might be obtained on
completion of the research process is termed as a
hypothesis.

Kerlinger (1986) defines a hypothesis as


‘…a conjectural statement of the relationship
between two or more variables.’

According to Grinnell (1993), ‘A


hypotheses is written in such a way that it can be
proven or disproven by valid and reliable data—it
is in order to obtain these data that we perform
our study’.
While designing any hypotheses, there are a few criteria that the researcher
must fulfill. These are:

A hypothesis must be formulated in simple, clear, and declarative


form. A broad hypothesis might not be empirically testable. Thus, it might
be advisable to make the hypothesis unidimensional, and to be testing only
one relationship between only two variables at a time.
EX: Consumer liking for the electronic advertisement for the new diet
drink will have positive impact on brand awareness of the drink.
 High organizational commitment will lead to lower turnover
intention.
A hypothesis must be measurable and quantifiable.
A hypothesis is a conjectural statement based on the existing literature
and theories about the topic and not based on the gut feel of the
researcher.
The validation of the hypothesis would necessarily involve testing the
statistical significance of the hypothesized relation.
 A Hypothesis gives a definite point to the
investigation, and it guides the direction on the
study.
 Specifies the sources of data
 Determines the data needs
 Suggest which type of research is likely to be

most appropriate
 Determines the most appropriate technique of

analysis
 Contribute to the development of theory.
Types of Research Hypotheses
The formulated hypothesis could be of two types:
1. Descriptive hypothesis
2. Relational hypothesis

Descriptive hypothesis: This is simply a statement about the


magnitude, trend or behavior of a population under study. Based on
past records, the researcher makes some presumptions about the
variable under study.
For example:
• Students from the pure science background score 90–95 per cent on
a course on quantitative methods.
• The current advertisement for the diet drink will have a 20–25 per
cent recall rate.
• The literacy rate in the city of Indore is 100 per cent.
Relational hypothesis: These are the typical kind of hypotheses which state the
expected relationship between two variables. While stating the relation if the
researcher makes use of words such as increase, decrease, less than or more than,
the hypothesis is stated to be directional or one-tailed hypothesis.

For example,
• Higher the likeability of the advertisement, higher is the recall rate.
• Higher the work exhaustion experienced by the BPO professional, higher is the
turnover intention of the person.

However, sometimes the researcher might not have reasonable supportive


data to hypothesize the expected direction of the relationship. In this case he or she
would leave the hypothesis as non-directional or two-tailed.
For example,
• There is a relation between quality of working life and job satisfaction
experienced by employees.
• Ban on smoking has an impact on cigarette sales.
• Anxiety is related to performance.
Significance tests often use a significance
level of α=0.05, but in some cases it makes
sense to use a different significance level.
Changing α-alpha impacts the probabilities of
Type I and Type II errors. In some tests, one
kind of error has more serious consequences
than the other. We may want to choose different
values for α-alpha in those cases.
 Example 1: Employees at a health club do a daily
water quality test in the club's swimming pool. If
the level of contaminants are too high, then they
temporarily close the pool to perform a water
treatment.

 We can state the hypotheses for their test as


◦ H0​: The water quality is acceptable
◦ Ha​: The water quality is not acceptable.
a) The club closes the pool when it needs to be
closed.
b) The club closes the pool when it doesn't need
to be closed.
c) The club doesn't close the pool when it needs
to be closed.
 Answer : (B)The club closes the pool when it
doesn't need to be closed.

A Type I error is when we reject a true H0.


In this setting, if H0 is true, then the water
quality is acceptable, and the pool doesn't need
to be closed. A Type I error would occur if they
close the pool when the water quality is actually
acceptable.
a) The club closes the pool when it needs to be
closed.
b) The club closes the pool when it doesn't need
to be closed.
c) The club doesn't close the pool when it needs
to be closed.
Answer : (C) The club doesn't close the pool when
it needs to be closed.

A Type II error is when we fail to reject a


false H0​. In this setting, if H0​ is false, then the
water quality is not acceptable, and the pool
should be closed. A Type II error would occur if
they don't close the pool when the water quality
is not actually acceptable.
Example 2: Seth is starting his own food truck
business, and he's choosing cities where he'll
run his business. He wants to survey residents
and test whether or not the demand is high
enough to support his business before he
applies for the necessary permits to operate in a
given city. He'll only choose a city if there's
strong evidence that the demand there is high
enough.
 We can state the hypotheses for his test as

◦ H0​:The demand is not high enough vs.


◦ Ha​:The demand is high enough.
Q1: What would be the consequence of a Type I
error in this setting?

a) He doesn't choose a city where demand is actually


high enough.
b) He chooses a city where demand is actually high
enough.
c) He chooses a city where demand isn't actually high
enough.

Answer: ….......
Answer : (C) He chooses a city where demand isn't
actually high enough.

A Type I error is when we reject a true H0​.


In this setting, if H0 is true, then demand in the
city is not high enough, and Seth shouldn't
choose that city. A Type I error would occur if he
chooses a city where the demand is not actually
high enough.
Q2: What would be the consequence of a Type II
error in this setting?

a) He doesn't choose a city where demand is actually


high enough.
b) He chooses a city where demand is actually high
enough.
c) He chooses a city where demand isn't actually high
enough.

Answer: ….......
Answer : (a) He doesn't choose a city where
demand is actually high enough.

A Type II error is when we fail to reject a


false H0. In this setting, if H0 is false, then
demand in the city is high enough, and Seth
should choose that city. A Type II error would
occur if he doesn't choose a city where the
demand is actually high enough.
Thank You

You might also like