Quantitative and Qualitative Research
In the study of human behavior both quantitative and qualitative approaches are being
applied, often as complementary approaches to the same topic. In this topic we learn about
quantitative and qualitative approaches to scientific inquiry from which much of the knowledge
about human behavior is derived.
Quantitative Research
It studies human behavior and mental processes by seeking causal relationships among
variables, by gathering data and performing statistical analyses.
Research Problem or Hypothesis guides the research process to ensure that the
information will be accurate. The research process usually starts with an observation about a
particular behavior or event. Then search for search for scientific explanation to account for the
observation. Then hypothesis that usually involves theory, examine the propositions of the
theory with appropriate research design, sample, sampling technique and techniques to analyze
data.
DATA SELECTION in QUANTITATIVE RESEARCH
Method in selecting the sample is dependent on the purpose and nature of the study.
Sample determines the generalizability of the research findings.
SAMPLING
The PROCESS OF SELECTION of Units from a population of interest so that by studying
the sample may fairly generate results back to the population from which they were chosen.
• “A statistical sample is miniature picture of cross selection of the entire group or
aggregate from which the sample is taken”. (Young, 1992)
• “A sample, as the name implies, is a smaller representative of a large whole”. (Goode
and Hatt,1981)
• “It is a small piece of the population obtained by a probability process that mirrors
with known precision, the various patterns and sub-classes of population”.
(Blalock,1960)
Sampling Terminology
• POPULATION
It refers to the whole that include all observations or measurements of a given
characteristic.
Finite or Infinite
• FINITE
A finite population is one where all the members can be easily counted.
• INFINITE
An infinite population is one whose size is unlimited and cannot count easily.
• SAMPLE
A sample is any number of persons selected to represent the population according to
some rule of plan. Thus, a sample is a smaller representation of the population.
• SAMPLE SIZE
No. of selected individual for example, no. of students, families from whom you obtain
the require information
• SAMPLING STRATEGY
It refers to the techniques or procedures the researcher would adopt in selecting some
sampling units from which inferences about the population are drawn.
• SAMPLING UNIT
Each individual or case that becomes the basis for selecting a sample
• SAMPLING FRAME
The list of people from which the sample is taken. It should be comprehensive, complete
and up-to-date.
• PURPOSE OF SAMPLING
The objective of sampling is to derive the desired information about the population at
the minimum cost or with the maximum reliability.
The aims in selecting a sample are to achieve maximum precision in estimates within a
given sample size and to avoid bias in the selection of sample.
• BIASES IN SAMPLING
a) The researcher selects the sample by non random method and influenced by human
choice.
b) The researcher does not cover the sampling population accurately and completely
c) A section of a sample population is impossible to find or refuses to cooperate.
NON PROBABILITY SAMPLING
• Refers to sampling techniques for which a person’s likelihood of being selected for
membership in the sample is unknown.
Types of nonprobability samples
• Purposive Sample
A researcher selects participants from their sampling frame because they have
characteristics that the researcher desires. A researcher begins with specific characteristics in
mind that they wish to examine and then they seek out research participants who cover that full
range of characteristics.
• Quota sampling
A researcher selects participants from their sampling frame because they have
characteristics that the researcher desires. A researcher begins with specific characteristics in
mind that they wish to examine and then they seek out research participants who cover that full
range of characteristics.
• Snowball Sampling,
A researcher identifies one or two people they would like to include in their study but
then relies on those initial participants to help identify additional study participants.
The researcher’s sample builds and becomes larger as the study continues, much as a
snowball builds and becomes larger as it rolls through the snow.
• Snowball sampling is an especially useful strategy when a researcher wishes to study a
stigmatized group or behavior.
• Snowball sampling is sometimes referred to as chain referral sampling.
• One research participant refers another, and that person refers another, and that person
refers another—thus a chain of potential participants is identified.
• Convenience Sampling
Nonprobability sampling strategy that is employed by both qualitative and quantitative
researchers.
To draw a convenience sample, a researcher simply collects data from people or other
relevant elements that they can access conveniently.
Also known as availability sampling, convenience sampling is the most useful in
exploratory research or student projects where probability sampling is too costly or difficult.
Stratified Sampling-Participants are deliberately selected from a variety of level (strata)
or subgroups within the population
Random Sampling- Every member has an equal chance of being chosen to participate in
the study.
TOOLS FOR DATA ANALYSIS For Quantitative Research
Descriptive Statistics- use to describe basic features of the data in the study.
Inferential Statistics- use to draw inferences or conclusion about associations between
variables.
a. Correlation use to measure the relationship between two variables.
Pearson Product Correlation- most commonly used in quantitative technique
t-test- compare means among two groups
Analysis of Variance (ANOVA)- use to compare the means among three or more groups
Reliability- extent to which the research study yields consistent results
Validity- measures the research method design.
a. Internal Validity- measure how well the study is conducted
b. External Validity- degree to which the research results are applicable or can be
generalized to other situations or people.
Qualitative Research
Does not rely on numerical measurements, and depends instead on research that
produces descriptive data.
It is multi method in focus, involving an interpretive, naturalistic approach to its
subject matter.
It seeks to understand action and experience as a whole and in context
Qualitative research perceives the role of the investigator as integral to the data, not in
the traditional view of an objective scientist looking through a telescope.
Qualitative Data Collection
In psychology, different types of data or information are collected. Some of these types are:
i) Demographic Information: This information generally includes personal information like
name, age, gender, birth order, number of siblings, education, occupation, marital status,
number of children, locality of residence, caste, religion, parental education, occupation, and
family income, etc.
ii) Physical Information: This category includes information about ecological conditions
(hilly/desert/forest), mode of economy, housing conditions, size of rooms, facilities available at
home, in the neighborhood, in the school, mode of transportation, etc.
iii) Physiological Data: In some studies physical, physiological and psychological data are
collected about height, weight, heart rate, level of fatigue, Galvanic Skin Resistance (GSR),
electrical activity of the brain measured by Electro-encephalograph (EEG), blood oxygen levels,
reaction time, duration of sleep, blood pressure, pattern of dream, amount of salivation,
running and jumping rates (in case of animal studies), etc., are collected.
iv) Psychological Information: Psychological information collected, may relate to such areas as
intelligence, personality, interest, values, creativity, emotions, motivation, psychological
disorders, illusions, delusions, hallucinations, perceptual judgment, thought processes,
consciousness, subjective experiences, etc.
Lincoln and Guba (Stahl & King, 2020) Trustworthiness refers primarily to credibility and to
transferability.
Credibility describes the appropriateness of the methods and subjects to the goals.
Transferability indicates the contextual limitations of the data.
Dependability pertains to the quality of the conclusions and data evaluations that
framed them,
Confirmability indicates the ability of an outside reviewer to audit the procedures and
analysis and reach the same conclusions
INTERVIEWS
Interviews involve interactions between the interviewer(s) and the respondent(s) based
on interview questions. Individual, or face-to-face, interviews should be distinguished from
focus group discussions. The interview questions are written down in an interview guide for
individual interviews or a questioning route for focus group discussions, with questions
focusing on the phenomenon under study.
Qualitative researchers usually employ “semi-structured” interviews which involve a number
of open-ended questions based on the topic areas that the researcher wants to cover. Can be
completely structured or unstructured.
The sequence of the questions is pre-determined. In individual interviews, the sequence
depends on the respondents and how the interviews unfold. During the interview, as the
conversation evolves, you go back and forth through the sequence of questions. It should be
a dialogue, not a strict question–answer interview.
Working with an interview guide or questioning route enables you to collect information
on specific topics from all participants. You are in control in the sense that you give direction
to the interview, while the participants are in control of their answers. However, you need to
be open-minded to recognize that some relevant topics for participants may not have been
covered in your interview guide or questioning route, and need to be added. During the
data collection process, you develop the interview guide or questioning route further and
revise it based on the analysis.
The interview guide and questioning route might include open and general as well as
subordinate or detailed questions, probes and prompts. Probes are exploratory questions,
for example, ‘Can you tell me more about this?’ or ‘Then what happened?’ Prompts are
words and signs to encourage participants to tell more. Examples of stimulating prompts are
eye contact, leaning forward and open body language.
a. face-to-face interview is an individual interview, that is, a conversation between
participant and interviewer. Interviews can focus on past or present situations, and on
personal issues. Most qualitative studies start with open interviews to get a broad
‘picture’ of what is going on. You should not provide a great deal of guidance and avoid
influencing the answers to fit ‘your’ point of view, as you want to obtain the participant’s
own experiences, perceptions, thoughts, and feelings. You should encourage the
participants to speak freely.
A face-to-face or individual interview might last between 30 and 90 min.
To prepare an interview guide to enhance that a set of topics will be covered by every
participant, you might use a framework for constructing a semi-structured interview
guide:
1. identify the prerequisites to use a semi-structured interview and evaluate if a
semi-structured interview is the appropriate data collection method;
2. retrieve and utilize previous knowledge to gain a comprehensive and adequate
understanding of the phenomenon under study
3. formulate a preliminary interview guide by operationalizing the previous
knowledge
4. pilot-test the preliminary interview guide to confirm the coverage and relevance
of the content and to identify the need for reformulation of questions
5. complete the interview guide to collect rich data with a clear and logical guide.
Focus Groups
In a way focus groups resemble interviews but focus group transcripts can be analyzed
so as to explore the ways in which the participants interact with each other and
influence each other’s expressed ideas, which obviously cannot happen with one-to-one
interview material.
An important preliminary for conducting focus groups is laying down the “ground rules”.
Acting as facilitator of a focus group, the researcher must allow all participants to
express themselves and must cope with the added problem of trying to prevent more
than one person speaking at a time, in order to permit identification of the speakers for
the purposes of transcription and analysis
A focus group discussion is a way to gather together people to discuss a specific topic of
interest. The people participating in the focus group discussion share certain
characteristics, e.g., professional background, or share similar experiences, e.g., having
diabetes. You use their interaction to collect the information you need on a particular
topic. To what depth of information the discussion goes depends on the extent to which
focus group participants can stimulate each other in discussing and sharing their views
and experiences. Focus group participants respond to you and to each other. Focus
group discussions are often used to explore patients’ experiences of their condition and
interactions with health professionals, to evaluate programmes and treatment, to gain
an understanding of health professionals’ roles and identities, to examine the perception
of professional education, or to obtain perspectives on primary care issues. A focus
group discussion usually lasts 90–120 mins.
You might use guidelines for developing a questioning route:
1. brainstorm about possible topics you want to cover
2. sequence the questioning: arrange general questions first, and then, more specific
questions, and ask positive questions before negative questions
3. phrase the questions: use open-ended questions, ask participants to think back and
reflect on their personal experiences, avoid asking ‘why’ questions, keep questions
simple and make your questions sound conversational, be careful about giving examples
4. estimate the time for each question and consider: the complexity of the question, the
category of the question, level of participant’s expertise, the size of the focus group
discussion, and the amount of discussion you want related to the question
5. obtain feedback from others (peers)
6. revise the questions based on the feedback; and
7. test the questions by doing a mock focus group discussion. All questions need to
provide an answer to the phenomenon under study.
You need to be prepared to manage difficulties as they arise, for example, dominant
participants during the discussion, little or no interaction and discussion between
participants, participants who have difficulties sharing their real feelings about sensitive
topics with others, and participants who behave differently when they are observed.
How should I compose a focus group and how many participants are needed?
The purpose of the focus group discussion determines the composition. Smaller groups
might be more suitable for complex (and sometimes controversial) topics. Also, smaller
focus groups give the participants more time to voice their views and provide more
detailed information, while participants in larger focus groups might generate greater
variety of information. In composing a smaller or larger focus group, you need to ensure
that the participants are likely to have different viewpoints that stimulate the discussion.
For example, if you want to discuss the management of obesity in a primary care district,
you might want to have a group composed of professionals who work with these
patients but also have a variety of backgrounds, e.g. GPs, community nurses, practice
nurses in general practice, school nurses, midwives or dieticians.
Focus groups generally consist of 6–12 participants. Careful time management is
important, since you have to determine how much time you want to devote to
answering each question, and how much time is available for each individual participant.
For example, if you have planned a focus group discussion lasting 90 min. with eight
participants, you might need 15 min. for the introduction and the concluding summary.
This means you have 75 min. for asking questions, and if you have four questions, this
allows a total of 18 min. of speaking time for each question. If all eight respondents
participate in the discussion, this boils down to about two minutes of speaking time per
respondent per question.
Observation
Observation is a technique that can be used when data cannot be collected through
other means, or those collected through other means are of limited value or are difficult
to validate.
Observation can also produce data for verifying or nullifying information provided in
face-to-face encounters
What is important is to immerse yourself in the research setting, to enable you to study
it from the inside. There are four types of researcher involvement in observations, and in
your qualitative study, you may apply all four. In the first type, as ‘complete participant’,
you become part of the setting and play an insider role, just as you do in your own work
setting. This role might be appropriate when studying persons who are difficult to
access. The second type is ‘active participation’. You have gained access to a particular
setting and observed the group under study. You can move around at will and can
observe in detail and depth and in different situations. The third role is ‘moderate
participation’. You do not actually work in the setting you wish to study but are located
there as a researcher. You might adopt this role when you are not affiliated to the care
setting you wish to study. The fourth role is that of the ‘complete observer’, in which you
merely observe (bystander role) and do not participate in the setting at all. However, you
cannot perform any observations without access to the care setting. Such access might
be easily obtained when you collect data by observations in your own primary care
setting. In some cases, you might observe other care settings, which are relevant to
primary care, for instance observing the discharge procedure for vulnerable elderly
people from hospital to primary care.
It is important to decide what to focus on in each individual observation. The focus of
observations is important because you can never observe everything, and you can only
observe each situation once. Your focus might differ between observations. Each
observation should provide you with answers regarding ‘Who do you observe?’, ‘What
do you observe’, ‘Where does the observation take place?’, ‘When does it take place?’,
‘How does it happen?’, and ‘Why does it happen as it happens?’
Observations are not static but proceed in three stages: descriptive, focused, and
selective. Descriptive means that you observe, on the basis of general questions,
everything that goes on in the setting. Focused observation means that you observe
certain situations for some time, with some areas becoming more prominent. Selective
means that you observe highly specific issues only.
You take field notes from all these observations and add your own reflections on the
situations you observed. You jot down words, whole sentences or parts of situations,
and your reflections on a piece of paper. After the observations, the field notes need to
be worked out and transcribed immediately to be able to include detailed descriptions.
Use of new media to collect qualitative data
Qualitative research moves from ‘virtual’ to ‘digital’. Virtual means those approaches
that import traditional data collection methods into the online environment and digital means
those approaches take advantage of the unique characteristics and capabilities of the Internet
for research. New media can also be applied.
New media are increasingly used for collecting qualitative data, for example, through
online observations, online interviews and focus group discussions, and in analysis of online
sources. Data can be collected synchronously or asynchronously, with text messaging, video
conferences, video calls or immersive virtual worlds or games, etcetera.
Qualitative DATA ANALYSIS and PARTICIPANT Selection
Theoretical sampling- sampling is directed towards making possible generalizations about
theoretical propositions and new cases are selected for their potential in extending or testing
emergent understanding.
Convenience sampling- Here researchers select those who are available and likely to
participate, perhaps over a specific period.
Typical case sampling -decide on the characteristics of “typical” individuals and select the
sample to fit the characteristics of typical cases in selecting people for focus groups etc.
Critical case sampling- Researchers choose cases that they believe to be especially important
because of the position they hold (e.g. because of their particular place within an organization)
or because they are especially well able to articulate a view (e.g. spokesperson for a medical
charity).
Maximum variation sampling -Here researchers identify cases with different characteristics to
maximize diversity in the sample, usually to get the widest range of views possible. This is best
done using quota methods (see “strategy determined in advance”) and iteratively (e.g. refine
your quotas based on the emergent analysis – you may decide you need to investigate one
group in more depth). Any common themes that emerge can capture “core” experiences or
views.
Intensity sampling -This is where researchers sample the same characteristics over and over. It
tends to be used in interpretive phenomenological analysis.
Snowball sampling -Relies on referrals, one participant recruits others. This can help
researchers to capitalize on informal networks that might otherwise be difficult to access (e.g.
sex workers, drug users, victims of domestic violence etc).
When Do we stop Collecting DATA?
Data Saturation
In qualitative research refers to the point where collecting more data yields no new
information or insights relevant to the research question
When designing a qualitative sampling plan, we (the authors) work with estimates. We
estimate that ethnographic research should require 25–50 interviews and observations,
including about four-to-six focus group discussions, while phenomenological studies require
fewer than 10 interviews, grounded theory studies 20–30 interviews and content analysis 15–20
interviews or three-to-four focus group discussions. However, these numbers are very tentative
and should be very carefully considered before using them. Furthermore, qualitative designs do
not always mean small sample numbers. Bigger sample sizes might occur, for example, in
content analysis, employing rapid qualitative approaches, and in large or longitudinal qualitative
studies.
DATA ANALYSIS IN QUALITATIVE RESEARCH
Thematic ANALYSIS
Method that involves reading through a set of data to identify patterns or
themes that come up repeatedly such as in transcripts from FGD or interviews.
VIRGINIA BRAUN & VICTORIA CLARKE Six STEPs APPROACH
1. Become Familiar with the Data
2. Generate initial Codes
3. Search for themes
4. Review Themes
5. Define and Name themes
6. Write up
****Detailed discussion on Data Analysis using TA and IPA will be discussed next time
Summary of the Difference between Qualitative and Quantitative Research
Qualitative Research Quantitative Research
tends to focus on how people or groups tends to focus on ways of describing
of people can have (somewhat) different and understanding reality by the
ways of looking at reality (usually social discovery of general “laws”
or psychological reality)
takes account of complexity by takes account of complexity by precise
incorporating the real-world context – definition of the focus of interest and
can take different perspectives on board techniques that mean that external
“noise” can be discounted
studies behavior in natural settings or involves manipulation of some variables
uses people’s accounts as data; usually (independent variables) while other
no manipulation of variables variables (which would be considered to
be extraneous and confounding
variables) are held constant
focuses on reports of experience or on uses statistical techniques that allow us
data which cannot be adequately to talk about how likely it is that
expressed numerically something is “true” for a given
population in an objective or
measurable sense
focuses on description and focuses on cause & effect - e.g. uses
interpretation and might lead to experiment to test (try to disprove) an
development of new concepts or theory, hypothesis
or to an evaluation of an organizational
process
