1

Research designs

Generally speaking, there three approaches to research; quantitative, qualitative

and mixed methods. Any research design we are going to examine here will fall
under any of the three approaches.

Advantages of quantitative research

Quantitative methods, by definition, are those which use numbers. The main
advantages of quantitative measurement are as follows:
 High reliability and validity due to numerical data, ability to generalize
results to a larger population by using large sample sizes, reduced
researcher bias .
 There are well-established statistical methods for analyzing the data. The
data can be easily summarized, which facilitates communication of the
findings.
 Quantitative measurements facilitate comparison. They allow researchers to
get the reactions of many people to specific stimuli and to compare
responses across individuals.
 Quantitative methods fit in well with hypothetico-deductive approaches.
Hypothesized relationships between variables can be specified using a
mathematical model, and the methods of statistical inference can be used to
see how well the data fit the predictions.
Advantages of using qualitative methods
 They avoid the simplifications imposed by quantification and gives the
researcher the ability to gain deep insights into human experiences,
behaviors, and motivations by providing rich, detailed data through open-
ended questions.
 2

 They allow the researcher to address research questions that do not easily
lend themselves to quantification, such as the nature of individual
experiences of a psychological condition (e.g., eating disorders) or event
(e.g., being a victim of crime).
 The raw data are usually vivid and easy to grasp: good qualitative research
reports make the participants come alive for the reader. In general, the
reports of qualitative studies are often more readable than those of
quantitative studies
 Qualitative methods are good for hypothesis generation, and for exploratory,
discovery-oriented research. They permit a more flexible approach,
allowing the researcher to modify his or her protocol in mid-stream. The
data collection is not constrained by pre-existing hypotheses.
 Qualitative self-report methods usually give more freedom to the participant
than structured quantitative methods. For example, open-ended questions
give interviewees a chance to respond in their own words and in their own
way.
Quantitative research designs
Quantitative designs can be grouped under experimental and non-experimental
designs
Experimental designs
Experimental designs are classified into randomized and non-randomized (quasi
experimental) designs, according to whether or not there is random assignment to
experimental conditions. Experimental designs are of particular interest to clinical
psychologists because therapeutic work itself can be thought of as an experimental
intervention. The therapist considers a problematic situation in the client’s life, forms
a hypothesis about what is causing it and what might be done to improve it, attempts
to change something about it, and then observes the results. Here the tentative
 3

connotation of experiment is apt: if the intervention does not work, the therapist. then
repeats the cycle by reformulating the problem, trying something else and once more
observing the results. This experimental approach to therapeutic work lies at the core
of the applied scientist model.
True experimental research (Randomized Control Trials)
Randomized controlled trial (RCT) is a type of scientific experiment where
participants are randomly assigned to different groups, usually an experimental group
receiving a new treatment and a control group receiving a standard treatment or
placebo, allowing researchers to compare the effects of the intervention with a
reliable baseline and minimize bias in the results; considered the gold standard for
evaluating the effectiveness of a medical treatment or intervention. The great
advantages of randomization are that it reduces the likelihood of selection bias as a
threat to internal validity and it allows the use of the statistical theory of error.
Randomized controlled trials (RCT) are prospective studies that measure the
effectiveness of a new intervention or treatment. Although no study is likely on its
own to prove causality, randomization reduces bias and provides a rigorous tool to
examine cause-effect relationships between an intervention and outcome. This is
because the act of randomization balances participant characteristics (both observed
and unobserved) between the groups allowing attribution of any differences in
outcome to the study intervention. This is not possible with any other study design.
Quasi-experimental design (non-randomized trials)

Similar to a typical experiment, a quasi-experiment does not randomly place

individuals in experimental groups. This lends support to studies where psychologists
may be more interested in an independent variable that cannot be a random variable,
such as a participant's intrinsic quality. For instance, since identified mental health
qualities are not random and make it impossible to randomly assign people to
 4

research groups, you may utilize a quasi-experiment to examine participants who

exhibit these traits.
Non-experimental research designs
Non-experimental designs can be classified, according to their aims, into descriptive
and correlational designs. As it is obvious from their names, descriptive designs
usually aim simply to describe, whereas correlational designs aim to examine
associations in order to make predictions or explore causal linkages.
Descriptive Designs
Descriptive research design is a powerful tool used by scientists and researchers to
gather information about a particular group or phenomenon. This type of research
provides a detailed and accurate picture of the characteristics and behaviors of a
particular population or subject. By observing and collecting data on a given topic,
descriptive research helps researchers gain a deeper understanding of a specific issue
and provides valuable insights that can inform future studies. The descriptive research
design involves observing and collecting data on a given topic without attempting to
infer cause-and-effect relationships.
The goal of descriptive research is to provide a comprehensive and accurate picture of
the population or phenomenon being studied and to describe the relationships,
patterns, and trends that exist within the data.
Descriptive research methods can include surveys, observational studies, and case
studies, and the data collected can be qualitative or quantitative. Descriptive research
can be cross sectional. Examples of descriptive research
 Descriptive epidemiological research, which aims to document the incidence
and prevalence of specified psychological problems.
 Consumer satisfaction research, which assesses clients’ satisfaction with a
psychological service.
 5

 Phenomenological research, which aims to understand the nature and

defining features of a given type of experience
Quantitative descriptive studies report their results using descriptive statistics such as
percentage, mean, median, incidence, and prevalence. However, it is rare to have a
purely descriptive study, as researchers often want to examine the associations
between two or more variables of interest. For example, in a consumer satisfaction
study you may want to see whether there is an association between client satisfaction
and various client demographic characteristics, such as gender or ethnicity. This leads
on to the next type of study, the correlational design.
Correlational Design
Correlational studies aim to examine the relationship between two or more variables:
in technical language, to see whether they covary, correlate, or are associated with
each other. Such studies are also called passive observation or naturalistic studies, in
contrast to studies employing active methods of experimental manipulation. In
correlational studies, researchers measure a number of variables for each participant,
with the aim of studying the associations among these variables. A well-known
example of a correlational design is Brown and Harris’s (1978) study of the social
origins of depression, which looked at the association between women’s depression,
their experience of stressful life events, and vulnerability factors (such as low
intimacy with the husband and loss of the mother before the age of 11.
The major drawback of correlational studies is that they cannot be used to make
unequivocal causal inferences. The golden rule of research design is: correlation does
not equal causation. Correlations may strongly suggest causal influences, but they
cannot firmly establish them
Let us take a simplified example, derived from early formulations of client centered
theory (Rogers, 1957). Suppose that variable A represents therapist empathy and
variable B represents the client’s outcome at the end of therapy, and that research has
 6

established a significant positive correlation between therapist empathy and client

outcome.
Then a number of inferences about their causal relationships are possible, some of
which are depicted in the following ways:
1. First it may be that A causes B: higher therapist empathy brings about better client
outcomes.
2. On the other hand, it is also possible that B causes A: clients who are improving in
therapy may tend to generate more empathic responses from their therapists.
3. A very common problem is that A and B may both be caused by a third variable, C,
e.g., client psychological mindedness. It is plausible that clients who are more
psychologically minded could have better outcomes and also generate more empathy
in their therapists. Thus the apparent causal relationship between A and B might be
spurious: that is, entirely explained by the influence of the third variable, C. The
presence of such third variables which provide competing causal explanations
prevents the researcher from drawing accurate causal inferences and thus reduces the
study’s validity.
4. Yet another possibility is that A does not influence B directly, but only indirectly
via D. Variables such as D are known as mediator variables (Baron & Kenny, 1986):
they mediate (come in the middle of) the relationship between two other variables.
For example, higher therapist empathy could lead specifically to increased client self-
exploration, which could then lead to better client outcome. We would then say that
the causal relationship between empathy and outcome was mediated by client self-
exploration.
Longitudinal Designs
Longitudinal designs involve taking multiple measurements of each study participant
over time. Generally, the purpose of longitudinal studies is to follow a case or group
of cases over a period of time to gather normative data on growth, to plot trends, or to
 7

observe the effects of special factors. For example, a researcher may want to study the
development of more than one birth cohort (i.e., a group of individuals born in the
same calendar year or group of years) to determine whether personality features are
stable over time.
Meta-Analysis
A quantitative research technique called meta-analysis examines the outcomes of
previously published studies that addressed the same subject and compiles different
study findings into a comprehensive set of data. By scanning library databases for all
studies that have been published on a certain subject, psychologists may do a meta-
analysis and compile the findings into a comprehensive overview. Psychologists can
produce an easily available resource that offers a collective appraisal of previous and
present research by combining several linked research questions into a single research
paper. As a result, meta-analysis can result in suggestions for future studies that will
assist the field of psychology to improve.

QUALITATIVE DESIGNS
In qualitative methods, data is not collected and processed numerically but mostly in
words or literature. Qualitative research tries to investigate people’s comprehension of
their social reality. It is inspired by many philosophical tenets and seeks to inquire
about the diverse facets of human life, for example, culture, beliefs, morality, etc. It is
part of the curriculum in several disciplines such as the arts, psychology,
anthropology, and others. Some ways of collecting qualitative data include
observation (including participant observation), interviews, questionnaires,
documentary sources focus groups, artifacts, audio and visual materials, among
others. Qualitative researchers follow a more constructivist worldview and are
predominantly interested in collecting and analyzing narrative data using open-ended
(holistic) procedures.
 8

Case Studies
Case studies involve an in-depth examination of a single person or a few people. The
goal of the case study is to provide an accurate and complete description of the case.
The principal benefit of case studies is that they expand our knowledge about the
variations in human behavior. Although experimental researchers are typically
interested in overall trends in behavior, drawing sample-to-population inferences, and
generalizing to other samples, the focus of the case-study approach is on individuality
and describing the individual as comprehensively as possible. Case studies of
individual participants often include in-depth interviews with participants and
collaterals (e.g., friends, family members, colleagues), review of medical records,
observation, and excerpts from participants’ personal writings and diaries.
A case research for fashion clothing and textile could be in form of an in-depth
examination of a specific fashion brand, designer or textile company to gain insight
into their design process, marketing strategies and consumer behaviour.

Case studies have a practical function in that they can be immediately applicable to
the participant’s diagnosis or treatment.
According to Kazdin (1982), the major characteristics of case studies are the
following:
• They involve the intensive study of an individual, family, group, institution, or other
level that can be conceived of as a single unit.
• The information is highly detailed, comprehensive, and typically reported in
narrative form as opposed to the quantified scores on a dependent measure.
• They attempt to convey the nuances of the case, including specific contexts,
extraneous influences, and special idiosyncratic details.
• The information they examine may be retrospective or archival. Although case
studies lack experimental control, their naturalistic and uncontrolled methods have set
 9

them aside as a unique and valuable source of information that complements and
informs theory, research, and practice
Ethnography
An ethnography research design is a qualitative research method that involves
immersing oneself in a natural setting to deeply understand the behaviors, culture, and
social interactions of a particular group of people by utilizing techniques like
participant observation, interviews, and archival research, providing rich insights into
their everyday lives and perspectives within their context. Ethnographic research
methods involve the examination of cultural phenomena from the perspective of the
subjects under investigation. This method of social research places a particular
emphasis on participant observation, where researchers engage with the setting or
individuals being studied, documenting intricate patterns of social interaction and
analyzing the participants’ own interpretations of their behavior within their local
contexts. While ethnography originated in social and cultural anthropology in the
early twentieth century, its application has extended to various disciplines. Widely
adopted as a qualitative data collection strategy, ethnographic research design stands
out for its reliance on observing life as it naturally unfolds, dispensing with the
controlled environment of a laboratory. Ethnographic observation seeks to understand
societies and individuals through direct observation and interviews, providing
valuable insights into how they interact with their surroundings in their natural
environments. For example, an observational study of street style of people in a
particular culture and how they use fashion to express their identity.
Phenomenological research design
Phenomenological research is a qualitative research approach that aims to understand
the essence of a phenomenon by exploring the lived experiences of individuals who
have directly experienced it, focusing on their perceptions, feelings, and meanings
attached to that experience, rather than relying on external interpretations or
 10

assumptions from the researcher; essentially, it seeks to describe the "universal"

nature of a phenomenon through in-depth analysis of participants' subjective
perspectives.
Grounded theory
Grounded theory research is a qualitative research method where a theory is
developed based on data collected and analyzed, meaning the theory emerges directly
from the data rather than being pre-defined before research begins; it is considered
"grounded" because the theory is rooted in the collected information

Features of GT
 Data collection and analysis occur simultaneously.

 Categories and analytic codes developed from data. Pre-existing

conceptualisations not to be used—this is known as theoretical sensitivity
(see below).

 Theoretical sampling used to refine categories.

 Abstract categories constructed inductively.

 Social processes discovered in the data.

 Analytical memos used between coding and writing.

 Categories integrated into a theoretical framework.

Mixed method designs

Sequential explanatory
This design consists of two distinct phases: quantitative followed by qualitative
(Creswell et al. 2003). The qualitative (text) data are collected and analyzed second in
 11

the sequence and help explain, or elaborate on, the quantitative results obtained in the
first phase
Sequential exploratory design
Exploratory sequential mixed methods design is characterized by an initial qualitative
phase of data collection and analysis, followed by a phase of quantitative data
collection and analysis, with a final phase of integration or linking of data from the
two separate strands of data.
Convergent parallel design
This is a one phase project in which quantitative and qualitative data are collected at
the same time and analyzed separately. After both analyses are complete, compare
your results to draw overall conclusions.

Threats to validity of Research Design

Threats to validity are specific reasons why an inference about a study is wrong.
They can help us anticipate problems in the design of our own research. The best
way to address threats to validity is to change the design of our research.
Understanding threats to validity also helps you critique research done by others.
Internal validity refers specifically to whether an experimental treatment/condition
makes a difference or not, and whether there is sufficient evidence to support the
claim.
External validity refers to the generalizibility of the treatment/condition outcomes.
INTERNAL VALIDITY
1. History and maturation: - changes or events that affect data; changes over time. The
specific events which occur between the first and second measurement. Maturation--
the processes within subjects which act as a function of the passage of time. i.e. if the
 12

project lasts a few years, most participants may improve their performance regardless
of treatment
2. Observer effects: - time spent observing, selection of informants (for maximum
variability), adequacy of probing overtime, adequacy of uncovering real relationships
and views, etc. affect accuracy of results
3. Selection and regression: - when selection of subjects is necessitated, does
selection adequately represent the variation in the population or does it represent a
regression toward the mean
4. Mortality: - loss of subjects can affect results
EXTERNAL VALIDITY
1. Selection effects: - are selection procedures delineated? can they be replicated?
2. Setting effects: - individual researchers affect settings differently; groups subjected
to a lot of research are affected differently from those not subjected to research
3. History effects: - different groups may have been affected by significant and
different unique historical events
4. Construct effects: - construct validity:- definitions and meanings of terms and
constructs can vary across time, settings, and populations - explanations for observed
phenomena can vary between groups
5. Reactive or interaction effect of testing--a pretest might increase or decrease a
subject's sensitivity or responsiveness to the experimental variable. Indeed, the effect
of pretest to subsequent tests has been empirically substantiated
Population and Sample
Population: A research population is a large collection of individuals or objects to
which the researcher wants the results of the study to apply. Population is the main
focus of a research question. A research population is also known as a well-defined
collection of individuals or objects known to have similar characteristics. All
individuals or objects within a certain population usually have a common, binding
 13

characteristic or trait. Population can also be defined as all individual that meet a set
of specification or a specific criterion. All researches are done for the benefit of
population.
Types of Population
i) The Target Population is also known as the theoretical population and refers to the
entire group of individuals or objects to which a researcher is interested to generalize
the conclusions. This type of population usually has varying degree of characteristics.
ii) The Accessible Population is also known as the study population. It is the
population to which a researcher can apply the conclusions of the study. This
population is a subset of the target population.
Sample: A sample is simply a subset or subgroup of population (Frey, Carl, & Gary,
2000).The concept of sample arises from the inability of the researchers to test all the
individuals in a given population. Sampling is the process of selecting some
individuals from the accessible population, in a way that these individuals represent
whole accessible population. The sample should be representative in a sense that each
individual should represent the characteristics of the whole population (Lohr, 1999).
The main function of the sample is to allow the researchers to conduct the study to
individuals from the population so that the results of their study can be used to derive
conclusions that will apply to the entire population.
Points to consider when selected a sample
 Sample size
 Sample representativeness
 Accessibility

Sampling Techniques
Generally, researchers use two major sampling techniques: probability sampling and
non-probability sampling.
 14

Probability sampling
It is a process that utilizes some form of random selection. In probability sampling,
each individual in chosen with a known probability. This type of sampling is also
known as random sampling or representative sampling; and depends on objective
judgment. Various types of probability are as under:
Simple Random sampling: In random sampling each member of the population has
an equal chance of being selected as subject. Each member is selected independently
of the other member of population. Many methods are used to proceed with random
sampling. In a commonly used method each member of the population is assigned a
unique number. All assigned numbers are placed in bowl and mixed thoroughly. The
researcher, then blind-folds and picks numbered tags from the bowl. All the numbers
picked are the subjects of the study. Another method is to use computer for random
selection from the population. For smaller population first method is useful and for
larger population computer-aided method is preferred.
Advantages of Simple Random Sampling
It is an easy way of selecting a sample from a given population. This method is free
from personal bias. As each member of the population is given equal opportunities of
being selected so it a fair way and one can get representative sample.
Disadvantages of Simple Random Sampling
One of the most obvious limitations of random sampling method is its nee of a
complete list of all members of the population. For larger population, usually this list
is not available. In such case, it is better to use other sampling techniques.
Systematic Random Sampling
In systematic random sampling, the researcher first randomly picks the first item or
the subject from the population. Then he selects each nth subject from the list. The
procedure involved in this sampling is easy and can be done manually. The sample
drawn using this procedure is representative unless certain characteristics of the
 15

population are repeated for every nth member, which is highly risky. Suppose a
researcher has a population of 100 individuals and he needs 12 subjects. He first picks
his starting number 7. He then picks his interval 8. The members of his sample will be
individual 7, 15, 23, 31, 39, 47, 55, 63, 71, 79, 87, and 95
Stratified Random Sampling
In this type of sampling, the whole population is divided into disjoint subgroups.
These subgroups are called stratum. From each stratum a sample of pre-specified size
is drawn independently in different strata, using simple random sampling. The
collection of these samples constitutes a stratified sample.
Advantages: This type of sampling is appropriate when the population has diversified
social or ethnic subgroups.
Cluster Sampling
It is a simple random sample in which each sampling unit is a collection or cluster, or
elements. For example, a researcher who wants to study students may first sample
groups or cluster of students such as classes, and then, select the sample of students
from among the clusters.
Non-Probability Sampling techniques
This technique depends on subjective judgment. It is a process where probabilities
cannot be assigned to the individuals objectively. It means that in this technique
samples are gathered in a way does not give all individuals in the population equal
chances of being selected. Choose these methods could result in biased data or a
limited ability to make general inferences based on the findings. But there are also
many situations in which choosing this kind of sampling techniques is the best choice
for a particular research question or the stage of research. There are four kinds of non-
probability sampling techniques are;
Convenience Sampling: In this technique a researcher relies on available subjects,
such as stopping peoples in the markets or on street corners as they pass by. This
 16

method is extremely risky and does not allow the researcher to have any control over
the representativeness of the sample. It is useful when the researcher wants to know
the opinion of the masses on a current issue; or the characteristics of people passing
by on streets at a certain point of time; or if time and resources are limited in such a
way that the research would not be possible otherwise. What may be the reason for
selecting convenience samples, it is not possible to use the results from a convenience
sampling to generalize to a wider population.
Purposive or Judgmental Sampling: In this technique a sample is selected on the
bases of the knowledge of population and the purpose of the study. For example,
when an educational psychologist wants to study the emotional and psychological
effects of corporal punishment, he will create a sample that will include only those
students who ever had received corporal punishment. In this case, the researcher used
purposive sample because those being selected fit a specific purpose or description
that was necessary to conduct the research.
Snowball Sample: This type of sampling is appropriate when the members of the
population are difficult to locate, such as homeless industry workers, undocumented
immigrants etc. a snowball sample is one in which the researcher collects data on a
few members of the target population he or she can locate, then asks to locate those
individuals to provide information needed to locate other members of that population
whom they know.
Quota Sample: Quota sampling is a non-probability sampling method where a
researcher divides the population into subgroups based on specific characteristics
(like age, gender, or income) and then selects a predetermined number of participants
from each subgroup, ensuring the sample reflects the proportions of those
characteristics in the overall population, even if the selection within each group is not
random; essentially, it aims to create a representative sample by filling "quotas"
within each subgroup.
 17

Tools for data collection in quantitative research

Surveys and Questionnaires: Questionnaires can be developed and administered
virtually such as Online surveys: Google forms, survey Monkeys and typeform. It can
be administered physically or through phone calls. They are commonly used to gather
data from large sample sizes on opinions, behaviors, and demographics through a
series of structured questions.
Standardized tests: Standardized tests such as personality tests, achievement test,
aptitude tests, interest inventory, attitude scales etc.
Structured Interviews: Interviews with a set list of questions to ensure consistency
in data collection across respondents.
Observation: Systematic recording of observable behaviors or events using
predetermined criteria.
Experiments: Laboratory experiments and field experiments
Secondary sources: Existing datasets and documents
Tools of data collection for qualitative designs
Interviews
One-on-one interviews are one of the most commonly used data collection methods in
qualitative research because they allow you to collect highly personalized information
directly from the source. Interviews explore participants' opinions, motivations,
beliefs, and experiences and are particularly beneficial in gathering data on sensitive
topics because respondents are more likely to open up in a one-on-one setting than in
a group environment.
Observation
Observation is one of the ultimate data collection tools in qualitative research for
gathering information through subjective methods. A technique used frequently by
modern-day marketers, qualitative observation is also favored by psychologists,
sociologists, behavior specialists, and product developers.
 18

The primary purpose is to gather information that cannot be measured or easily

quantified. It involves virtually no cognitive input from the participants themselves.
Researchers simply observe subjects and their reactions during the course of their
regular routines and take detailed field notes from which to draw information.
Naturalistic observation involves observing organisms or phenomena in their natural
settings. For example, a researcher who wants to examine the socialization skills of
children may observe them while they are at a school playground, and then record all
instances of effective or ineffective social behavior. The primary advantage of the
naturalistic observation approach is that it takes place in a natural setting, where the
participants do not realize that they are being observed. Consequently, the behaviors
that it measures and describes are likely to reflect the participants’ true behaviors.
Focus Groups
Focus groups are formally organized, structured groups of individuals brought
together to discuss a topic or series of topics during a specific period of time. Like
surveys, focus groups can be an extremely useful technique for obtaining individuals’
impressions and concerns about certain issues, services, or products. Originally
developed for use in marketing research, focus groups have served as a principal
method of qualitative research among social scientists for many decades. In contrast
to other, unilateral methods of obtaining qualitative data (e.g., observation, surveys),
focus groups allow for interactions between the researcher and the participants and
among the participants themselves. Like most other qualitative research methods,
there is no one definitive way to design or conduct a focus group. However, they are
typically com posed of several participants (usually 6 to 10 individuals) and a trained
moderator. Fewer than 6 participants may restrict the diversity of the opinions to be
offered, and more than 10 may make it difficult for everyone to express their opinions
comprehensively (Hoyle, Harris, & Judd, 2002). Focus groups are also typically made
 19

up of individuals who share a particular characteristic, demographic, or interest that is

relevant to the topic being studied.
The presence of a trained moderator is critical to the focus-group process (Hoyle et
al., 2002). The moderator is directly responsible for setting the ground rules, raising
the discussion topics, and maintaining the focus of the group discussions. When
setting the ground rules, the moderator must, above all, discuss issues of
confidentiality, including the confidentiality of all information shared with and
recorded by the researchers (also covered when obtaining informed consent). In
addition, the moderator will often request that all participants respect each other’s
privacy by keeping what they hear in the focus groups confidential. Other ground
rules may involve speaking one at a time and avoiding criticizing the expressed
viewpoints of the other participants.
Open-Ended Surveys and Questionnaires
Open-ended surveys and questionnaires allow organizations to collect views and
opinions from respondents without meeting in person. They can be sent electronically
and are considered one of the most cost-effective qualitative data collection tools.
Unlike closed question surveys and questionnaires that limit responses, open-ended
questions allow participants to provide lengthy and in-depth answers from which you
can extrapolate large amounts of data.