RESEARCH DESIGN

Introduction to Research Designs

● A research design is the plan or framework used to conduct

a research study. It involves outlining the overall approach

and methods that will be used to collect and analyze data in
order to answer research questions or test hypotheses.
● A well-designed research study should have a clear and well-

defined research question, a detailed plan for collecting data,

and a method for analyzing and interpreting the results.
● A well-thought-out research design addresses all these
features.
 Elements of Research Design

● Research design encompases the following elements:

1. Research approach (quantitative, qualitative, mixed)

2. Methods of data collection and data collection procedures
3. Population and sampling
4. Population,Sample size and sampling procedures/techniques
5. Methods of data analysis
6. Time frame: time frame, duration of the study
7. Ethical considerations: must include decisions about ethical
considerations
8. Resources: A decisions about the budget and other resources
needed to carry out the study.
 Factors Affecting Design Selection

1. Research problem and questions

2. Purpose of the study (descriptive,exploratory or explanatory)
3. Researcher's knowledge and experience (in qualitative or
quantitative research)
4. Population of interest-is it large population?how accessible?
5. Available resources (time, money)
6. Intended users of study findings (do they prefer narrative or
statistical reports?
Research design types can be divided into qualitative
and quantitative research.
● Qualitative research is subjective and exploratory. It determines relationships
between collected data and observations. It is usually carried out through
interviews with open-ended questions, observations that are described in
words, etc.
● Quantitative research is objective and employs statistical approaches. It
establishes the cause-and-effect relationship among variables using different
statistical and computational methods. This type of research is usually done
using surveys and experiments.
 Qualitative research design
1. Case Study
 In-depth investigation of a singular entity (person, group, event)
 Focuses on a particular unit called a "case"
 Can use multiple data collection methods e.g questionnaires,
interviews, observations, or written accounts by the subjects. (A nurse
researcher might be interested in how people with diabetes respond to
an insulin pump. One person or a group of people with diabetes could
be studied for a time to determine their responses to the use of an
insulin pump. Diaries might be used for the day-to-day recording of
information. The nurse researcher would then analyze these diaries
and try to interpret the written comments
 Achieves rich description of real-life phenomena
 2. Ethnography

● Describes culture and social interactions of a particular group

● According to Leininger (1985), ethnography can be defined as “the
systematic process of observing, detailing, describing, documenting,
and analyzing the lifeways or particular patterns of a culture (or
subculture) in order to grasp the lifeways or patterns of the people in
their familiar environment”
● The researcher frequently lives with the people and becomes a part of
their culture. The researcher explores with the people their rituals and
customs.
● An entire cultural group may be studied or a subgroup in the culture.
● Data are generally collected through participant observation and
interviews (key informants)
 3. Grounded Theory

● Grounded theory studies are studies in which data

are collected and analyzed and then a theory is
developed that is grounded in the data. (Purpose -
theory development)
● The grounded theory method uses both an inductive
and a deductive approach to theory development.
● Uses systematic procedures to derive theory about a
phenomenon
● Starts with data, then develops themes/patterns
 4. Phenomenology

● Examine human experiences through the descriptions provided by the

people involved. These experiences are called lived experiences. The
goal of phenomenological studies is to describe the meaning that
experiences hold for each subject. This type of research is used to
study areas in which there is little knowledge (Donalek, 2004)
● Key question: What is the experience from the participant's
perspective?
● Main data collection: In-depth interviews
● Example: Parent's experience of raising an autistic child OR “What is
it like for a mother to live with a teenage child who is dying of
cancer?”
 5. Biography/Narrative Research

● Studies life experiences of an individual (study of a person)

● Researchers write narratives about experiences of
individuals, describe a life experience, and discuss the
meaning of the experience with the individual.
● Usually, a narrative research design is focused on studying
an individual person.
● The researcher becomes the interpreter of the individual's
stories, as opposed to a community.
 Overview of Quantitative Research Designs

● Survey designs
● Ex post facto (causal-comparative) designs
● Experimental designs
1. Descriptive Research Design
● Explains the current status of an identified and measurable variable
● This type of quantitative research describes the characteristics of a problem and
answers the what, when, where of a problem. However, it doesn’t answer
the why of the problem and doesn’t explore cause-and-effect relationships
between variables.
● Descriptive research is also referred to as “observational studies” because your
role is strictly that of an observer
○ Examples of questions that can be answered using a descriptive research
design:
○ What is the overall level of job satisfaction and remuneration of employees
at Company X?.
 2. Survey Designs
● Used to describe characteristics of a population
● allows researchers to collect structured data from individuals or groups to
gain deeper insights into their thoughts, behaviors, or experiences related
to a specific topic.
● highly valued in research because it is an accessible and efficient way for
respondents to share their perspectives. By leveraging survey research,
organizations can quickly gauge public opinions, understand trends
within a population, and identify issues or areas for improvement.
● This method is widely used in academic, business, and government
research to uncover data that can lead to actionable solutions or further
study.
● One of the key strengths of survey research is its ability to provide a
snapshot of trends or opinions within a population, allowing researchers to
generalize findings and make informed decisions.
● Additionally, surveys can be used to test hypotheses, track changes over
time, or serve as the foundation for more in-depth studies.
● As a result, survey research design remains a cornerstone of modern
research methods.
● Often uses questionnaires or structured interviews
 Types of Survey Designs

● Cross-sectional: Data collected at one point in time selected to

represent a larger population. (collects data at a single point in
time, providing a snapshot of opinions, behaviors, or trends at
that specific moment.)
● Longitudinal: Data collected over an extended period
● involves collecting data at multiple points over a defined time
period to examine changes in key variables. In this approach,
surveys are administered at least twice: once at the beginning
and once at the end of the study period. Researchers may also
choose to collect data at intervals throughout the study.
 Longitudinal Survey Methods

 Trend:
Surveys of sample population at different time
points.
 Cohort:
Study of sample population each time data are
collected but samples studied maybe
different.
 Panel:
Data collection at various time points with the
3. Correlational Research Design
● A correlational design compares two or more variables and/or investigates how they
relate to each other. The researcher does not influence, control or manipulate the
variables of interest, and therefore cannot assign cause and effect. Remember the
golden rule: Correlation does not imply causation.
● Examples of questions that can be answered using a correlational research design:
○ Is there a relationship between an employee’s job satisfaction and their
remuneration package?
○ Is there a relationship between a restaurant’s negative online reviews and the
number of table bookings they receive?
○ Is there a relationship between the celebrity endorsements of skincare products
and the number of product sales?
 4. Ex Post Facto (Causal-Comparative) Design

● Causal comparative research, or ex post facto research, studies the

reasons behind a change that has already occurred.
● For example, researchers might use a causal comparative design to
determine how a new diet affects children who have already begun it.
This type of research is especially common in sociological and
medical circles.
● Though causal comparative research designs can provide insight into
the relationships between variables, researchers can’t use it to define
why an event took place. This is because the event already occurred,
so researchers can’t be sure what caused it and what the effects are.
 Limitations of Ex Post Facto Design

● Researcher has no control over groups

● Cause-effect relationship may be
spurious
● Results are tentative
● May require repeated measures for
satisfactory results
 5. Experimental Designs

● Determines cause and effect relationships

● Researcher manipulates independent variable
● Allows for stronger causal inferences
● The researcher has control over all study variables which are
manipulated to systematically test a specific theory or theories.
The aim of an experimental research design is to establish a
cause-and-effect relationship
● Example: A researcher studies the importance of a drug in
treating a disease by administering the drug in few patients
and not administering in a few.
6. Quasi-Experimental Quantitative Research Design

● The researcher attempts to establish a cause-effect relationship from one

variable to another. For example, a researcher may determine that high
school students who study for an hour every day are more likely to earn high
grades on their tests. To develop this finding, the researcher would first
measure the length of time that the participants study each day (variable one)
and then their test scores (variable two).
● A quasi-experimental study is not a true experimental study because it does
not randomly assign study participants to groups. Rather, it assigns them to
groups specifically because they have a certain attribute or meet non-random
criteria.