Basic Research Designs

This module will introduce the basics of choosing an appropriate

research design and the key factors that must be considered.

Learning Objectives

 Distinguish between quantitative and qualitative research methods.

 Identify whether or research project is qualitative or
quantitative in nature.
 List the key factors that must be considered when choosing a
research design.

Once the research question has been formulated, it is critical that the
researcher select the appropriate research methodology to answer the
question. The type of research question will typically dictate the
methodology that will be employed. The reliability and validity of the
results depends on upon proper selection of the research approach and
design.

Forms of Research
Research is a systematic inquiry used to describe, explain, predict or
control some observed phenomenon - the research topic. Research can be
classified into four main forms based on the specific purpose:

 Basic Research - This research is descriptive in nature and is

used to understand and explain a phenomenon. This type of research
is often conducted for the sake of increasing and advancing a
knowledge base.
 Applied Research - The purpose of this research is to provide
information that can be used and applied in an effort to help people
understand and control their environment. This type of research is
more prescriptive in nature and seeks to offer potential solutions to
problems.
 Evaluation Research - The purpose of evaluation research is to
examine the processes and outcomes associated with a particular
solution to a problem. The research may be formative in that it
attempts to improve the intervention or solution or it may be
summative and attempt to evaluate the effectiveness of solution or
program.
 Action Research - This research is often conducted within a
program, organization or community and the researchers are involved
 in gathering data and studying themselves.

Regardless of the purpose of the research, the process is similar.

Researchers begin by selecting a broad research topic and conducting a
literature review to build up the researcher's knowledge base and to
ensure the significance of the research. The researcher will then
develop a research problem related to the topic and create a specific
question. The research design will then be developed and the procedures
for analyzing the data will be identified. The results of the research
will hopefully lend themselves to the publication of a scholarly
article.

Quantitative and Qualitative Designs

There are two main approaches to a research problem - quantitative and

qualitative methods. Quantitative methods are used to examine the
relationship between variables with the primary goal being to analyze
and represent that relationship mathematically through statistical
analysis. This is the type of research approach most commonly used in
scientific research problems. Qualitative methods are chosen when the
goal of the research problem is to examine, understand and describe a
phenomenon. These methods are a common choice in social science
research problems and are often used to study ideas, beliefs, human
behaviors and other research questions that do not involve studying the
relationship between variables. Once the main approach to the research
problem has been determined, there are several research designs for
each type of approach that may be considered.

Choosing a Design

The following table lists and describes the most common research designs
used at Grand Canyon University. Different research books will use
different terms for similar types of research. However, the research
designs identified in this document are fairly common in terms of their
use and their terminology.

Types of Research Designs

 Quantitative Designs Qualitative Designs
Design Focus Design Focus
Correlational Explore the Case Study Intent is to
relationship study and
between two or And Historical understand a
more variables single
through a situation, which
correlational could be a
analysis. The leader, a
intent is to classroom, a
determine if and process,
to what degree program,
the variables activity.
are related. It Collect a
does not imply variety of
one causes the material in a
other. specific and
bounded time
period. This is
also used for
historical
studies, when
collecting
historical data
to understand
and learn from
the past.
Causal Comparative Compare two Narrative Describe the
groups with the lives of
intent of individual(s) to
understanding get meaning from
the reasons or them.
causes for the
two groups being
different.
Experimental Test an idea, Grounded Theory The focus is to
treatment, develop an
program to see understanding of
if it makes a a phenomenon or
difference. situation in
There is a order to be able
control group to develop a
and a test theory/model for
group. items such as
Individuals are factors, a form
 randomly of interaction,
assigned to the or a process.
two groups. One
group gets the
treatment (test
group) and the
other group
(control group)
does not get the
treatment. There
is a pre and
post-test for
both groups in a
traditional
experimental
design.
Quasi-experimental It is the same Phenomenology Studies a human
as experiment in experience at an
that there is a experiential
control and test level such as
group. However, understanding
current groups what it means
are used as is for a woman to
rather than lose a child. It
randomly is about
assigning people understanding
to the two the essence or
groups. Both meaning of the
groups receive experience.
the pre and
post- test in a
traditional
design.

Mixed Research Designs

A mixed research design involves having both a quantitative design and

qualitative design. Mixed designs is the best approach if the study
requires both quantitative and qualitative designs to address the problem
statement.

Mixed design studies take significantly more time, more resources, and
require the researcher to develop expertise in qualitative analysis
techniques and quantitative analysis techniques. Qualitative studies can
use numbers, counts and even descriptive statistics. Using numbers does
not mean the study has to be quantitative or mixed methods.
Different Types of Research Designs
 The research design is the structure of a scientific work. A
good research design will obviously describe the strategy to be employed
for choosing samples, collecting data, managing costs along with other
factors which are important for conducting research.

The research methods which are employed and purpose of the research can
also be utilized to classify the different types of research designs.
The method you select will influence your results and the way you
conclude the findings. The majority of researchers are curious about
getting reliable observations which can help the understanding of a
phenomenon. There are different research designs that are utilized in
research, all with certain benefits and drawbacks. Which one the
researcher employs, is dependent upon the goals of the study and the
nature of the phenomenon. It is dependent on following factors:

 Exactly what information are you interested in? The objectives of

the study.
 The type of the phenomenon – Is it possible to gather the data,
and if so, will it be valid/reliable?
 How trustworthy should the information be?
 Is it ethical to carry out the research?
 The expense of the design
 Is there little or much existing scientific theory and materials
on the subject?

What are the Different Types of Research Designs

Methods ?
It is crucial that you select a suitable research design before any
research is started. Various types can be classified as:

1. Historical Research Design – The idea is to gather, validate,

synthesize evidence to establish facts which defend or oppose your
hypothesis. It makes use of primary sources, secondary sources, and a
lot of qualitative data sources for example logs, diaries, official
data, reports, and so on. The issue is that the sources need to be both
authentic and valid.

2. Case Study: It is an in-depth investigation of a specific research

problem as opposed to a sweeping statistical survey. It is usually
employed to limit a very wide area of research into one or a few easily
research-able examples. The case study research design can also be
helpful for testing whether a particular theory and model actually
pertains to phenomena in real life. It is a useful design if not much is
known about a phenomenon.

3. Descriptive research: Descriptive research includes much government

backed research such as the population census, the gathering of a broad
range of social indicators and economic information for example
household expenditure patterns, time use studies, employment and crime
statistics.

4. Causal Design: Causality research could be regarded as understanding

a phenomenon with regards to conditional statements in the form, “If A,
then B.” This kind of research is utilized to determine what affect a
certain change may have on present norms and assumptions. The majority
of social scientists seek causal explanations which reflect tests of
hypotheses. Causal effect takes place when variation in one phenomenon,
an independent variable, results in, on average, in variation in another
phenomenon, the dependent variable.

5. Longitudinal Research Design: A longitudinal study consists of a

panel, which is a fixed sample of elements. The elements could be shops,
retailers, individuals, or other entities. The panel, or sample, stays
relatively constant over time, despite the fact that members may be
added to replace dropouts or to keep it representative. The sample
members in a panel are calculated regularly over time, in contrast with
the one-time measurement in a cross-sectional study.

6. Cross-Sectional Design: Cross-sectional research designs have 3

exclusive features: no time dimension, a reliance upon present
differences rather than change following intervention; and, groups are
chosen according to existing differences as opposed to random
allocation. The cross-sectional design can only measure differences
between or from among a number of people, subjects, or phenomena instead
of change. As a result, researchers employing this design can only use a
relative passive approach to making causal inferences based on findings.

7. Correlation or Prospective Research Design: It tries to discover

relationships to make predictions. It uses one set of subjects with a
couple of variables for each.

8. Cohort Design: A cohort study is a research program looking into a

specific group with a certain trait, and observes over a period of time.
A few examples of cohorts may be those who have taken a certain
medicine, or have a medical problem.

9. Observational Design: This kind of research design draws a conclusion

by evaluating subjects against a control group, in situations where the
researcher doesn’t have control over the experiment. There are a couple
of general types of observational designs. In direct observations,
people realize that you are watching them. Unobtrusive measures include
any way of studying behavior where individuals have no idea they are
being observed. An observational study allows a good insight into a
phenomenon and eliminates the ethical and practical complications of
establishing a large and cumbersome research project.

10. Experimental Research Design: This design is best suited in

controlled settings for example labs. The design assumes random
assignment of subjects and random assignment to groups (A and C). It
tries to investigate cause and affect associations where causes could be
manipulated to generate different types of effects. Due to the
requirement of random assignment, this design can be challenging to
carry out in the real world (non laboratory) setting.

11. Philosophical Design: This method makes use of the tools of

argumentation based on philosophical traditions, concepts, models, and
theories to critically explore and challenge, for instance, the
relevance of logic and evidence in academic debates, to evaluate
arguments about fundamental problems, or to discuss the cause of
existing discourse about a research problem.
What is Multiple Linear Regression?
Multiple linear regression is the most common form of linear regression
analysis. As a predictive analysis, the multiple linear regression is
used to explain the relationship between one continuous dependent
variable and two or more independent variables. The independent
variables can be continuous or categorical (dummy coded as appropriate).

Example Questions Answered:

Do age and IQ scores effectively predict GPA?

Do weight, height, and age explain the variance in cholesterol levels?

Assumptions:

Regression residuals must be normally distributed.

A linear relationship is assumed between the dependent variable and the

independent variables.

The residuals are homoscedastic and approximately rectangular-shaped.

Absence of multicollinearity is assumed in the model, meaning that the

independent variables are not too highly correlated.

At the center of the multiple linear regression analysis is the task of

fitting a single line through a scatter plot. More specifically the
multiple linear regression fits a line through a multi-dimensional space
of data points. The simplest form has one dependent and two independent
variables. The dependent variable may also be referred to as the
outcome variable or regressand. The independent variables may also be
referred to as the predictor variables or regressors.

There are 3 major uses for multiple linear regression analysis. First,
it might be used to identify the strength of the effect that the
independent variables have on a dependent variable.

Second, it can be used to forecast effects or impacts of changes. That

is, multiple linear regression analysis helps us to understand how much
will the dependent variable change when we change the independent
variables. For instance, a multiple linear regression can tell you how
much GPA is expected to increase (or decrease) for every one point
increase (or decrease) in IQ.

Third, multiple linear regression analysis predicts trends and future

values. The multiple linear regression analysis can be used to get
point estimates. An example question may be “what will the price of
gold be 6 month from now?”

When selecting the model for the multiple linear regression analysis,
another important consideration is the model fit. Adding independent
variables to a multiple linear regression model will always increase the
amount of explained variance in the dependent variable (typically
expressed as R²). Therefore, adding too many independent variables
without any theoretical justification may result in an over-fit model.

*Please call 877-437-8622 to request a quote based on the specifics of

your research, or [email protected].

Related Pages:

Conduct and Interpret a Multiple Linear Regres