Kinds of Quantitative Research

Kinds of Quantitative Research Designs

Research design refers to the overall strategy that you choose in order to integrate the different
components of the study in a coherent and logical way, thereby ensuring you will effectively address the
research problem. Furthermore, a research design constitutes the blueprint for the selection,
measurement and analysis of data. The research problem determines the research design you should
use.
Quantitative methods emphasize objective measurements and the statistical, mathematical, or
numerical analysis of data collected through polls, questionnaires, and surveys, or by manipulating pre-
existing statistical data using computational techniques.
Quantitative research designs are generally classified experimental and non experimental as the
following matrix shows:

Experimental research design allows the researcher to control the situation. In so doing, it
allows the researcher to answer the question, "What causes something to occur?" This kind of research
also allows the researcher to identify cause and effect relationships between variables and to
distinguish placebo effects from treatment effects. Further, this research design supports the ability to
limit alternative explanations and to infer direct causal relationships in the study; the approach provides
the highest level of evidence for single studies.
Pre-experimental types of research apply to experimental. designs with the least internal
validity. One type of pre-experiment, the single group, pre-test-post-test design, measures the group
two times, before and after the intervention.
Instead of comparing the pretest with the posttest within one group, the posttest of the treated groups is
compared with that of an untreated group. Measuring the effect as the difference between groups marks
this as between-subjects design. Assuming both groups experienced the same time-related influences,
the comparison group feature should protect this design from the rival explanations that threaten the
within-subject design.
Two classes of experimental designs can provide better internal validity than-pre -experimental
designs: quasi-experimental and true experimental (Dooly, 1999).
In a quasi-experimental design, the researcher can collect more data, either by scheduling more
observations or finding more existing measures.
A true experimental design controls for both time-related and group-related threats. Two
features mark true experiments- two or more differently treated groups and random assignment to these
groups. These features require that the researchers have control over the experimental treatment and
the power to place subjects in groups.
True experimental design employs both treated and control groups to deal with time-related rival
explanations.
A control group reflects changes other than those due to the treatment that occur during the
time of the study. Such changes include effects of outside events, maturation by the subjects, changes
in measures and impact of any pre-tests.
True experimental design offers the highest internal validity of all the designs. Quasi-
experimental design differs from true experimental design by the absence of random assignment of
subjects to different conditions. What quasi-experiments have in common with true experiments is that
some subjects receive an intervention and provide data likely to reflect its impact.

Types of Quasi-Experimental Design

1. Non-equivalent control group design -refers to the chance failure of random assignment to equalize
the conditions by converting a true experiment into this kind of design, for purposes of analysis.
2. Interrupted Time Series Design- employs multiple measures before and after the experimental
intervention. It differs from the single-group pre-experiment that has only one pretest and one
posttest. Users of this design assume that the time threats such as history or maturation appear as
regular changes in the measures prior to the intervention.

Non-experimental Research Design

In this kind of design, the researcher observes the phenomena as they occur naturally and no
external variables are introduced. In this research design, the variables are not deliberately manipulated
nor is the setting controlled. Researchers collect data without making changes or introducing
treatments.
The Descriptive research design's main purpose is to observe, describe and document aspects
of a situation as it naturally occurs and sometimes to serve as a starting point for hypothesis generation
or theory development (www.drjayeshpatidar. blogspot.com ).

Types of Descriptive Research Designs

1. Survey - a research design used when the researcher intends to provide a quantitative or numeric
description of trends, attitudes or opinions of a population by studying a sample of that population
(Creswell, 2003). For example, universities regularly float surveys to determine customer
satisfaction, that is, the students' attitudes toward or opinions regarding student services like the
canteen, clinic, security, the guidance and counseling services, and the like.
2. Correlational - Correlational Research has three types:
 Bivariate correlational studies- obtain scores from two variables for each subject, then use them
to calculate a correlation coefficient. The term bivariate implies that the two variables are
correlated (variables are selected because they are believed to be related).
Examples: Children of wealthier (variable #1), better educated (variable #2) parents earn higher
salaries as adults.
 Prediction studies-use correlation co-efficient to show how one variable (the predictor variable)
predicts another (the criterion variable).
Examples: Which high school applicants should be admitted to college?
 Multiple Regression Prediction Studies - suppose the high school GPA is not the sole predictor of
college GPA, what might be other good predictors? All of these variables can contribute to the
over-all prediction in an equation that adds together the predictive power of each identified
variable.
3. Ex-Post Facto Research Design - These are non-experimental designs that are used to investigate
causal relationships. They examine whether one or more pre- existing conditions could possibly
have caused subsequent differences in groups of subjects. Researchers attempt to discover whether
differences between groups have results in an observed difference in the independent variables.
(www.genesep.edu/esham/educ.604/research.pdf).
Examples: What is the effect of home schooling on the social skills of adolescents?
4. Comparative design - involves comparing and contrasting two or more samples of study subjects
on one or more variables, often at a single point of time. Specifically, this design is used to
compare two distinct 'groups on the basis of selected attributes such as knowledge level,
perceptions, and attitudes, physical or psychological symptoms. For example, a comparative
study on the health problems among rural and urban older people from district Mehsana, Gujarat.
(www.dryayeshpatidat.blogspot.com )
5. Evaluative Research - seeks to assess or judge in some way providing information about
something other than might be gleaned in mere observation or investigation of relationships.
 For example, where a test of children in school is used to assess the effectiveness of teaching or
the deployment of a curriculum.
(changingminds.org/explanations/research/design/evaluativeresearch.htm).
Evaluation research is conducted to elicit useful feedback from a variety of respondents from
various fields to aid in decision making or policy formulation.
There are various types of evaluation depending on the purpose of the study. Formative and
summative evaluation types are most commonly used in research.
Formative evaluation is used to determine the quality of implementation of a project, the
efficiency and effectiveness of a program, assessment of organizational processes like
procedures, policies, guidelines, human resource development and the like.
6. Methodological - in this approach, the implementation of a variety of methodologies forms a
critical part of achieving the goal of developing a scale-matched approach, where data from
different disciplines can be integrated.