Vous êtes sur la page 1sur 10

1

Quantitative Research

Quantitative research is the systematic investigation of social


phenomena using statistical techniques.Quantitative research is deductive
research approach. It assumes;

Social facts have an objective reality


Primacy of method
Variables can be identified and relationships measured
Etic (outsiders point of view)

To the quantitative researcher, the world is external to the researcher


and there is an objective reality Independent of any observations. This
reality can be understood in the whole by dividing it up into smaller pieces
and studying the parts. Within these smaller environments, observations
can be taken and the relationships among variables can be hypothesized,
tested, and reproduced. In the quantitative approach, the researcher begins
with theory, generates hypotheses, tests those hypotheses through
observation and analysis, and then draws conclusions. Generalizability is a
central benefit of, and purpose for, quantitative research. By drawing
representative samples from larger populations and testing hypothesized
relationships among variables, quantitative researchers aim to find results
that can be generalized beyond the scope of their studies.

Quantitative research starts with the statement of the problem. The


problem should address a gap in the professional literature and should
improve professional practice when answered. Good research question
build on previous research. A quantitative research design is a plan that
guides the decision as to:

1. When and how often to collect data


2

2. What data to gather and from whom


3. How to analyze the data
4. Examines linkage, causation, or relationships

Descriptive: to the analysis of data that helps describe, show or


summarize data in a meaningful way such that, for example, patterns
might emerge from the data.
Inferential: to try to infer from the sample data what the population might
think.

Sampling
3

The collection, analysis, and interpretation of data gathered from


random samples of a population under study. The target population is the
population to which the researcher wants to generalize study result

Probability Sampling (Random selection of research participants)

1. Simple Random Sample. All members of the population have an


equal and independent chance of being selected.
2. Stratified Random Sample. Population is first divided into subsets
or strata.
3. Cluster Random Sample. Existing cluster or groups are randomly
selected and then each member of the cluster is used in the
research.

Non-Probability Sampling (Participants are selected because of


convenience or access)

1. Convenience Sample. Relies on available participants.


2. Purpose Sample. Based on researchs knowledge of the target
participants.
3. Quota Sample. Stratified convenience-sampling strategy.

Sample Frame

1. List of sampling units, which may be individuals or groups.


2. Sample error: 5%

Non-Sampling Error (caused by human error)

1. Specification Error Occurs. Instruments are not properly aligned.


2. Coverage or Frame Error. Biased representation of the target
population.
4

3. Nonresponse Error. Some members of the sample do not respond.


4. Measurement Error. Data collection is not reliable.
5. Processing Error. Editing mistakes, coding mistakes, data entry
mistakes, and/or programming errors during data analysis.

Measurement

Measurement is the process of representing the construct with


numbers in order to depict the amount of a phenomenon that is present at
a given point in time.

Three Basic Types of Measurements

1. Self-Report Measurement. One can measure a variable by asking


participants to describe their behavior, to express their opinions, or
to engage in interviews or focus groups in order to express their
view.
2. Physiological Measurement. Deals with measurements pertaining to
the body.
3. Behavioral Measurement. Through observation.

Scaling

The branch of measurement that involves the construction of an


instrument. There are Three major types of scaling, these are the Likert
Scaling, Guttman Scaling, and Thurstone Scaling.
5

Likert Scaling

Guttman Scaling

Thurstone Scaling

Variables

Any observable characteristics (Lacar, Luis Q.). A variable could be in the


form of the following:
6

1. Weight 6. Nationality
2. Age 7. Ethnic Background
3. Sex 8. Number of Children per
4. Religion Family
5. Race 9. Income

Scale Measurement

Scale measurements are used to define and categorize variables. Variable


are categorized as ratio, interval, ordinal, and nominal.

Ratio/Interval Scale

Variables allow one to quantify and compare the sizes of


differences between them.

Ordinal Scale

Variables allow one to rank order the items one measures in terms
of which has less and which has more of the quality represented by the
variable, but they do not provide information regarding much more.

Nominal Scale

Variables are unordered categories.

Gender
Designated by name, class, or category only.
7

Quantitative Research Design

A research design is a blueprint for research that focuses on the


logical structure of the research and identifies how research participants are
grouped and when data are to be collected (Yin, 1989)

Quantitative Research: Types (Campbell & Stanley, 1963; and Crowl,


1993)

Non-Experimental Design

Identify the characteristics of a phenomenon and describe the


variable(s) under study. The researcher tests relationships between
variables without controlling and manipulating research participants and/or
conditions. In other words, the researcher studies what naturally occurs or
has already occurred.
8

Non-Experimental Design

There are Three types of non-experimental studies:

1) Descriptive Design
a) Survey Design: Longitude Design and Cross Sectional Design
b) Observational Design
2) Correlation Design
3) Casual Comparative

Experimental Design

An experiment study involves design in which the researcher


controls the manipulation of the independent variable. There are Three
types of experimental studies:

1) True Experiments
2) Quasi-Experiments
3) Pre-Experiments
9

QUANTITATIVE RESEARCH DESIGN

A NARRATIVE REPORT

Presented to
DR. MARILOU S. NANAMAN
Graduate Faculty of
Master of Public Administration
MSU Iligan Institute of Technology
Iligan City

In Partial Fulfillment
of the Requirements for the Degree of
MASTER OF PUBLIC ADMINISTRATION
(ORGANIZATION AND MANAGEMENT)

AJREE DUCOL MALAWANI


OCTOBER 2015
10

REFERENCE LIST

LACAR, LUIS Q., PH.D. ELEMENTARY STATISTICS FOR THE SOCIAL,


BEHAVIORAL, AND EDUCATIONAL SCIENCES.

ROVAI, ALFRED P., JASON D. BAKER, AND MICHAEL K. PONTON, 2013.


SOCIAL SCIENCE RESEARCH DESIGN AND STATISTICS

CRESWELL, JOHN W. 2012, RESEARCH DESIGN

Vous aimerez peut-être aussi