Chapter 4
Research Design
Three Purposes of Research
1. Exploration
2. Description
3. Explanation
Purpose of Exploratory Studies
• Satisfy researcher’s curiosity and desire
for better understanding.
• Test the feasibility of undertaking a more
extensive study.
• Develop methods to be employed in a
subsequent study.
Purpose of Descriptive Studies
• Observe and describe situations and
events
• Answer questions of what, where, when,
and how
• Examples: US Census, American Housing
Survey, Unified Crime Reports
Purpose of Explanatory Studies
• Answer questions of why?
• Test hypotheses and theories.
Explaining a Political
Phenomenon
• Identifying causality
• Not an easy thing to do
• Multiple factors likely to influence an event
or behavior
• Approach my depend on approach
– Idiographic
– nomothetic
Criteria for Nomothetic Causality
1. A statistical correlation between the two
variables.
2. The cause takes place before the effect.
3. There is no third variable that can explain
away the observed correlation as
spurious.
Remember
• Research can determine some causes,
but it cannot determine complete
causation.
• Exceptions do not disprove a causal
relationship.
• Causal relationships can be true even if
they don’t apply in a majority of cases.
Necessary & Sufficient Causes
• Necessary cause - a condition that must be
present for the effect to follow.
• Sufficient cause - condition that if present,
guarantees the effect in question.
• Causes that are both necessary and sufficient
are the most satisfying outcome in research.
• Note – this is language used in the sciences, it is
hard to find a necessary or sufficient cause in
political science
Units of Analysis
What is a “Unit of Analysis”?
What or whom to study:
• Individuals
• Groups
• Organizations
• Social artifacts
Units of Analysis and Faulty
Reasoning
• Ecological fallacy – assuming something
learned about an ecological unit says
something about the individuals in the unit.
• Reductionism – Reducing something to a
simple explanation when in reality it is
complex.
Time Dimension
• Cross-Sectional Studies
• Longitudinal Studies
– Trend
– Cohort
– Panel
Example
Year
Approve abortion
for any reason
1980
1985
1990
1994
2000
Yes
37.9% 38.0% 49.2% 51.7% 47.6%
No
62.1% 62.0% 50.8% 48.3% 52.4%
100% 100% 100% 100% 100%
(480) (481) (323) (331) (309)
How to Design a Research
Project
1. Define the purpose of your project.
2. Specify exact meanings for the concepts
you want to study.
3. Choose a research method.
4. Decide how to measure the results.
How to Design a Research
Project
5.
6.
7.
8.
9.
Decide whom or what to study.
Collect empirical data.*
Process the data.*
Analyze the data.*
Report your findings.*
* We will not be collecting or analyzing data for the research
paper, only identifying data sources and measures.
Elements of a Research
Proposal
•
•
•
•
Problem or objective
Literature review
Subjects for study
Measurement
– How do you measure:
• Corruption
• Equality
• Effectiveness
Elements of a Research
Proposal
•
•
•
•
Data-collection methods
Analysis
Schedule
Budget
– For you research project imagine you have a
limited budget
Example
• http://faculty.unlv.edu/kfernandez/articles/research-design.pdf