Scribd
Upload
96 views27 pages

Research Design & Variable Measurement

This document discusses key concepts in research design and variable measurement. It covers different approaches to empirical research, basic principles of social science research, the difference between social and natural sciences, and major components of research design including research questions, theory, and data. It also discusses causality, types of research designs, and common errors to avoid in research.

Uploaded by

Faisal Shafique
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
96 views27 pages

Research Design & Variable Measurement

This document discusses key concepts in research design and variable measurement. It covers different approaches to empirical research, basic principles of social science research, the difference between social and natural sciences, and major components of research design including research questions, theory, and data. It also discusses causality, types of research designs, and common errors to avoid in research.

Uploaded by

Faisal Shafique
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 27

Research Design &

Variable Measurement
• Different ways of doing p.s.
research
• Basic laws for doing research
• Social science vs. Natural
science/engineering
• Components of research design
– Side trip to data
• Causality
– Side trip to types of research
designs
• Seven things to avoid
The Road Map
Philosophy

Normative

Positive

Causal

Descriptive
Different Ways of Doing
Empirical Research
• Interpretive
– Verstehen
• Small-N case study
– Haphazard
– Structured
• Large-N statistical analysis

• Interactions among these ways


Basic Laws of Doing
Empirical Social Science
Research I
• No clear path between
interesting & researchable
questions
• Path paved with observable
implications
• Any research work doing
contributes to a body of
knowledge
• Most of the low-hanging fruit
has been picked
Basic Laws of Doing
Empirical Social Science
Research II
• But there are other orchards
• Never under-estimate the ease
of replication
• Build upon scalable ambitions
Social Vs. Natural
Science & Engineering
• Reductionism

• Degree of reductionism

• Implications
– Measures of association weak
– Aggregates often better predictors

• Why we have statistics


– Probabilities
– Expected values
Major Components of
Research Design
• Research question
• Theory
• Data
Research Question

• Importance
– Not too general
– Not too specific
– Just right
• Contribute to literature
– www.webofscience.com
Theory

• Def: A general statement of a


proposition that argues why events
occur as they do and/or predicts
future outcomes as a f(prior
conditions).

• General/concrete trade-off
• Observable implications

• Falsification
– Karl popper
• Parsimony
– Occam’s razor
Data

• Terms
– Cases
– Observations
– Variables
– Units of analysis

• Mapping between the abstract


and concrete
– Measures
– Indicators
Side Trip to
Measurement
• From abstraction to measure
• Sources of error
• What to do about error
The Mapping

X Y

x y

e ey
x
Mapping from
Abstraction to Measure
• Very abstract
– Alienation and suicide
– Moral decay and crime
• Less abstract
– Democracy and peace
– Party identification and voting
– Fear of defeat and fundraising
– Polarization and responsiveness
Sources of Error

• Conceptual or design error


• Bad breaks in random sampling
• Survey question wording
• Non-random out-selection
• Transcription errors
• Calculation & mechanization
errors
What to Do About Error

• Practice safe data


– Know where your data come from
– Watch for anomalies
– Use multiple measurement
techniques
– Collect as much data as possible
and disaggregate
Causality

• Definitions of causality
• Problems in causal research
• Side trip to Campbell and
Stanley
Definitions of Causality

• Mechanical
• Logical
• Statistical
– Experimental paradigm
– Expected values
Problems in Causal
Research
• Theory
– Confounding effects
• Design
– Experimentalism is an ideal
– Observationalism
• “natural experiments”
• Control variables
Donald Campbell and
Julian Stanley

Experimental and Quasi-


Experimental Designs for
Research (1963)
Research design types

• One-shot case study


• One-group pre-test/post-test
• Static group comparison
• Pre-test/post-test with control
group
• Solomon four-group design
• Post-test only experiment
One-shot Case Study

• Summary:
X O

• Journalism
• Common sense
• “of no scientific value”
One-group Pre-test/post-
test
• Summary:
O X O

• Better than nothing


• Standard way of doing most
research
Static group comparison

• Summary:
X O1
------
O2
• Problems
– Selection
– Mutual causation
• This is most cross-sectional
analysis
Pre-test/Post-test Control
Group
• Summary:
R O1T X O2T
-----------------------------
R O1C O2C

• Effect of treatment:
[O2T - O1T] – [O2C - O1C]
Solomon Four-Group
Design
• Summary:
R O X O
R O O
R X O
R O

• This allow you to control for the


effect of the experiment itself
Post-test only
experiment
• Summary:
R X O
R O
• No selection
• No prior observation
• Classical scientific and
agricultural experimentalism
Last word: Things to
Avoid
• Colinearity
• Sampling on the dependent
variable
• Constant explanatory variables
• Constant dependent variables
• Measurement error
• Excluded variable bias
• Endogeneity

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy