4. True experiments have these features:
#1: Presence ofTwo Distinct Groups
▪ Control Group
▪ Experimental Group
#2:Variation in IV Before Change in DV
#3: Random Assignment
5.
6. #1: Establishment ofTwo Groups
#2: RandomAssignment of Individuals
#3: Administration of Experimental
Treatment
#4: Pre and Post-Measures of DV
#5: Researcher-Controlled Environment
7. Bunch of
People Measure DV
Measure DVRandom
Assignment
Random
Assignment
(PRE-TEST)
Introduce IV
Stimulus
“Placebo”
Measure DV
Treatment
Group
Control GroupControl Group
Measure DV
Treatment Group
(POST-TEST)
8.
9. Helps to control for effects that might create
a spurious relationship
Is random assignment always the answer?
Matching as potential solution?
What are the problems with this?
10.
11. Research procedure demonstrates a true
cause-and-effect relationship NOT created
by spuriousness
History
Maturation
Selection Bias
Regression Artifacts
Experimental Mortality
12.
13. Extent to which results of study can be
generalized across populations, times, and
settings
Gerber and Green: “When evaluating the
external validity of political experiments, it is
common to ask whether the stimulus used in
the study resembles the stimulus of interest in
the political world…”
16. Similar to classical experiment
Two Groups,TwoVariables
Random Assignment
Experimental Group – Stimulus
Control Group – “Placebo”
Difference: No Pre-Test
17.
18. Multiple levels of IV and/or DV are created
Useful Design:
IV can assume several values
Researcher wants to vary IV
Example: Mail Questionnaires
25. Jeopardy! has been used to
understand betting strategies
in two-person games.
26.
27.
28. Researcher examines one or few cases of
given phenomenon in detail
Employ several data collection methods:
Personal Interviews
Document Analysis
Direct and Indirect Observation
29. SMALL-N DESIGNS
Exploratory or Descriptive
Purposes
Case Study /
Comparative Analysis
Focus Group
CROSS-SECTIONAL DESIGNS
Measurements of IV and
DV taken at same time
Example: Survey Research
30.
31. Time-Series Designs
Measure variables at different time points
What are the advantages of these designs?
Age, Period, and Cohort Effects
32. Also known as time series designs
Characterized by measuring variables at
different points in time
Advantages of Longitudinal Designs
Age, Period, Cohort Effects
33.
34. FORMAL MODELING
Simplified and abstract
representation of reality
Expressed in mathematical
or similar format showing
how parts make whole
Example:Turnout Equation
R = PB – C + D
SIMULATION
Representation of system
in order to study behavior
over time
Examples:
Computer Programs
Board Games
Role-Playing
Example: Prisoners’
Dilemma