Chapter 6 Causation and Experimentation Flashcards
1 receiving the experimental condition (treatment or intervention) AKA experimental group AND 1 receiving no treatment or intervention AKA control group
2 comparison groups
Mechanism and Context
2 conditions important in specifying causal relationships
Empirical association, Appropriate time order, and Nonspuriousness
3 conditions required to establish cause and effect (causality)
Expectancies of experimental staff, Placebo effect, Hawthorne effect
3 sources of treatment misidentification
Measurement of the DV in both groups after the experimental group has received the treatment
Assessment of change (posttest)
Has a pretest and posttest but no comparison group (only an experimental group)
Before-and-after design
the outcome that would have occurred if the subjects who were exposed to the treatment were actually not exposed, but given identical experiences to those who did get the treatment
Counterfactual
People who have all experienced a similar event or common starting point
Cohort
ability to confidently apply the results of the study to its corresponding population
Generalizability (external validity)
When either the experimental groups or the comparison group is aware of the other group
Contamination
A study in which data are collected at only one point in time
Cross-sectional design research
when natural developments in the subjects account for some or all of the observed change between pretest and posttest
Endogenous change
“After the fact.” Uses nonrandom control groups designated after the treatment
Ex post facto control group design
Things that happen outside of the experiment that can also change the subject’s outcome scores
External events (history effect)
Whenever studies utilize conditions of an experimental method in a real-world setting
Field research (or field experiment)
A type of longitudinal study in which data are collected from the same individuals at 2 or more points in time
Fixed-sample panel design
when the experimental treatment is effective only when particular conditions created by the experiment occur
Interaction of testing and treatment
Ability to confidently state that the relationship between X (the IV) and Y (the DV) is causal
Internal validity
A study in which data are collected at 2 or more points in time, so identification of time is straightforward
Longitudinal research Designs
a procedure for equating the characteristics of individuals in the experimental group and the control group
Matching
Experimental and comparison group that are designated before the treatment occurs, individual matching or aggregate (group) matching
Nonequivalent control group design
A relationship that exists between 2 variables that is not due to variation in a 3rd variable
Nonspuriousness
Research design where a comparison group is comparable to the treatment group in important ways
Quasi-experimental designs
a type of longitudinal study in which data are collected at 2 or more points in time from different samples of the same population
Repeated cross-sectional design (trend study)
When characteristics of the experimental and comparison group subjects differ in a way that influences the outcome
Selection bias
testing and treatment interact to produce the outcome of this
Solomon four-group design
when the treatment itself is not what causes the outcome, but the change occurs through a process that the researcher hasn’t identified
Treatment misidentification
True experiments
Great for internal validity, allow us to confidently establish the first 3 criteria for causality