Term
| True Experiment differ from a quasi? |
|
Definition
| Quasi is not randomly assigned. True is. |
|
|
Term
How does a non-experimental design (that tries to establish causality)
differ from an experimental design? |
|
Definition
| Comparison groups are selected after the treatment. |
|
|
Term
| What are the 5 criteria used to establish internal validity? |
|
Definition
1. Association
2. Time Order
3. Nonspuriousness
4. Mechanism
5. Context |
|
|
Term
| What are the esstential features of of a true experiment? |
|
Definition
1. 2 comparison croups (est. assoc)
2. Variation in the IV before assement of chagne in the DV (est. time order)
3. Random assignment to the 2 groups (est. nonspuriousness) |
|
|
Term
| Strengths of experimental research? |
|
Definition
| Best way to establish causal relationships or testing causal hypotheses. (allows us to estalbish confidently the first 3 criteria for causality) |
|
|
Term
| What are the weaknesses or experimental research? |
|
Definition
|
|
Term
| Ethical concerns of experimental researchers? |
|
Definition
Experiments involve subject deception.
-not informed of of reason for study, of assignment to treatment or control, often behaviors elicited from experiment can be harmful |
|
|
Term
| How do researchers address ethical concerns? |
|
Definition
| Post experimental debriefing to inform subject. |
|
|
Term
| How do you identify the cause & effect? |
|
Definition
| Operationalize causes and effects as variables (IV and DV) |
|
|
Term
|
Definition
|
|
Term
| What is empirical association? |
|
Definition
variation/change in 1 variable is related/associated to varation/change in another variable.
(Weak evidence since: correlation does not est causation) |
|
|
Term
| establishing Time Order means? |
|
Definition
the variation in the IV must occur before the variation in the DV.
(CHANGE not DIFFERENCE) (otherwise causation is not established) |
|
|
Term
|
Definition
| means false or inauthentic. Observed association is due to a 3rd variable associated with both IV & DV |
|
|
Term
|
Definition
| process that creates the connection b/w the variation in IV and variation in DV. Difficult. Identifying aspects of the process through which the IV influences the DV can establish the mechanism. |
|
|
Term
|
Definition
| Does the relationship exist in all contexts, or just specific ones? |
|
|
Term
| Quasi experiment: non-equivelent control group design..? |
|
Definition
| Design in which there are experimental and comparison groups that are designated before the treatment occurs but are not created by random assignment. |
|
|
Term
| Individual vs. Aggregate matching |
|
Definition
Individual matching: comparing similar ind
Aggregate: comparing similar groups |
|
|
Term
| Before and After designs..? |
|
Definition
| consists of several before-and-after comparisons involving the same variables but different groups. No comparison group. |
|
|
Term
|
Definition
True: good at producing internal validity, bad at achieving external validity.
Quasi: provide more generalizable results, more prone to problems of internal validity.
Measurement validity is a central concern for both kinds. |
|
|
Term
| Threats to internal validity: non-comparable groups |
|
Definition
| something interferes with the control and experimental groups being the same (before and after) the 2 groups are not comparable. -selection bias, differential attrition, instrument decay |
|
|
Term
| Threats to internal validity: endogenous change |
|
Definition
occur when natural developments in the subjects, independent of the experimental treatment itself, account for some or all of the observed change between pre and posttests
-Testing, maturation, regression |
|
|
Term
| Threats to internal validity: history |
|
Definition
occurs when something other than the treatment influences outcome scores
-External events |
|
|
Term
| Threats to internal validity: contamination |
|
Definition
occurs when either the experimental and/or the comparison group is aware of the other groups and is influenced in the posttest as a result; somehow affect each other
-Compensatory rivlarly |
|
|
Term
| Threats to internal validity: treatment misidentification |
|
Definition
a problem that occurs in an experiment when the treatment itself is not what causes the outcome but rather the outcome is caused by some intervening process that the researcher has not identified and is not aware of
-Experimenter expectation, placebo effect, hawthorne effect |
|
|
Term
|
Definition
can we generalize from our sample to a larger population; the more artificial the experiment, the greater the problem
-external validity |
|
|
