This site is 100% ad supported. Please add an exception to adblock for this site.

2950 Chapter 7


undefined, object
copy deck
Latin square design
A specific repeated-measures design with built-in counterbalancing
double-blind procedures
Procedures in which neither the experimenter nor the participants know who has been assigned to the experimental and control groups
method of difference
If not X, than not Y. X is a necessary condition of Y
factorial design
A research design with more than one factor and two or more levels of each factor
The principle that in order to demonstrate causality what is labeled as the cause should be shown to be positively correlated with what is labeled as the effect
Mill's methods
Logical methodsor propositions popularized by the 19th century English philosopher Mill, exemplified by the method of agreement and the method of difference
one-shot case study XO
A preexperimental design in which the reactions of only one group of subjects are measured after the event or treatment has occurred
necessary condition
A requisite or essential condition
lambda weights
Values that sum to zero and are used to state a prediction
A procedure in which some subjects receive Treatment A before Treatment B, and others receive B before A (like Latin Square)
efficient causality
The idea that a propelling or istigating event or condition sets some other event in motion or alters another condition to some degree
sufficient condition
A condition that is adequate to brin about some effect or result
blind experimenters
Experimenters who are unaware of which participants are in the experimental and control conditions
between-subjects design
Statistical design in which the sampling units are exposed to one treatment each
A specific threat to validity, or a confounded aspect of the scientist's observations
A plausible threat to the internal validity of research not using randomization when the kinds of research subjects selected for one treatment group are different from those selected for another group
control group
A condition with which the effects of the experimental or test condition are compared
nested design
Another name for the basic between-subjects design, because te subjects are nested within their own treatment conditions
AKA Random assignment. Random allocation of sampling units to treatment conditions
Solomon design
A four-group experimental design, developed by Solomon, as a means of isolating pretest sensitization effects without contamination by pretesting
A plausible threat to internal validity that occurs when changes in the measuring instrument (e.g., deterioration of the instrument) bias the reasults of research nor using randomization
A plausible threat to internal validity that occurs when results not using randomization are contaminated by the participants' having, for instance, grown older, wiser, stronger, or more experienced between the pretest and posttest
crossed design
Another name for the basic within-subjects design, because subjects can be said to be "crossed" by treatment conditions
randomized experiments
Experimental designs that use randomization
expectancy control design
An experimental design in which the expectancy variable operates separately from the independent variable of interest
formal causality
Emphasis on the implicit form or meaning of something (Aristotle)
preexperimental designs
Campbell and Stanley's term for research designs in which there is such a total absence of control that they are of minimal value in establishing causality
repeated-measures design
Statistical design in which the sampling units generate two or more measurements
experimenter expectancy effect
An experimenter-related artifact that results when the hypothesis held by the experimenter leads unintentionally to behavior toward the subjects that, in turn, increases the likelihood that the hypothesis will be confirmed
demand characteristics
Orne's term for the mixture of hints and cues that govern the participant's perception of a) his or her role as the research subject and b) the experimenter's hypothesis
quasi-control subjects
Research participants who are asked to reflect on the context in which an experiment is conducted and to speculate on the ways in which the context may influence their own and other subjects' behaviors
within-subjects design
Statistical design in which the sampling units (e.g. the research participants) generate two or more measurements
material causality
Emphasis on the composition or substance of which something is made (aristotle)
method of agreement
If X, then Y. X is a sufficient condition of Y
final causality
An emphasis on the end goal or objective (Aristotle)
temporal precedence
The principle that the cause must be shown to have occurred before the effect
one-group pre-post design OXO
A preexperimental design in which the reactions of only one group of subjects are measured before and after exposure to the treatment
A plausible threat to internal validity when an event or incident that takes place between the pre and postmeasurements contaminates the results of research not using randomization
internal validity
The degree of validity of statements made about whether X causes Y
random assignment
Same thing as randomization

Deck Info