Problem 7 Flashcards
causal relationship
changes in the value of one variable directly or indirectly causes changes in the value of the second
correlational relationship
two variables simply change values together and may or may not influence one another, measures only linear association, bidirectional/unidirectional
correlational research
determine whether two (or more) variables covary and, if so, to establish the directions, magnitudes, and forms of the observed relationships; non-experimental research
third-variable problem
possibility that a third, unmeasured variable influences both observed variables in such a way as to produce the correlation between them
directionality problem
if two variables are causally related, correlational designs cannot determine in which direction the causal arrow points
predictor variable
used to make predictions
experimental research
strong control over variables, allow you to establish whether variables are causally related
experimental groups
receives the experimental treatment
control group
is treated identically except that it does not receive the treatment
demonstration
type of non-experimental design, resembles an experiment, lacks manipulation of an independent variable; useful for showing what sorts of behaviors occur under specific conditions, but cannot identify relationships among variables
confounding variable
varies along with your independent variable
- -> damages internal validity
- -> not able to establish causal relationship between independent & dependent variable
- -> experimenter bias; avoid with blind technique
quasi-independent variable
correlational variable that resembles an independent variable in an experiment
cross-sectional design
select several participants from each of a number of age groups
generation effect
influence of generational differences in experience, which become confounded with the effects of age per se –> is confounding = threat to internal validity
longitudinal design
single group of participants is followed over some time period
cross-generational effects
conclusion drawn from the longitudinal study of a particular generation may not apply to another generation
subject mortality
loss of subjects from the research over time
–> threats to external validity
multiple-observation effect
multiple observations of same participants over time
cohort-sequential design
combines the two developmental designs and lets you evaluate the degree of contribution made by factors such as generation effects
Simpson’s paradox
association or comparison that holds for all of several groups can reverse direction when the data are combined to form a single group
aggregating data
we ignore variable which then become lurking variables
confounding
two variables’ effects on response variable can’t be distinguished from each other; confound variable: explanatory/independent variable, lurking variable, both
conceptual confound
overlapping measurements of cause & consequence (variable)
extraneous variable
all variables other than the specific variables that are studied, only becomes confound if it systematically varies with the two variables that are studied
common-response
changes in response and explanatory variable are caused by changes in lurking variables; lurking variable Z explains association
mediator variable
A –> D –> C
moderator variable
relationship between A and B differs according to the values of E; variable moderates the relationship between two other variables, acting like a gate
placebo control group
condition in which participants receive a placebo instead of the actual treatment
manipulation check
additional measure to assess how the participants perceived & interpreted the manipulation and/or to assess the direct effect of the manipulation
quasi experiment
tries to establish a causal relation between one variable and another; does not directly manipulate a variable but tries to isolate a causal influence by selection rather than manipulation
covariation
two variables are associated
precedence
the causal variable precedes the effect variable
matching
divide variable with much influence equally over groups
blocking
limited population = keep suspected confounder constant (only test women)
criterion variable
value is being predicted
