RM 11 Flashcards
Threats to internal validity
Did the independant variable really cause the difference
Design confound
result in an alternative explanation of the results of an experiment because there has been a variable that varied systematically along with the independent variable
selection effect
occurs in an experiment when the kinds of participants in one level of theindependent variable are systematically different from those in the other. (If participants choosethe group to be in)
order effect
different orders in which the questions are presented may influence respondents’ answers
Potential internal validity threats in one group, pretest/post test designs
a. maturation threats/ spontaneous remission
b. history threats
c. regression threats
d. attrition threats
e. testing threats
f. instrumentation threats
maturation threat
occurs when changes in behaviour emerge more or less spontaneously over time
ex: patient improves just because time passes
can be prevented by: using appropriate comparison group
history threat
external threat, independent of the study may influence the participants at the same time
then becomes unclear whether the change in behaviour is caused by the independent variable or the external factor
regression threats
- Ex with italy’s win 5-0 football: the extreme score was a lucky combination of random factors that did not repeat itself in the next game, so the next game’s score grossed back toward the average: the mean
- So it’s when extreme outcome is cause by a combination of random factors that re unlikely to happen in the same combination again, so the extreme outcomes gets lass extreme over time
attrition threat
threat occurs if participants leave the experiment before post test, and are systematic in one condition
testing threats
The effect of being tested twice may change people’s behaviour or something, such as order effect (remembering the stuff from before, or having practiced)
Instrumentation threats
Measurement intsruments differ bewteen pre and post test, so we think it’s a change in the participants when it’s actually your fault bitch
Types of internal validity threats for studies with placebo group
Observer bias
Observer effect
Demand characteristic
can be avoided by using: double-blind study
three potential internal validity threats in any study
Observer bias
Demand characteristics
Placebo effect
Observer bias
Researcher may see differences between the conditions that are not actually there
can be avoided: by using double-blind study
Observer effect
Researcher may treat participants differently dependant on the condition they’re in
can be avoided: by using double-blind study
Demand characteristic
Participant may behave according to the research hypothesis
can be avoided by using: double-blind study
double-blind study
neither the participants nor the researchers know who is in the treatment group and who is the comparison group
alternative: masked design
masked design
could be used in which participants know in which group they are but the observers don’t ???
placebo effect
participants receive a treatment and actually improve, but only because they believe they are receiving a valid treatment
can be avoided by using: double blind placebo control study
double blind placebo control study
one group receives the actual treatment, and the other a placebo but both particpants and researchers don’t know which is which
null effect
experiments don’t show any significant relationship
independent variable did not make a difference on the dependent variable
result of a poor experimental design
internal validity
does my
Internal validity : within group pretest/post test
a. maturation threat
b. history threat
c. regression to the mean
d. attrition threats
e. testing threat
f. instrumentation threat
Internal validity threats: within group, between group
a. placebo
can be resolved by double blind experiment
b. observer bias
can be prevented: using a double blind or masked design
c. demand characteristics
can be prevented by double blind experiment
mixed cantorial design with CONTROL GROUP
non-specific effect
non-specific effect
effects that are not due to the treatment but due to the expectation that you will be treated
waiting list group
placebo effect