Use LEFT and RIGHT arrow keys to navigate between flashcards;
Use UP and DOWN arrow keys to flip the card;
H to show hint;
A reads text to speech;
38 Cards in this Set
- Front
- Back
Belmont Principles (5)
|
TRIBJ
1)trust 2)respect for persons 3)integrity 4)beneficence 5)justice |
|
to help solve the problem of carryover effect, use...
|
counterbalancing
|
|
respect for persons
|
voluntary participation, informed consent
|
|
beneficence
|
benefits outweigh the risks
|
|
justice
|
selection process is fair; use science for things that benefit society
|
|
trust
|
debriefing, deception, confidentiality, anonymity
|
|
internal analysis
|
an analysis of the effects of nonmanipulated variables-like looking at the effects of subject variables or the effects of subject variables and treatments on the dv
|
|
Cross-lagged Panel Technique
|
collect correlational data on 2 or more separate occasions (with the idea that causes precede effects)
|
|
what correlational design provides a partial solution to the problem of direction of causality?
|
Cross-lagged Panel Technique
|
|
one-group pretest-posttest design
|
a pseudoexperimental design where one group of subjects is pretested, receives a treatment, and is then posttested
|
|
one-shot case study (posttest-only design)
|
a single group is observed after a treatment (no comparison)
|
|
history, maturation, testing, instrumentation, and mortality are all...
|
types of threats to internal validity
|
|
threats to internal validity
|
variables that are beyond the control of the researcher and prevent him from determining that the treatment was the sole cause of the outcome
|
|
history
|
events that occur (other than the treatment) between the treatment and measurement of outcome that may have an effect on the outcome
|
|
maturation
|
the effects of internal processes that unfold within subjects as a function of time (getting tired, bored, hungry, etc.)
|
|
testing
|
effects of subjects knowing they're being tested on the outcome; effects of observation on outcome rather than effects of treatment
|
|
instrumentation
|
effects of changes in the observer/researcher (grow tired, hungry, etc.)
|
|
mortality
|
loss of subjects; this could make a difference in the results since those who left the study may have had different results than those who stayed for some reason
|
|
threats to internal validity occur in...
|
one-group pretest-posttest design
|
|
in the one-shot case study design, the only comparisons researchers can kind of make to the group after treatment is ...
|
remembered impressions of other groups or assumptions of what the group might have been like without the treatment
|
|
one-group pretest-posttest design
|
measure the group before and after the treatment
|
|
pseudoexperiment
|
don't have good methods for comparison
|
|
threat to internal validity for static-group comparison design
|
selection effects
|
|
selection effects (as a threat to internal validity for a Static-group comparison desigh)
|
the effects of initial differences between the two groups not caused by the treatment
|
|
Static-group comparison design
|
a pseudoexperimental design which uses 2 groups of subjects, only one of which receives a treatment before the results are measured
|
|
main difference b/w experiments and quasi-experiments
|
in quasi-experiments, subjects are not randomly assigned to experimental groups whereas they are in experiments
|
|
2 kinds of quasi-experiments
|
interrupted time series design, and nonequivalent control group design
|
|
interrupted time series design
|
(uses a within-subjects design); the effect of the IV is assessed by comparing multiple observations of the same group of people-either b4 and after administration of one level of treatment or after the administration of different levels of treatment
|
|
nonequivalent control group design
|
(uses a b/w-subjects design); the effect of the IV is assessed by comparing 2 or more groups of subjects-subjects who are not assigned at random to their groups
|
|
2 fatal mistakes of the 1936 Literary Digest Poll
|
1)only mailed to telephone and car-owners so it was biased
2)voluntary response |
|
stratified random sampling
|
the population is first divided into a number of parts or 'strata' according to some characteristic, chosen to be related to the major variables being studied
|
|
double-barrel questions
|
asks about two different items
|
|
ceiling effect
|
when test questions are too easy and most people get high scores so their scores won't change much with the treatment(high scores=ceiling)
|
|
floor effect
|
when test questions are too hard and most people get low scores-scores won't change much (low scores=floor)
|
|
Time-Series Experiment
|
a single administration of a treatment is embedded within a series of observations; like having the subjects come over every night and one night giving them alcohol and observing them that night and every other night w/out alcohol
|
|
what is the major threat to internal validity for a time-series experiment design?
|
history: other events happen in the subjects' lives between the various observations
|
|
Equivalent Time-Samples Design
|
administer the treatment more than once during the series of observations (the same as time-series experiment but administer treatment more than once)
|
|
role-playing studies
|
alternatives to deception experiments in which subjects are asked to behave as if they were in a particular situation; subjects collaborate with experimenters and play the role of someone who is not in an experiment setting or who does not know the true purpose of the research
|