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;
61 Cards in this Set
- Front
- Back
3 basic principles of Belmont report |
Respect for persons, beneficence-maximize benefits, minimize risk, justice-benefits and burdens are distributed equally |
|
informed consent |
statement informing potential research participants of purposes, procedures, risks, benefits of research; participation is voluntary |
|
key components of informed consent |
1) made fully aware of nature and purpose 2) consent is voluntary 3) has legal capacity to give consent 4) obtaining consent lies with researcher |
|
purpose of an IRB |
to protect the rights of research participants, make sure Belmont Report is followed |
|
3 categories of IRB review |
exempt- no review expediated- minimal risk full review-risks are more than minimal |
|
scientific misconduct due to fabrication or falsification |
they made up or or changed data numbers to influence the results |
|
academic dishonesty due to plagiarism |
they passed off someone else's work as their own without citing it |
|
most crucial element in selecting a sample from a population |
make sure sample is representative of population |
|
probability sampling |
sampling technique in which the probability of selecting participant is known
|
|
nonprobability sampling |
probability of selecting participants in unknown |
|
simple random |
equal chance of being selected; selection of one element does not influence selection chances adv-bias free disadv-may not be representative |
|
systematic |
choose every xth element adv-quick, efficient disadv-not random |
|
stratified random |
divide into subgroups, then pick from subgroups adv-representative sample disadv-not completely random |
|
cluster sampling |
sample is naturally occuring group/cluster adv-participant demographics are spread out, more practical, cheap disadv-if small cluster, not equal size |
|
convenience |
get people who are most convenient adv-easy , quick disadv- not generalizable |
|
purposive sampling |
select people with traits that are critical to result adv-qualitative disadv-not large sample size |
|
procedures involved in purposive sampling |
depends on target population and how generalized you want results to be |
|
five factors that influence researcher's decision on sample size |
preliminary studies, money and time, documenting something rare, variability of population, if looking for sample difference you need a larger sample size |
|
p-value |
relationship between variables is due to real difference and not sampling error p<.05= reject null, low sampling error p>.05=fail to reject, high sampling error |
|
components required when writing hypothesis |
complete sentence identify IV and DV significance use association or relationship when talking about correlation |
|
alpha level |
probability level selected that warrants rejection of null hypothesis, usually .05 |
|
manipulation vs. control |
manipulation is where you actively change a variable to see its effects control is where you take out variables for research |
|
internal validity |
how valid the findings are within the study |
|
external validity |
degree to which findings in study can be inferred or generalized |
|
threats to internal: History |
things happening past or present that will affect scores or treatment |
|
threats to internal: maturation |
maturation of participants can affect performance and change results |
|
threats to internal: testing |
act of taking a test can change scores |
|
threats to internal: instrumentation |
affected by type, calibration, adjustment |
|
threats to internal: stats regression |
people who score extreme first time will score closer the mean the second time |
|
threats to internal: selection bias |
researcher is biased in selecting participants |
|
threats to internal: experimental mortality |
loss of participants means sample may not be representative anymore |
|
threats to external: expectancy |
if you expect a certain result, you may be biased toward it |
|
threats to external: reactive effects of experimental setting |
experimental treatment has unique effect on participants that would not be observed in another setting |
|
threats to external: multiple treatment interference |
effect of prior treatment on response to current treatment |
|
pre-experimental design |
no random selection or random assignment, poor control |
|
what determines type of review for IRB |
high vs. low risk, high=full, low=expediated |
|
population validity |
the extent to which the resultscan be generalized from the experimental sample to a defined population |
|
ecological validity |
extent to which the results of an experiment canbe generalized from the set of environmental conditions in the experiment toother environmental conditions |
|
true experimental design |
random sampling and assignment, high level of control |
|
quasi-experimental |
lack either random selection or assignment, moderate level of control |
|
using physical manipulation to control variables |
can control environment and experience |
|
using selective manipulation to control variables |
choose certain participants and matched pairs |
|
placebo effect |
treatment that has no effect, gives participant idea that they are receiving treatment |
|
john henry effect |
control group will try harder if they know they are not supposed to be as good as experimental group |
|
experimenter bias |
the effect experimenter has on results can affect methodology, treatment, and data collection |
|
hawthorne effect |
participants may perform differently if they know they are in a study or being watched |
|
central tendancy error |
rate participants in middle of scale instead of rating extremes |
|
rating affect as source of error |
human error can affect results, discrepancies in rating, halo effect |
|
single-blind study |
participants don't know purpose of study |
|
double-blind study |
participants not aware of purpose of study or who is in what group |
|
administered questionnaire |
give by researcher, response is manadory and immediate |
|
distributed questionnaire |
don't have to get it back, not direct, may take while |
|
reliability and examples |
consistency of response can do questionnaire on two different days, use opposite terms |
|
validity and example |
degree to which answers are correct usually determine by jury; judge content, construction, and use |
|
norm referenced |
rating on best to worst scale, percentile ranks |
|
criteron referenced |
pass or fail, drivers test |
|
importance of format elements |
appearance-professional, typed neat demographics at end keep length to one page more likely to get returned |
|
privacy |
capacity of individuals to control when and under what conditions others will have access to their info AMT OF CONTROL WE HAVE OVER INFO |
|
condfidentiality |
ability to link info/data collected during study to person's identity HOW DISCLOSED PERSONAL INFO MAY BE USED |
|
longitudinal study |
follow one group over x number of years |
|
cross-sectional study |
take data from several groups at one time period |