1-5 Flashcards
What factors help you choose variables for your study?
research tradition (variables used in other studies)
theory (a theory you are referring too might give you ideas of variables)
availability of new techniques (fMRI, PET scans)
availability of equipment (variables are limited to the resources you have)
reliability
a measures ability to produce similar results when repeated measurements are made under identical conditions
a measures ability to produce similar results when repeated measurements are made under identical conditions
reliability
Why is it a good idea to use measures that are already established?
Reliability is known
Validity is known
What are the different types of reliability?
interrater reliability, test-retest reliability, split-half reliability and parallel forms of reliability
interrater reliability
used to establish the degree of agreement among observers when the measures involve making judgments or ratings
used to establish the degree of agreement among observers when the measures involve making judgments or ratings
interrater reliability
test-retest reliability
administering the same test twice, separated by a relatively long interval of time
administering the same test twice, separated by a relatively long interval of time
test-retest reliability
split-half reliability
one test is given at one point in time, then the test is split (looking at odds vs evens)
one test is given at one point in time, then the test is split (looking at odds vs evens)
split-half reliability
parallel forms
two different forms of the same test (one given at tie point a, the second form given at time point b)
two different forms of the same test (one given at tie point a, the second form given at time point b)
parallel forms
validity
the extent to which a measure assesses what you intend it to measure
the extent to which a measure assesses what you intend it to measure
validity
What are the types of validity?
face, content, criterion-related, construct
face validity
how well a measurement instrument “appears” to measure it was designed to measure
how well a measurement instrument “appears” to measure it was designed to measure
face validity
content validity
how adequately the content of a test samples the knowledge, skills, or behaviors that the test is intended to measure
how adequately the content of a test samples the knowledge, skills, or behaviors that the test is intended to measure
content validity
criterion-related validity
how adequately a test score can be used to infer and individual’s value on some”criterion” measures
how adequately a test score can be used to infer and individual’s value on some”criterion” measures
criterion-related validity
concurrent validity
when the scores on your test and the criterion are collected at about the same time
when the scores on your test and the criterion are collected at about the same time
concurrent validity
predictive validity
comparing the scores on a test with the value of a criterion measure observed at a later time
comparing the scores on a test with the value of a criterion measure observed at a later time
predictive validity
construct validity
determined by whether those who score high or low on the measure behave as predicted by theory
determined by whether those who score high or low on the measure behave as predicted by theory
construct validity
What are the scales of measurement?
nominal, ordinal, interval, ratio scale
nominal
values differ in quality and not quantity
values differ in quality and not quantity
nominal
ordinal
rank ordering of categories
rank ordering of categories
ordinal
interval
spacing between values along the scale are known, but zero point is arbitrary
spacing between values along the scale are known, but zero point is arbitrary
interval
ratio scale
spacing between values along the scale are known, but has a zero point
spacing between values along the scale are known, but has a zero point
ratio scale
What are the range effects?
ceiling: when the variable reaches its highest possible value
and
floor: when the variable reaches its lowest possible value
What are the types of dependent variables (DV)?
behavioral measures, physiological measures, self-report measures, implicit measures
behavioral measures
record actual behavior of subjects
may not help you find the cause for the behavior
record actual behavior of subjects
behavioral measures
physiological measures
physical measure of body function (e.g. EEG)
physical measure of body function (e.g. EEG)
physiological measures
self-report measures
participants report on their own behavior or state of mind
fake-good (say you’ve never taken drugs to look good)
fake-bad (say symptoms are worse to get Rx)
participants report on their own behavior or state of mind
self-report measures
implicit measures
measures responses that are not under direct conscious control
measures responses that are not under direct conscious control
implicit measures
reactivity
participants’ behavior changes because they are in a study
participants’ behavior changes because they are in a study
reactivity
What are demand characteristics?
cues provided by the researcher and the research context that give participants information about a study
these can negatively affect the study
experimenter bias
when the behavior of the researcher influences the results of a study
two sources: expectancy effects and treating the groups differently
How do we avoid experimenter bias?
double-blind technique
blind-technique
automate the experiment (use computer to generate randomness)
pilot study
a small-scale version of a study used to establish procedures, materials, and parameters to be used in the full study
can help find what’s wrong with the study before starting it
a small-scale version of a study used to establish procedures, materials, and parameters to be used in the full study
pilot study
manipulation checks
measures to assess the success of your independent variables
advantages: provide info that can help to interpret the results
measures to assess the success of your independent variables
manipulation checks