Chapter 3/4 Flashcards

1
Q

When and when not to use true-false response format

A

.use for questions of fact like “i attended church last week”
.do NOT use for measuring attitudes and feelings! not clear-cut. (most would say “it depends!”)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Give respondents no more thatn ____ possible response options.
BUT why 12-pt can be used?

A

Seven! Can only hold 7 in short term memory.12pt scales with five scale labels can be helpful, select an area then fine tune based on the distance from verbal labels.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

free response format items good but…

A

respondents usually don’t know HOW .detailed to be in their answers (“tell me everything you did today”)
.if verbal, have to code all responses so can make them statistically meaningful

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

free response format

A

participant provides an unstructured response. number or words…

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

rating scale response format

A

used for questions about behaviors thoughts or feelings

x-point scale.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Double-barrelled question

A

asks more than one question but provides respondent opportunity for only one response
“do you eat healthfully and exercise regularly?”

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

____ info should precede the key idea of item

A

if question contains conditional or hypothetical info, should precede central part of question
better to ask “If a good friend were depressed for a long time, would you suggest he or she see a therapist” than other way around.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What is wrong with “How do you feel about your mother?”

A

Makes assumptions about participant based on own experiences! What if the person doesn’t have a mom, is adopted?
Respondent that doesn’t know about a current event could not give their opinion on it!

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What’s wrong with “What kind of drugs do you take?”

A

Not specific or precise in phrasing. One might list recreational drugs while one might list prescriptions, while one might list over-the-counter!

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Five types of psychophysiological or neuroscientific measures

A

neuroimaging (fMRI e.g.)
measures of neural electrical activity (EEG)
measures of autonomic nervous system activity (hr, bl presure, skin temp)
blood and saliva assays
precise measurement of overt reactions (sexual arousal, special sensors can measure blushing)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

two ways to increase reliability of observational methods

A

.clear and precise operational definitions!!

.raters should practice using the coding system in advance

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

3 LATENCY types of temporal measures (also duration is another temporal measure k)

A

.reaction time (time b/t stimulus and response)
.task completion time (length takes to solve/complete task)
.behavior latency (time b/t two behaviors)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

narrative vs field notes

A

narrative: capture as completely as possible everything participant said or did during a time
.field notes more a summarization
.these must be CONTENT ANALYZED to be of any meaning!

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

reactivity

A

textbook term for how people behave diff when they know they are being watched

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

unobtrusive measures

A

measures not directly part of participant’s behavior

looking at alcohol bottles in garbage cans behind houses instead of asking directly, to get more truthful responses

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Construct validity

A

Convergent and discriminant validity!

17
Q

Criterion-related validity

A

Predictive vs Concurrent!

18
Q

Split-half reliability

A

divide items on scale into two sets. correlate responses. should correlate highly if measuring same construct
.Should go above .70!

19
Q

Cronbach’s alpha coefficient

A

average of ALL possible split-half reliabilities. high interitem reliability if Cronbach’s exceeds .70!

20
Q

item total correlation

A

correlation between one item and the sum of all other items on the scale
.researchers want item-total correlation to be ABOVE .30!
so items measuring diff aspects of a construct should be somewhat correlated

21
Q

Ordinal scale

A

just a ranking, like who finished in each place in a race

NO indication of interval/distance between participants on a dimension

22
Q

Nominal scale

A

like doing -1 if you are married, 1 if you are not