8. Observational Methods 2 - Coding and Reliability Flashcards

1
Q

A coding scheme is a m____ i____

A

measuring instrument

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

The outcome of the application of a coding scheme is a set of q____ data, and those data are then a____

A

quantitative, analysed

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

Principles of measurement:
1. There is no such thing as p____ measurement
2. Measurement are more or less a____. A____ is about c____ or v____ measurement (the degree to which measurements a____ c____ the phenomena of interest)
3. Measurements are more or less p____. P____ is about e____ (the degree to which measurements are r____ or r____)

A
  1. perfect
  2. accurate, accuracy, correct, valid, actually capture
  3. precise, precision, exactitude, reliable, replicable
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Intra-observer reliability means the s____ observer codes the same behaviour record at different times

A

same

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

Inter-observer reliability means that d____ observers i____ cded the same behavioural record either at the same time or at different times

A

different, independently

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

No strict standard currently exists for how much of a behavioural record to independently code, for purposes of reliability, but typically it is around __% to __% off the record.

A

15% - 20%

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

Consensus estimates are based on the a____ that two or more coders can come to e____ a____. This is typically used on n____ data, where different codes represent q____ d____ ideas

A

assumption, exact agreement
nominal, qualitatively distinct

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

Consistency estimates are based on the a____ that it is u____ for two or more coders to interpret a scale i____, but that the coders will c____ c____ phenomena with their understanding of the scale. Typically used on o____-to-c____ scales

A

assumption, unnecessary, identically, consistently classify, ordinal-to-continuous scales

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

Percent agreement does not correct for agreement by r____ c____.

A

random choice

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

Cohen’s kappa us the proportion of agreement after c____ for agreement by r____ c____

A

corrections, random chance

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

Correlation coefficient does not take into account v____ between c____

A

variance, coders

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

Cronbach’s alpha corrects for v____ between c____ and can e____ r____ for more than two coders

A

variance, coders, estimate reliability

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

Codes should be m____ e____ (each behaviour can only be put into one category) and e____ (all possible behaviours have categories)

A

mutually exclusive, exhaustive

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