CH05 - Quality Measurement IOA

Question 1

IOA Defined

Answer 1

The degree to which TWO or more INDEPENDENT observers REPORT the SAME VALUES for the same events.

Question 2

IOA Benefits

Answer 2

Benefits:

1. DETERMINE COMPETENCE of new observers
2. DETECT OBSERVER drift
3. JUDGE clarity of DEFINITIONS and system
4. INCREASE BELIEVABILITY of data. (Changes in data reflect changes in the clients behavior not who was taking data)

Question 3

IOA requisites

Answer 3

1. must use SAME measurement SYSTEM
2. must measure SAME EVENT
3. must be INDEPENDENT

Question 4

Three categories for Calculating IOA

Answer 4

1. Event recording IOAs (tally count)
2. Timing IOAs (yes or no)
3. Time sampling IOAs (yes or no)

Question 5

1. Event Recording IOA’s - Methods

Answer 5

1. Total count
2. Mean Count-per-Interval
3. Exact Count-per-Interval
4. Trial-by-Trial Count

Question 6

2. Timing/Duration IOA’s - Methods

Answer 6

1. Total Duration

2. Mean Duration (or IRT)-per-Occurrence

Question 7

3. Time Sampling / Interval Recording IOA - Methods

Answer 7

1. Interval-by-Interval IOA
2. Scored Interval IOA
3. Unscored Interval

Question 8

Total Count IOA

Answer 8

Simplest and Crudest (Interval by Interval, Point by point)

total c. / total c. x 100
(Smaller) / (Larger) X 100%

20/25 = .8 x 100 = 80% Total Count IOA

Question 9

Mean Count IOA

Answer 9

AVERAGE Each INTERVAL add (+) together then divide (/) by TOTAL number of intervals. (%)

(Interval 1 + Interval 2 + Interval “n” IOA) / n intervals x 100

Interval 1 (small tallies/large tallies = %) 4/5 = 80%, etc.
80% + 78% + 65% + 72% + 79% = 374     374/5 = 74.8

Question 10

Exact Count IOA (Most stringent)

Answer 10

Total number of intervals in agreement by both observers then divide by total number of trials/intervals.

(# of intervals with 100% agreements) / n intervals x 100 = Exact count- per-interval IOA%.

2 / 5 = .40 x 100 = 40%

Question 11

Scored Interval

Answer 11

Low Rates of bx

number of intervals both scored divided by at least one scored

Question 12

Unscored Interval

Answer 12

High Rates of bx

number of intervals with no occurrences divided by at least on unscored

Question 13

How often should IOA be obtained?

Answer 13

during each phase of a study
across days of the week, times of day, setting, observers
20% (minimum sessions)

Question 14

How should IOA be recorded?

Answer 14

Narrative description (most common/simplest)
Table
Graphic Display

Question 15

Acceptable scores

Answer 15

Closer to 100%

No less than 80%

Question 16

IOA Considerations for Implementation

Answer 16

1. During EACH CONDITION and PHASE of a study
2. DISTRIBUTED across days of the week, time of day, settings, observers
3. MINIMUM of 20% of sessions, preferably 25-30%
4. More FREQUENT if COMPLEX SYSTEMS