Unit 3 Flashcards
Data
The quantitative results of deliberate, planned, and usually controlled observation
Datum
Singular form of the term ‘data’
Characteristics of a good response definition
Objective, clear, complete
Continuous response measures
Directly measure a dimensional quantity of behavior
Discontinuous response measures
Do not measure bx directly
Dimensional quantities of continuous response measures
Event, latency, duration, IRT
Event Recording
Record time observation began Count the responses Record time observation ended Divide: Count/unit of time Report as rate per unit of time
Event recording of restricted operants
Record time observation began Record each antecedent Record each response Record time observation ended Report as (Responses/Antecedents)/unit of time
Duration per session
total amount of time an individual engages in an activity
Duration per occurrence
amount of time a target behavior occupies
Latency Recording
Specify when to start recording (onset or offset of the stimulus)
Inter-response time recording
Start timing at the END of the response
cycle.
Stop timing at the BEGINNING of the
next response cycle.
Estimating IRT’s
When given the rate, provided that the
variability is not too great, or that there
are no outliers
Dimensionless quantities of discontinuous
response measures
Percent occurrence Trials to criterion Discrete categorization Partial interval recording Whole interval recording Momentary time sampling PLACHECK
Percent occurrence
Similar to event recording of a restricted
or discriminated operant which has been
converted into a percent
Trials to criterion
The number of consecutive opportunities to respond required to achieve a performance standard. Record each opportunity to respond until the performance standard is met.
Trials to criterion steps
- Determine what one trial will be
- Decide how to report (number of trials
or number of block trials) - Record count as the measure
- Present data
Discrete categorization
A method for classifying responses into
discrete categories
Partial interval recording
A discontinuous response measure in which a recording session is broken into short intervals of time; occurrence is recorded if a response happens during any part of the interval
whole interval recording
A discontinuous response measure in which a recording session is broken into short intervals of time; occurrence is recorded if the behavior occurs for the whole interval
Momentary time sampling
A discontinuous response measure in
which a response is recorded as
occurring only if it occurs at the point in
time in which an interval ends.
PLACHECK
A group of individuals is observed at the end of an interval Count how many of individuals are engaging in the target behavior(s) Compare with the total number of individuals Percent of individuals engaging in behavior(s)
Factors to consider when selecting a response measure
The dimensional quantity of interest.
The estimated rate of the behavior.
Whether to measure responses or
episodes.
Permanent products
measuring the results of behavior
reliability
the consistency of measurement
Interobserver agreement
The coefficient of agreement between two or more independent observers. Usually calculated as a percentage by dividing the number of agreements by the total number of agreements plus disagreements, then multiplying by 100.
Uses for IOA
Competence of new observers Detecting observer drift Validate collection methods Increase confidence that interventions are responsible for behavior change
IV integrity
The degree to which an intervention is
implemented as described/designated
Two main methods of IOA
Total count, percent agreement
mean count per interval
Total agreement in each interval/
Number of intervals
X 100
Exact count per interval
# of intervals with 100% agreement/ Number of intervals X 100
IOA should be at or above
80%
IOA should be collected and scored for a minimum of ___ of observations
33%
