Measurement dimensions (e.g. rate, duration, percentage)
- Rate is a measured used in ABA therapy that calculates the number of times a behavior occurs in a specific time interval. A rate will always be expressed as an occurrence per hour. To determine the rate of behavior you divide the frequency by the time measure.
- This type of measurement procedure that measures the amount of time a behavior occurs from its start to its finish using an appropriate unit of time (seconds, minutes, etc). Duration data is typically collected for behaviors that occur across time in episodes
- Percentage: Count the number of intervals during which the behavior occurred. Divide this number by the total number of intervals and multiply by 100 to determine the percentage of intervals during which the behavior occurred
Measurement procedures (e.g. event recording, timing, time sampling)
- Event recording is a process for documenting the number of times a behavior occurs. An observer using event recording makes a tally mark or documents in some way each time a student engages in a target behavior. The observer also records the time period in which the behavior is being observed
- Time: Set up a time frame where you will measure the behavior (e.g. minutes, hours, days, etc.). Note the time when the first behavior happens. Tally each behavioral tick that occurs until you reach the time frame you originally established. Divide the number of behaviors with the total amount of time to get the frequency
- Time Sampling: Refers to a variety of methods to record behavior at specific moments. One divides the observation period into intervals and then record either the presence or absence of a behavior within or at the end of the interval
Skill Acquisition Data
First evaluate the student’s ability to perform the targeted skill. This data provides a ‘baseline’ evaluation that can be used to compare the student’s progress over time. During the initial evaluation, the student is not given any prompts or reinforcement to complete the skill. Essentially, the teacher wants to evaluate what the student can do independently. Once the assessment has been completed, a training objective can be written that specifies the outcome to be achieved
Problem Behavior Data
With data collection and analysis, it becomes easier for professionals to understand behavior patterns and to measure the progress of the individual. Most importantly, data provides accurate and specific information that allows clinicians to make informed and educated decisions (evidence-based decisions) regarding the individuals intervention to help the individual achieve great outcomes in their learning and developing allowing that individual to live toward their fullest potential
Graphing
Graphing in applied behavior analysis is how we determine if the treatment being provided to your child is showing a positive change. Graphs also allow us to adjust our interventions unique to the client to provide the best care applicable. When asked for clarification on reliability and validity we can refer to these graphs and feel confident when explaining the reason for our interventions. In this field we take pride in making sure that everything we do is based on reliable and valid empirical research
Inter observer Agreement (IOA)
- The most commonly used indicator of measurement quality in ABA is inter observer agreement (IOA), the degree to which two or more observers report the same observed values after measuring the same events
- Researchers and practitioners use measures of IOA to (a) determine the competence of new observers, (b) detect observer drift, (c) judge whether the definition of the target behavior is clear and the system is not too difficult to use, and (d) convince others of the relative believability of the data
- There are numerous techniques for calculating IOA, each of which provides a somewhat different view of the extent and nature of agreement and disagreement between observers
- Percentage of agreement between observers is the most common convention for reporting IOA in ABA
- IOA for data obtained by event recording can be calculated by comparing (a) the total count recorded by each observer per measurement period, (b) the counts tallied by each observer during each of a series of smaller intervals of time within the measurement period, or (c) each observer’s count of 1 of 0 on a trial-to-trial basis
- Total count IOA is the simplest and crudest indicator of IOA for event recording data, and exact-count-per-interval IOA is the most stringent for most data sets obtained by event recording
