Domain G: Data Collection Analysis Flashcards
Types of Measurement
Frequency/rate
Frequency/Rate
-total number of occurrences of a behavior / by the observation time.
-number of responses per unit of time.
-usually recorded as count per hour, count per day, count per week, count per month.
Types of Measurement
Duration
Duration
-amount of time in which a behavior occurs.
-measures the amount of time an individual engages in a behavior.
-helpful in measuring behaviors that occur for too long or too short of a period of time.
-good for measuring behaviors that occur at high rates, or continuous behaviors.
Type of Measurement
Response Latency
Response Latency
-measures the time elapsed between the delivery of a stimulus and the onset of a response (I.e., time between the delivery of the SD and when the learner responds).
-how long does it take the learner to respond?
Type of Measurement
Interresponse Time
Interresponse Time(IRT)
-Measures the time between responses.
-IRT is related to rate of behavior, shorter IRTs means less time elapsed between responses equaling higher rate of responding. While longer IRTs are associated with lower rates of behavior.
Type of Measurement
Force/Magnitude
Force/Magnitude
-refers to the intensity in which a response is emitted.
-some behaviors require a certain amount of force, or intensity used when the behavior is emitted to obtain the desired outcome (e.g., tone of voice, speaking at a volume that is considered too loud or too soft).
Types of ABA Graphs
Line Graphs
Graphical Displays of Data
-Provide a visual analysis of data.
-Used in ABA to organize, store, interpret, and communicate results.
Line Graphs
-Aka frequency polygon
-Most common graph used in ABA
-Each data point represents some quantifiable dimension of the target behavior, or dependent variable, in relation to the intervention being used, or independent variable.
Bar Graph
Bar Graph
-Aka Histogram-Similar to the line graph
-Bar graph does not have distinct, successive data points measured through time.
-Allow for quick and easy comparisons across participants/conditions.
-Serves2 major functions in ABA: (1) used for displaying and comparing discrete sets of data that do not share a common underlying dimension in which the horizontal axis (x axis) may be scaled. Example: results of the FAST are displayed in a bar graph.(2) Bar graphs provide a visual summary of participant or group performance across multiple conditions.
-Do not show variability or trend lines.
-Typically depict central tendencies (I.e., mean, median).
Cumulative Records
Cumulative Records
-Developed by Skinner
-Utilizes a cumulative recorder, a device that enables the subject to “draw” its own graph. For Example: Each time the bird responds, the pen moves across the paper. A horizontal line represents no response, and a steep line represents an increase in responding.
-The term cumulative is used because the number of responses made during each observation is added to the total number of responses from previous observations. -Used to record frequency, latency, and duration.
Scatter Plots
Scatterplots
-Data points are not connected.
-Patterns or clusters of data points suggest relationships.
-May be used to identify relationships between different subsets of data.
-Often used in ABA to provide temporal distributions of the target behavior (I.e., does the behavior occur during a certain time of the day?).
Data Collection Methods
Rate of responding
Duration
Response Latency
Magnitude
A percentage expresses the proportional quantity of some event in terms of the number of times the event occurred per 100 opportunities that the event could have occurred.
Rate of responding, is defined as the number of responses per unit of time
Duration, the amount of time in which behavior occurs, is the basic measure of temporal extent
Response latency (or, more commonly, latency) is a measure of the elapsed time between the onset of a stimulus and the initiation of a subsequent response
Magnitude refers to the force or intensity with which a response is emitted.
Continuous vs. Discontinuous measurement systems
Partial Interval Recording
Whole Interval Recording
Momentary Time Sampling
When using partial-interval recording, the observer records whether the behavior occurred at any time during the interval.
With whole-interval recording, the observation period is divided into a series of brief time intervals (typically from 5 to 10 seconds). At the end of each interval, the observer records whether the target behavior occurred throughout the interval.
An observer using momentary time sampling records whether the target behavior is occurring at the moment that each time interval ends.
Types of IOA
Total Count
Trial by Trial
Interobserver Agreement (IOA)
-The degree of agreement between 2 or more independent observers when measuring the same events.
-May be used as a way to assess the competence of new observers (may be used as a training technique).
-May be used to identify observer drift.
-Having multiple observers with a high degree of agreement supports that the target behavior is clear and unambiguous and system of measurement is not too difficult.
-A high degree of agreement amongst observers verifies that any variability in the data is not attributed to errors in measurement.
Total Count IOA
-Simplest indicator of IOA
-Compares the total count recorded by each observer per measurement period.
-Smaller count / Larger count X 100= % of agreement-A high degree of agreement does not mean that 2 observers had recorded the same occurrences of behavior.
Trail by Trial IOA
-Agreement between two observers who measure the occurrence or non occurrence of discrete trials
-# of trials in agreement/total # of trials x 100
Visual analysis (e.g., trend, level, variability)
Variability
Level
Trend
Visual Analysis is used in ABA to answer two questions: 91) did behavior change in a meaningful way? (2) To what extent can the observed change be attributed to the independent variable (intervention)?
Variability
-different outcomes in the behavior being measured(how often, to what extent)
-A high degree of variability usually means little control over the factors influencing behavior.
-Increased variability means more data points will be needed to establish a stable pattern of responding.
Level
-The value on a vertical (y) axis that a set of behavioral measures converge.
-Depicts the degree of stability and/or variability as well as the amount of change between one level to the next.
Trend
-Trend represents the overall direction of the data path.
-Described as: increasing, decreasing, or zero trend.
-Trend may be visually represented by drawing a straight line through the data (I.e., a trend line).
Characteristics of trustworthy measurements
Reliability
Reliability describes the extent to which a “measurement procedure yields the same value when brought into repeated contact with the same state of nature” Like validity and accuracy, reliability is a relative concept; it is a matter of degree. The closer the values obtained by repeated measurement of the same event are to one another, the greater the reliability.
Characteristics of trustworthy measurements
Accuracy
Accuracy
When used in the context of measurement, accuracy refers to the extent to which the observed value, the quantitative label produced by measuring an event, matches the true state, or true value, of the event as it exists in nature
