C. Measurement, Data Display, and Interpretation Flashcards
Data
quantification of behavior change with direct and repeated measurement
Occurrence Data
Frequency, Rate, and Percentage
Count
Frequency - How often/many times a behavior occurs.
Rate
How often a behavior occurs over an amount of time.
Celeration
Measures how rates of responding change over time (rate/per unit of time).
Percentage
A measurement expressed as a portion of each hundred.
Trials to Criterion
A form of event recording. It is a derivative measure, calculated by measuring the number of practice opportunities needed for a person to achieve the pre-established criterion.
Duration
the amount of time a behavior happens
Latency
The amount of time between the antecedent (SD) and the start of the behavior.
Inter Response Time (IRT)
The amount of time between successive responses. (i.e. the end of one response to the beginning of another response.)
Topography
The way the behavior looks.
Magnitude
the intensity of the behavior
Direct Measures of Behavior
A way of taking data on a behavior of interest by observing the behavior itself and recording observable and measurable information about it.
Indirect Measures of Behavior
Data that are obtained by interviews, checklists and rating scales which include an individual’s subjective experience of target behavior. Indirect measures still gather information about the behavior of interest using interactions with people, but not through direct observation. Depending on the case, information could be gathered from the primary client themselves as well as other stakeholders.
Product Measures
Measuring a behavior after it occurred by examining the effects the behavior produced on the environment. Unlike direct and indirect measures, product measures sometimes do not involve people at all.
Whole Interval Recording
the observer marks down whether or not a behavior occurred throughout the entirety of the interval
Partial Interval Recording
the observer marks down whether or not a behavior occurred at all during the interval
Momentary Time Sampling
the observer marks down whether or not the behavior was occurring at the moment the interval ended
Planned Activity Check (PLACHECK)
involves an observer recording a tally of the number of learners engaged in an activity at the end of an interval
Validity
The extent to which we are measuring what we intend to measure. In other words, do our data points actually represent what we think/say they do?
Accuracy
The extent to which the observed value, the quantitative label produced by measure an event, matches the true state, or true value. Does the data match what actually occurred?
Reliability
The extent to which a measurement procedure produces the same value repeatedly. In other words, can you rely on it?
Measurement Artifact
data that appear to exist, but only because of the way that they were measured
Observer Drift
An unintended change in the way an observer uses a measurement system over time that results in a measurement error. This happens when the behavior being measure is not clearly operationally defined or the operational definition clarifying what is and what is not the behavior is not reviewed regularly.
Measurement Bias
Nonrandom measurement error; a form of inaccurate measurement in which the data consistently overestimate or underestimate the true value of an event
Observer Reactivity
An error in measurement that occurs when someone is watching you take data.
Interobserver Agreement (IOA)
is the extent to which two different observers agree about the occurrence of a behavior or a specific metric of a behavior
Total Count IOA
Compares the total sum of frequency data from each observer. It can be calculated as: IOA % = (Smaller sum / larger sum) x 100
Mean count-per-interval IOA/ Partial Agreement within Intervals IOA
is used to determine the average percentage of agreement between observers within each of the intervals. You have to complete two different formulas to calculate the final IOA percentage. The first formula must be done for each and every interval. The second formula is used to calculate the final IOA percentage at the end.
Formula 1:
Agreement % = (Smaller observation / larger observation) x 100
Formula 2:
Partial agreement within intervals % = (Sum of % agreement / # of intervals)
Exact count-per-interval IOA/ Exact Agreement IOA
is an even stricter measure of agreement than total count or partial agreement. It is a measure of the percentage of intervals in which both observers record the same data. It can be calculated as:
Exact agreement % = (# of exact agreement intervals / # of intervals) x 100
Trial by Trial IOA
is similar to exact agreement but can be used with non-numerical data as well (such as when an observer records “yes”/“no”). It also does not necessarily have to involve interval data.
Calculates the percentage of trials in which the observers agree. The formula can be written as:
Trial-by-trial % = (# of agreement trials / # of trials) x 100
Total Duration IOA
is the time-based sibling of total count IOA. It compares the sum of each observer’s duration recordings with one another.
It can be calculated by using this formula:
Total duration IOA % = (Smaller sum / larger sum) x 100
Mean Duration-per-occurrence IOA
is used to determine the average percentage of agreement between observers for each occurrence. Much like partial agreement within intervals, you must use two formulas.
Formula 1:
Agreement % = (Smaller observation / larger observation) x 100
Formula 2:
Mean duration-per- occurrence IOA % = (Sum of % agreement / # of intervals)
Interval by Interval IOA
the same thing as trial-by-trial but with intervals. It differs from exact agreement in that exact agreement involves frequency data but this type can involve non-numerical data (such as “yes”/”no” or “occurrence”/”non-occurrence”). The formula can be written as:
Interval-by-interval % = (# of agreement intervals / # of intervals)
Scored Interval IOA
measures the percentage of agreement between two observers within only the intervals in which either observer documented an occurrence of the behavior.
IOA % = (# of agreement intervals within occurrence intervals / total # of occurrence intervals) x 100
Unscored Interval IOA
is used to calculate the percentage of agreement between two observers in intervals in which one or both observers documented non-occurrence of the behavior of interest. It excludes intervals in which both observers DID record an occurrence of the behavior of interest. The formula can be written as:
Unscored-interval IOA %: (# of agreement intervals within non-occurrence intervals / total # of non-occurrence intervals) x 100
Line Graph
Points on the graph represent relationships between the dependent and independent variables.
Comparisons of data points on this graph reveal the presence or absence of changes in level, trend, and variability.
Bar Graph
A graph where there are no distinct data points representing responses through time.t
Cumulative Record
A graph that displays the cumulative number of responses emitted are represented on the vertical axis, where the steeper the slope of the response the greater the response rate.
Scatter Plot
A graph that shows the relative distribution of individual measures in a data set
Standard Celeration Chart
a standardized semi logarithmic chart that has time extending from the left to the right on the x axis in an additive fashion while rates of behavior are charted on an exponential scale on the Y axis. Allows for analysis of change in rate over time.
Level
The value of a data point along the x-axis of a graph.
Trend
The overall direction of the data path.
Variability
The extent to which the data move around on the graph.
