Unit 5b Flashcards
Control condition
Baseline condition
A condition or phase of an experiment in which the
independent variable is not present.
Experimental condition
Treatment condition
Intervention condition
Independent variable condition
A condition or phase in which the independent
variable is present.
Functional relation
An experimentally determined relation that shows that the dependent variable depends on or is a function of the independent variable and nothing else.
Experimental control
The management or control of different variables in a
study, including the independent variable and
extraneous variables.
Treatment integrity
The extent to which the independent variable is
consistently implemented as designed.
Tactics to manage extraneous variables
- Eliminate
- Hold constant
- Evaluate experimentally
Replication
Repetition of any parts of an experiment
Reproduction
Repetition of results, usually as an outcome of
repetition of procedures.
Within-session replication
Repetition of a basic element of a procedure
throughout each session.
Within-phase replication
Repetition of the same condition many times in
succession throughout a phase.
Within-experiment replication
Repetition of an entire phase during the course of an
experiment.
Within-literature replication
Repetition of an earlier experiment, usually by other
researchers.
Across-research-literature replication
Repetition of phenomena under different conditions
across different fields of science.
Functions of replication
- Reliability (if repeat procedure, get same effect?)
* Generality (if change procedure, get same effect?)
AB design
A within-subject experimental design composed of a
control and an experimental condition
Reversal design
A within-subject experimental design involving a pair
of control and experimental conditions in which one
or both conditions repeat at least once.
Multi-element design
Alternating-treatments design
A variation of a reversal design that exposes a
participant first to one condition and then to another
in some form of repeated alternation.
Changing criterion design
A within-subject, single baseline design using AB and
reversal sequences to identify effects of manipulating
performance criteria.
Parametric design
A within-subject, single baseline design using AB and
reversal sequences to identify effects of manipulating
a specific parameter of a procedure.
Multiple baseline design
A within-subject design that uses two or more
baselines in a coordinated way to allow controltreatment
comparisons both within and across
baselines.
Requirements for comparing responding
across multiple baselines
• Each baseline must be independent of the others
• The sensitivity of each baseline to the intervention must
eventually be demonstrated
• When the intervention is ongoing in one baseline, the
control condition must be ongoing in other baselines.
• There must be sufficient temporal overlap between
intervention and control conditions in different baselines to
allow extraneous effects to develop
• Extraneous variables associated with the intervention
condition must have the opportunity of influencing
responding under the control condition
Exploratory data analysis (EDA)
An approach to data analysis that emphasizes largely
graphical techniques focusing on discovering order
and structure in the data.
Linear interval scale
A measurement scale that allows descriptions of
events that show how much they differ in terms of
equal intervals between values.
Logarithmic interval scale
A measurement scale that allows description of
events that show how much they differ in terms of
equal rations between values.
No chance day
A plotting convention referring to days on which the
target behavior could not have occurred. Data points
bracketing such days should not be connected in line
graphs.
Ignored day
A plotting convention referring to days on which the
target behavior could have occurred but was not
measured. Data points bracketing such days should
be connected in line graphs.
Generality
The meaningfulness of experimental interpretations
under circumstances different from those that
generated the data.
