Multiple Baseline Designs

1
Multiple Baseline Designs

• Chapter 7
• Single Subject Research and Design

2
Multiple Baseline

• Description
• Multiple measures are used to obtain data over
  two or more baselines
• The end result appears visually as a series of
  A-B designs on top of one another
• The DV may consist of 2 or more different
  behaviors
• Versatile and relatively easy to understand
• Perhaps the most common design in use today

3
Multiple Baseline Design

• If 3 dependent variables have been chosen,
  baseline data is obtained for all three dependent
  variables
• The researcher implements the intervention for
  the first DV while maintaining baseline
  conditions for the other two
• When the criterion is obtained on the first
  behavior, the intervention may be implemented and
  analyzed as to its effect on the second DV
• A follow-up stage is included to ensure that the
  effects of the IV are maintained

4
Multiple Baseline Design

• MBD are used
• When withdrawal or reversal designs may not be
  feasible due to ethical concerns of withdrawing
  treatment
• When practical considerations are necessary, such
  as more than one person needing interventions
• In cases where the IV should not be withdrawn or
  the achieved target behavior cannot be reversed

5
Prediction Verification and Replication

• Verification is evident if the data path changes
  in a predictable manner through a phase change,
  as from baseline to intervention
• Inferences can be made concerning the
  complimentary roles of prediction and
  verification
• 1. If potential confounding variables are held
  constant across all variables and the target
  behavior remains unchanged from DV 1 to variables
  2 and 3, then the prediction is valid
• 2. if changes in the IV occur with DV 1, the
  observed changes in the target behavior are
  brought about by the IV because only that DV was
  exposed to the IV

6
Replication

• Replication is achieved when similar results are
  obtained with each DV following the introduction
  of the same IV
• Replication can provide evidence of a functional
  relationship between the dependent and
  independent variables

7
Covariance Among Dependent Variables

• The variables in the treatment may covary, so it
  is important to select dependent variables that
  exhibit some degree of independence
• Each dependent variable must be measured using
  the same method of recording behavior

8
Advantages of Multiple Baseline Designs

• The withdrawal of an effective treatment is not
  required to demonstrate the functional
  relationship between the IV and DV
• The sequential implementation of the IV parallels
  the practice of teachers
• Generalization of behavior change is monitored
  through the design
• The design is easily used and conceptualized

9
Disadvantages of Multiple Baseline Design

• Possibility of covariance
• Functional relationships may not be clearly
  demonstrated
• Verification relies on the dependent variable
  levels not changing until the independent
  variable is introduced and then changing in a
  similar manner to any previously treated
  behaviors
• Implementation can be time consuming and may
  require substantial resources

10
Multiple Baseline design should not be used

• When selected target behaviors are not
  functionally similar nor independent of one
  another
• If there is only one subject in one setting and
  one target behavior
• When more than one intervention phase is
  desirable to demonstrate the functional
  relationship
• When constraints on resources make implementation
  impossible

11
Multiple Baseline Across Behavior

• Three or more behaviors are identified that are
  exhibited by the same subject in the same setting
  and then systematically subjected to the same
  intervention or independent variable

12
Critical Issues in Implementing a MB Across
Behaviors Design

• 1. selection of an individual participant who
  displays multiple behaviors in a single setting
  that require intervention
• 2. functional similarity and independence of
  those behaviors as one might be able to determine
  priority
• 3. a reasonable expectation that the same
  variables will exert equal influence on each of
  the dependent variables

13
Critical Issues (continued)

• 4. selection of a treatment that can be expected
  to produce a similar and independent effect on
  each of the dependent variables
• 5. a consistent recording procedure for each of
  the target behaviors and a criterion level for
  decision making
• 6. confidence that the resources and time needed
  to record multiple baselines and subsequent
  intervention will be maintained throughout the
  study

14
Multiple Baseline Across Settings

• Only one subject is identified but the researcher
  identifies two or more settings in which the
  individual emits the same behavior
• The same subject is treated for the same behavior
  in different settings

15
Issues in the Implementation of the MB Across
Settings design

• 1.Selection of an individual subject who displays
  the same target behavior in multiple settings
• 2. selection of settings that are functionally
  similar but also independent of one another as
  one may best determine priority
• 3. a reasonable expectation that the same
  variables will be exerting the same influence in
  each of the settings

16
Issues continued

• 4. selection of a treatment that can be expected
  to produce similar effects in each setting
• 5. a consistent recording procedure for each
  setting and a criterion level for decision making
• 6. confidence that resources will be maintained
  throughout the length of the study

17

• It is important to note that a major disadvantage
  of MB across settings design is that extraneous
  variables that may influence responding in
  different settings can be difficult to control or
  predict.

18
Multiple Baseline Across Subjects

• In this design more than one subject
  participates.
• Two or more individuals are identified that emit
  the same target behavior in the same setting
• The subjects should be enough alike that one can
  expect each subject to respond similarly to the
  same intervention yet independent enough of one
  another to avoid covariance

19
Issues in Implementing a MB across Subjects Design

• 1. selection of individual participants who
  display the same target behavior in the same
  setting
• 2. The subjects should be enough alike that one
  can expect each subject to respond similarly to
  the same intervention yet independent enough of
  one another to avoid covariance
• 3. a reasonable expectation that the same
  variables will exert the same influence on each
  of the subjects

20
Issues in Implementing a MB across Subjects Design

• 4. selection of an independent variable that is
  likely to have a similar effect on each subject
• 5. a consistent recording procedure for each of
  the target behaviors and a criterion level for
  decision making
• 6. confidence that the resources and time needed
  to record multiple baselines and subsequent
  intervention will be maintained throughout the
  study

21
Adaptations of the Multiple Baseline Design

• Multiple Probe Design
• Data probes are taken during baselines rather
  than continuous measurement
• Used to decrease the collection of data
• Researcher makes periodic recordings (probes) of
  baseline levels to ensure that no significant
  changes have occurred before the introduction of
  the intervention
• The use of probes reduce the need for resources
  that may be unavailable to maintain the
  continuous recording of behavior during baseline
  phases

22

• Delayed Multiple Baseline Design
• May be employed when a withdrawal design no
  longer is possible or when other behaviors,
  settings, or individuals emerge that are in need
  of intervention
• Baselines are not measured at the same time
• It allows the use of fewer resources and the
  researcher may extend the study to new
  behaviors, settings, and individuals that had not
  been targeted a priori