Ch. 14: Single-Subject Designs Flashcards
what is needed for single-subjects designs to qualify as experiments
these designs must include manipulation of an independent variable and control of extraneous variables to prevent alternative explanations for the results
single-subjects designs
experimental research designs that use the results from a single participant to establish the existence of cause-and-effect relationships
how was the single-subjects design developped?
it was developed by behaviourists examining operant conditioning
goal of single-subjects designs
to identify cause-and-effect relationships between variables
single-subject designs incorporate elements of _____
descriptive case studies and quasi-experimental time-series designs
baseline
there is a clear measure of baseline behaviour before administering treatment
repeated observations
multiple measures are obtained during baseline and each treatment condition to ensure that outside factors are not influencing behaviour until the researcher intervenes and changes to the next treatment condition
what is needed for the success of a single-case design?
the series of observations/measurements during the baseline and each treatment must be stable
replication
if results show a clear change in behaviour when the researcher changes the treatment condition, the same change must be demonstrated a second time before the researcher can conclude the change in treatment is responsible for causing the change in behaviour
evaluating results from a single-case study
Presentation and interpretation of results from a single-case experiment are based on visual inspection of a simple graph of the data
Two reasons for skepticism concerning the results of single-case studies
- There is no control over extraneous variables
- The results may simply be due to chance
phase
a series of observations of the same individual under the same conditions
baseline observations
the observations made when no treatment is being administered
annotation of baseline observations
A series of baseline observations is called a baseline phase and is identified with the letter A
treatment obseravtions
the observations made when treatment is being administered
annotation of treatment observations
- A series of treatment observations is called a treatment phase and is identified by the letter B
- When a study contains two or more distinct treatments, B identifies the first treatment condition, and C, D, and so on identify other treatments
- When a study contains modifications of the basic treatment B, the different modifications are called B₁, B₂, etc.
level
the magnitude of the participant’s response
trend
a consistent increase or decrease in the magnitude of behaviour across the series of observations that make up the phase
stability
the degree to which the observations show a pattern of consistent level or consistent trend
can stable data show variations?
Stable data may show minor variations from a perfectly consistent pattern but the variations should be relatively small and the linear pattern clear
dealing with unstable data
- Keep making observations and hope that the data will stabilize and reveal a clear pattern
- Average a set of two or more observations
- Look for patterns within the inconsistency
length of phases
- To establish a pattern, a phase must consist of a minimum of three observations
- Typically, 5-6 observations are necessary to determine a clear pattern
- When high variability exists, you should make additional observations
phase change
involves changing the conditions, usually by administering or stopping a treatment
goal of a phase change
to demonstrate that adding or removing a treatment produces a noticeable change in behaviour
when is a phase change not appropriate?
- When data in a baseline phase show a trend indicating improvement,
- This can result in ambiguous results
when does the researcher have an obligation to begin the treatment?
- If the baseline data indicate a high level of dangerous or threatening behaviour
- If the behaviour is brought under control during a treatment phase, the researcher can consider resuming the experiment by changing back to a baseline phase
when should a researcher stop or modify the treatment?
If a treatment appears to produce an immediate and severe deterioration in behaviour, the researcher/clinician should stop, change, or modify the treatment immediately
appropriate vs. necessary phase changes
- If the responses establish a clear pattern, a change is appropriate
- If the responses indicate a serious problem, a change is necessary
4 visual inspection techniques
- change in average level
- immediate change in level
- change in trend
- latency change
change in the average level
involves comparing the average levels of behaviour between phases
immediate change in level
involves comparing the last data point in one phase with the first data point in the following phase
change in trend
involves assessing whether the trend observed in one phase is noticeably different from the trend in the previous phase
latency of change
involves assessing whether the data show a large, immediate change in pattern
what is the most convincing evidence for a difference between phases?
latency of change
reversal design
consists of a series of phases, including baseline phases followed by a treatment phase and at least one replication of a baseline followed by a treatment
what is the most commonly used reversal design?
ABAB design
ABAB design
consists of a baseline, treatment, return to baseline, and second treatment phase
goal of the ABAB design
to demonstrate that the treatment causes changes in the participant’s behaviour by showing that:
1. The pattern of behaviour in each treatment phase is different from the pattern in each baseline phase
2. The changes in behaviour from baseline to treatment and from treatment to baseline are the same for each of the phase-change points in the experiment
limitations of the ABAB design
- Its credibility depends largely on the reversal (return to baseline)
- Withdrawing treatment may not result in a change in behaviour
- This means that it is not appropriate to evaluate treatments that are expected to have a permanent or long-lasting effect
- The ethical question of withdrawing a successful treatment
variations on the ABAB design
- The exact sequence of baseline and treatment phases often evolves during the study, creating an unlimited number of potential designs
- Not every potential phase sequence qualifies as an experimental design
- To qualify as an experiment, a study must consider alternatives and eventually produce one unambiguous explanation for the results
multiple-baseline design
begins with two simultaneous baseline phases. A treatment phase is initiated for one of the baselines while baseline observations continue for the other. At a later time, the treatment is initiated for the second baseline
multiple-baseline across subjects
when the initial baseline phases correspond to the same behaviour for two separate participants
multiple-baseline across behaviours
when the initial baseline phases correspond to two separate behaviours for the same participant
multiple-baseline across situations
when the initial baseline phases correspond to the same behaviour in two separate situations
component-analysis design
consists of a series of phases in which each phase adds or subtracts one component of a complex treatment to determine how each component contributes to the overall treatment effectiveness
Two main strategies for conducting a component-analysis design
- Component analysis with a reversal design
- Component analysis with a multiple-baseline design
component analysis with a reversal design
Involves a return to baseline followed by a second demonstrating the treatment effect
phases of the component analysis with a reverse design
- Baseline phase
- A series of phases adding treatment components one by one
- Return to a baseline phase
- Repeat the series of phases adding treatment components
variations on the component analysis with a reversal design
It is also possible for it to add one component, return to baseline, add a different component, and then return to baseline
component analysis with a multiple-baseline design
Replicates the demonstration of a treatment effect by repeating the effect for a different participant (or behaviour or situation) at a different time
goal of the multiple-baseline design
to show that the treatment causes a change in behaviour
criteria for a successful multiple-baseline design
- There is a clear and immediate change in the pattern of behaviour when the researcher switches from a baseline to a treatment phase
- The design includes at least two demonstrations that behaviour changes when the treatment is introduced
strength of the multiple-baseline design
It eliminates the need for a reversal or return-to-baseline phase, making it well-suited for evaluating treatment effects that are permanent or long-lasting
weaknesses of the multiple baseline design
- It can be difficult to identify similar but independent behaviour
- The clarity of the results can be compromised by individual differences between participants or behaviours