Unit 5 Flashcards
Experimental Design
Repeated, systematic presentation and removal of an independent variable (IV) while measuring changes in the dependent variable (DV), and holding other factors constant
The primary goals of experimental design
To demonstrate a functional relationbetween the IV and DV To evaluate the interventions once they are decided upon
Functional relation
Exists when changes in an antecedent or consequent stimulus class consistently alter a dimension of a response class
Internal validity
The extent to which an analysis assures that measured changes in behavior are due to the manipulation and NOTdue to uncontrolled extraneous variables
External validity
The extent to which a study’s results are generalizable to other subjects, settings, or behaviors
Why Internal Validity is a Priority
It makes little sense to consider the generality of the effect (external validity) if extraneous variables cannot be ruled out for the effect
Threats to internal validity
History Maturation Testing Instrumentation Diffusion of treatment Regression towards the mean Selection bias Attrition
History
Introduction of the IV may coincide with other events in the person’s life (and those other events could have produced the effects)
Maturation
Natural developmental events or learning experiences may coincide with the introduction of the independent variable to produce the change
Testing
Changes in the dependent variable may have come about as a function of repeated exposure to the experimental arrangements
Instrumentation
Changes may reflect modifications in the measurement systems rather than effects of the IV
Diffusion of treatment
Inadvertent, uncontrolled “seepage” of the treatment to control conditions or control subjects
Regression towards the mean
Changes occurred because baseline measurements were NOT representative of the natural state of events; perhaps less relevant to single-case designs because of repeated measures
Selection bias
The assignment of subjects to groups may have biased the outcome even in the absence of any intervention; Perhaps less relevant to single-case designs because participants serve as their own controls
Attrition
The loss of subjects over time, especially if systematic, may influence the effects; Perhaps less relevant to single-case designs because participants serve as their own controls
Minimizing Validity Threats
Measurement
Stability
Immediacy
Replication
Measurement
Continuous assessment-collecting data on the dependent measure for an extended period of time
Stability
If levels of the DV remain relatively stable over time before the independent variable is introduced, the likelihood that the change canbe attributed to the IV increases
Immediacy
The more immediate the effect, the stronger the case that the IV produced it
Replication
Demonstration using multiple cases; If the IV affects many subjects in the same manner, a stronger case can be made that it produced the change
Single-Case Designs(SCD)
A variety of research designs that use baseline logic to demonstrate the effects of IVs on the behavior of individual subjects.
Other names for Single-Case Designs
Single-subject design
Within-subjects design
Intra-subject design
Small n design
Characteristics of Single-Case Designs
ndividuals serve as their own control; Each individual is exposed to each level of the IV; Changes in the IV are made once the DV has reached a steady state; Small number of subjects; Multiple and repeated measures; Usually visual data analysis
Characteristics of Group Designs
Comparisons are made between groups of individuals (“control” group vs. experimental group); large number of subjects; each individual often exposed to only one level of the IV
Advantages of Single-Case Designs
Dynamic change (repeated measurement and stability permit you to see patterns of behavior change); Variability (allows the examination of inter-subject and intra-subject variability); Accountability (represents the performance of an individual subject)
Baseline
Assessment of the dependent variable prior to the introduction or change of the independent variable
Functions of Baseline
Descriptive
Predictive
Insight
Setting targets
Phase change
Movement in the analysis from one level or kind of independent variable to the next level or kind of independent variable
A-B Design
Baseline phase followed by a treatment phaseEffect is demonstrated when behavior changes from one phase to the next
Limitations of A-B Designs
Supports weak conclusions
Changes in behavior may be the result of extraneous variables
Phase change logic
Ideally phase changes are made when behavior reaches a steady state defined by level, stability and trend.
3 factors needed for “steady state responding”
Level (behavior is high or low enough to detect a change if one occurs); Stability (levels of behavior do NOT vary greatly from one measurement to the next);Trend (the behavior is NOT already changing in the predicted direction).
Reversal Design
Following baseline, the IV is introduced, then withdrawn (at least once, 2 times is preferable)
Advantages of Reversal Designs
Most straightforward single-casearrangement; Most powerful demonstrationof functional relations
Limitations of Reversal Designs
Reversibility (some behavior changes are not reversible)
Ethical concerns of treatment reversalTime (to get stability in all phases)
Order (could be sequence effects)
Multiple Baseline Design
Two or more independent baselines are established; The IV is then separately introduced in a staggered fashion to each baseline; When behavior is stable for the first baseline, the IV is introduced on the second baseline,and so on.
3 Standard Variations of Multiple Baseline Designs
Multiple baseline across subjects
Multiple baseline across behaviors
Multiple baseline across settings
Advantages of Multiple Baseline Designs
Useful when behavior change is notreversible
Does not require countertherapeutic behavior change to demonstrate control
Experimenter can empirically evaluate methods and interventions before applying on a larger scale
Limitationof Multiple Baseline Designs
Interdependency (changing behavior in one baseline is likely to change behaviors in the other baseline even though the IV is not introduced to other baselines)
Non-concurrent Multiple Baseline (Delayed Multiple Baseline)
Across individuals.
Separate baselines are taken; The baselines are staggered but not conducted at the same time
Advantages of Non-concurrent Multiple Baseline Designs
Permits greater flexibility in analysis (not constrained by needing all subjects concurrently present)
Disadvantages of Non-concurrent Multiple Baseline Designs
Greater interpretive challenge if behavior changes on subsequent baseline before IV is introducedNOT useful across behaviors or settings
Multiple probe technique
First baseline is continuous, but subsequent baseline data collection is conducted intermittently (as “probes”), relative to the first baseline
Advantages of Multiple Probe Design
Avoids “ritualistic” gathering of Baseline data
Avoids various threats
Useful when extended baseline sessions are impractical, costly, or possibly detrimental
Disadvantages of Multiple Probe Design
Risks stability (perhaps infrequent probes were outliers)