• When a predictable change in behavior (DV) can be reliably produced by the systematic manipulation of some aspect of the individual's environment (IV).

• The ANALYSIS dimension of the seven dimensions of ABA.

1. Behavior is INDIVIDUAL:
   • A person's interaction with the environment.
   • Groups of people do NOT behave.
   • Experimental strategy of ABA is based on single-subject methods of analysis; NOT large groups.
2. Behavior is CONTINUOUS:
   • Behavior changes over time; it is not a static event.
   • Requires continuous measurement over time.
3. Behavior is DETERMINED:
   • Occurrence of any event is determined by the functional relation it holds with other events.
   • Behavior is a natural phenomenon, and is subject to the same natural laws as other natural phenomena.
4. Behavior variability is EXTRINSIC to the organism:
   • Variability (i.e., change in behavior) is the result of the environment such as:
     • The IV under investigation
     • Some uncontrolled aspect of experiment (e.g., another child in student's classroom elopes from the classroom).
     • Uncontrolled factor outside of experiment (e.g., weather changes).

• A brief but specific statement of what the researcher wants to learn from conducting the experiment. 

• All well-planned experiments begin with this
• Can be in Question or Statement form
  • Q: What are the effects of the IV on the DV for what population and what setting?
  • S: The purpose of the study was to see the effects of the IV on the DV.

At Least ....

1. 1 Subject - Single-Subject Design
2. 1 Behavior - Dependent Variable
3. 1 Setting
4. 1 Treatment - Independent Variable
5. 1 Measurement System & Data Analysis
6. Experimental Design

6 Components of Experiments in ABA

1. At Least One Subject

AKA: Single Subject Design

• Repeated measures of the subject's behavior during each phase of the study provide the basis for comparing experimental variables as they are presented or withdrawn on subsequent conditions (i.e., the presence and absence of the IV).
• ABA uses SINGLE-SUBJECT DESIGNS
• This does not mean there is only one subject (sometimes there is only one subject).
  • Called single subject because the subject acts as their own control
  • The subject is exposed to each condition several times over the course of the study. 
  • Studies usually involve 4-8 subjects.
    • Each subject's data are graphed separately. 
• ABA does not use group comparison designs with large numbers of subjects. Group designs mask individual progress

6 Components of Experiments in ABA

2. At Least One Behavior

AKA: Dependent Variable

• In some studies, more than one DV is measured. Reasons include:
  • Provide data that can serve as controls for evaluating and replicating the effects of an IV.
  • Assess if any COLLATERAL EFFECTS occurred.
  • Collateral Effects: A Phenomenon in which the IV effects behaviors other than the targeted behavior. 
  • Determine whether changes in the behavior of a person other than the subject occur during the course of an experiment and if such changes can explain changes in the subject's behavior.  

6 Components of Experiments in ABA

3. At Least One Setting

• Control TWO sets of environmental variables to demonstrate experimental control:
  1. IV → present, withdraw, or vary its value
  2. Extraneous Variables: prevent unplanned environmental variations.
• Environments are easier to control in the laboratory than in natural environments such as home, school, etc. 
• When unplanned variations take place you must try to wait them out or incorporate them into the design. Repeated measures of the behavior tell us whether unplanned environmental changes are of concern. 

6 Components of Experiments in ABA

4. At Least One Treatment

AKA: Independent Variable

• The particular aspect of the environment that the experimenter manipulates to find out whether it affects the subjects behavior. 

6 Components of Experiments in ABA

5. Measurement System and Ongoing Data Analysis

• Observation and recoding procedures must be conducted in a standardized manner.
• Standardization involves every aspect of the measurement system. 
• Behaviorists must detect changes in level, trend, variability.

6 Components of Experiments in ABA

6. An Experimental Design

• The particular arrangement of conditions in a study so that meaningful comparisons of the effects of the presence, absence, or different values of the IV can be made.
• Two types of Experimental Designs:
  1. Nonparametric Analysis: IV either present of absent during study. 
     • nONparametric has the word ON in it, so either the IV is ON (present) or OFF (absent) in this type of design. 
       • Ex: Medication is either given and then taken away in the course of the study. 
  2. Parametric Analysis: The value of the IV is manipulated. Seeks to discover the differential effects of a range of values.
     
     • Ex: Various doses of medication are given during the Cours of a study. 
• Rules of Experimental Designs:
  • Changes only one variable at a time. 
    • If variable is treatment package ensure that the entire package is presented or withdrawn at the same time. 

• A pattern of responding that exhibits very little variation in its measured dimensional qualities over a period of time.
• Provides the basis for BASELINE LOGIC.

• Refers to the experimental reasoning inherent in single-subject experimental designs. Entails 3 elements:
  1. Prediction
  2. Verification
  3. Replication
• Each of these elements depends on an overall experimental approach called steady state strategy.

Baseline Logic

Prediction

• The anticipated outcome of a presently unknown measurement.

• Data should be collected until stability is clear.
• More data points → Better predictive power.
  • No 'magic number' of data points.
• Main question: are data stable enough to serve as the basis for experimental comparison?

Baseline Logic

Verification

• Demonstrating that the prior level of baseline responding would have remained unchanged had the independent variable not been introduced.

• Verifying the accuracy of the original prediction reduces the probability that confounding variables were responsible for observed change in behavior.
• Verification of a previously predicted level of baseline responding by termination or withdrawal of the treatment variable. 

Baseline Logic

Replication

• Repeating conditions within an experiment to determine the reliability of effects and increase internal validity.

• Shows reliability of behavior change; "We can make it happen again".
• Accomplished by reintroducing the IV.

• Repeated exposure of a given subject to a given condition while trying to eliminate extraneous influences on behavior and obtaining a stable pattern of responding before introducing the next condition.

• Serves as a control condition.
• Does not imply the absence of intervention; can be the absence of a specific IV.

• Use the subject's performance in the absence of the IV as an objective basis for detecting change.
• Obtain descriptions of ABC correlations for the planning of an effective treatment.
• Guide us in setting the initial criteria for reinforcement.
• See if the behavior targeted for change really warrants intervention.

4 Patterns of Baseline Data

DAVS

1. Descending
2. Ascending 
3. Variable
4. Stabe

4 Patterns of Baseline Data

DAVS

1. Descending Variable

• Shows behavior is already changing.
• Generally DO NOT introduce IV when behavior is NOT STABLE.
  • Unless behavior goal is increasing responding, and descending trend shows it is worsening.
• If descending baseline is due to a behavior you want to decrease you should wait because  the behavior is already improving.

4 Patterns of Baseline Data

DAVS

2. Ascending Baseline

• Shows behavior is already changing.
• Generally DO NOT introduce IV when behavior is NOT STABLE.
  • Unless behavior goal is decreasing responding, and ascending trend shows it is worsening.
• If ascending baseline is due to a behavior you want to increase you should wait because the behavior is already improving.
  
  

4 Patterns of Baseline Data

DAVS

3. Variable Baseline

• No clear trend
• If one's data is variable, wait it out and do not introduce the IV.
• Variability is assumed to be due to the environmental variables that are uncontrolled. If you introduce the IV now you will not be able to determine if behavior change is due to intervention or not.
• Should try to control uncontrolled course of variability.

4 Patterns of Baseline Data

DAVS

4. Stable Baseline

• No evidence of ascending or descending trend.
• All the values of the DV fall within small range.
• Best way to look at the effects of IV on DV.
• BEST TIME TO INTRODUCE IV!

5 Main Experimental Designs

AKA: MC RAW

1. Multiple Baseline
2. Changing Criterion
3. Reversal
4. Alternating Treatment
5. Withdrawal

5 Main Experimental Designs

AKA: MC RAW

1. Multiple Baseline

• Multiple treatment design which begins with the concurrent measurement of two or more behaviors in a baseline condition, followed by the application of the treatment variable to one of the behaviors while baseline conditions remain in effect for the other behaviors 
• Staggered implementation of the intervention in a step-wise fashion across behaviors, settings, and subjects.
• Mostly Widely Used design.
• Highly Flexible.
• Do not have to withdraw a treatment variable in his design.
• When it is UNETHICAL or impractical to reverse conditions or when the behavior is irreversible, use this design instead of a reversal design.

5 Main Experimental Designs

AKA: MC RAW

1. Multiple Baseline

Designs

• 3 Types
  1. M.B. Across Behaviors
  2. M.B. Across Settings
  3. M.B. Across Subjects

• Weaker Variations
  1. Multiple Probe Design
  2. Delayed Multiple Baseline Design

Baseline Logic of Multiple Baseline Design

Prediction, Verification, Replication

• A functional relation requires a change in behavior with the onset of the intervention.
  • Apply IV to behavior 1 when you can confidently predict that the behavior would remain the same in constant conditions.
  • If behaviors 2 & 3 remain unchanged after application of the IV to behavior 1, this verifies the prediction.
  • If the IV changes behavior 2 like it did for behavior 1, the effect of the IV has been replicated.
• More replications, the more convincing the demonstration.
• Most commonly 3-5 tiers.

5 Main Experimental Designs

AKA: MC RAW

1. Multiple Baseline

1. M.B. Across Behaviors

• After steady state baseline responding, the IV is applied to the first behavior while other behaviors are kept in baseline.
• When steady state responding is reached for the first behavior, then the IV is applied to next behavior.
• Two or more different behaviors of teh SAME SUBJECT.
• Each subject serves as his/her own control. 

5 Main Experimental Designs

AKA: MC RAW

1. Multiple Baseline

2. M.B. Across Settings

• After steady state responding, the IV is applied to the first setting while other settings are kept in baseline.
• When steady state responding is reached for the first setting, then the IV is applied to the next setting.
• A single behavior is targeted in 2 or more different settings or conditions.

5 Main Experimental Designs

AKA: MC RAW

1. Multiple Baseline

3. M.B. Across Subjects

• After steady state responding is, the IV is applied to the first subject, while the other subjects are kept in baseline.
• When steady state responding is reached for the first subject, then the IV is applied to the next subject.
• One target behavior for two or more subjects in teh SAME SETTING.
• Most widely used MBD.

5 Main Experimental Designs

AKA: MC RAW

1. Multiple Baseline

Variations

• Multiple Probe Design
• Delayed Multiple Probe Design
  • Both inherently weaker than traditional MBD.
  • Use when extended baseline measurement is unnecessary, impractical, too costly, or unavailable.

5 Main Experimental Designs

AKA: MC RAW

1. Multiple Baseline

A. Multiple Probe Design

• Analyzes relation between IV and the acquisition of skill sequences.
• Instead of simultaneous baselines, probes provide the basis for determining if behavior change has occurred prior to intervention. 

5 Main Experimental Designs

AKA: MC RAW

1. Multiple Baseline

B. Delayed Multiple Baseline Design

• Initial baseline and intervention begin and subsequent baselines are added in a delayed or staggered fashion (i.e., fewer baseline probes for subsequent tiers.). 
• Effective when:
  • Reversal Design is not possible
  • Limited resources preclude a full-scale design
  • When a new behavior, subject, or setting becomes available.
• Limitations: Shorter baselines do not show interdependence of DVs.

1. Select independent yet functionally similar baselines.
   • behaviors are functionally independent of one another.
   • behaviors share enough similarity that the will change with the application of the same IV.
   • behaviors should be of different response classes.
2. Select concurrent and plausibly related multiple baselines.
   • behaviors must be measured concurrently.
   • All relevant behaviors that influence one behavior must have the same opportunity to influence other behaviors. 
3. Do not apply IV to next behavior too soon.
4. Vary significantly the lengths of multiple baselines.
   1. The more baselines differ in length, the stronger the design.
5. Intervene on the most stable baseline first.

• Advantages:
  • Successful intervention does NOT have to be removed
  • Easy to implement
  • Quick comparisons
  • No delay to start
  • Evaluates Generalization

• Disadvantages:
  
  • Functional relation is NOT directly shown in this design.
  • Carryover effect
  • Effectiveness of IV is demonstrated, but not information regarding the function of the target behavior.
  • IV may be delayed for certain behaviors, settings, or subjects
  • Takes resources to implement properly

5 Main Experimental Designs

AKA: MC RAW

2. Changing Criterion Design

• Experimental design in which an initial baseline phase is followed by a series of treatment phases consisting of successive and gradually changing criteria for reinforcement or punishment.
• There is only one behavior in this design.
• Behavior in this design has to already be in subject's repertoire. 
• Evaluates treatment that is applied in graduated or step-wise fashion.

Baseline Logic of Changing Criterion Design

Prediction, Verification, Replication

• Prediction: In the absence of effective intervention, levels of performance will not change from baseline.
• Verification: A return to a previous counter-therapeutic criterion results in a change in behavior to levels observed in the previous presentation of that criterion.
• Replication: A return to a previous therapeutic criterion results in a change in behavior to levels observed in the previous presentation of that criterion.
• The criterion lines should have a large separation to show functional relation.
• Experimental control is evidenced by the extent that the level of responding changes to conform to each new criterion.
• If data points do not fall around the criterion lines, that shows that there is very little experimental control.
• The greater the vertical distance between the criterion lines, the more experimental control.

1. Length of phases
   • Each phase must be long enough to achieve stable responding.
   • Target behaviors that are slower to change require longer phases.
   • Validity of the design is increased when you vary the length of each phase.
2. Magnitude of criterion changes
   • The size of the changes between each criterion should vary to prove strong functional relations.
   • Changes in size must be large enough to be detectable, but not so large as to be unachievable.
   • Changes in size can be smaller if you are dealing with stable data.
3. Number of criterion changes
   • The more criterion changes the better proof of experimental control.

• Advantages:
  • Does not require reversal of improved behavior.
  • Enables an experimental analysis within the context of a gradually improving behavior.

• Disadvantages:
  • The target behavior must already be in the person's repertoire.
  • Not appropriate for analyzing the effects of a shaping program.
  • It is NOT a comparison design.

5 Main Experimental Designs

AKA: MC RAW

3. Reversal Design

• Any Experimental design in which the researcher REVERSES responding to a level obtained in a previous condition.
• Encompasses experimental designs in which the IV is withdrawn (A-B-A-B) or reversed in its focus (e.g., DRI / DRA)
• Alternating between baseline and a particular intervention.
• Each reversal in a reversal design strengthens experimental control.
• Evidence of a functional relation is strengthened with each reversal (e.g., switch from one condition to the other with a corresponding change in trend and level).
• For a reversal to occur, the behavior must approximate the initial baseline level.
• Requires at least 3 consecutive phases:
  1. Initial Baseline (A)
  2. Intervention (B)
  3. Return to Baseline (A)
• A-B-A-B preferred over A-B-A: as stronger design
• MOST POWERFUL WITH-IN SUBJECT DESIGN for demonstrating function

5 Main Experimental Designs

AKA: MC RAW

3. Reversal Design 

Designs

1. Repeated Reversals
2. BAB
3. Multiple Treatment Design
4. NCR Reversal Technique
5. DRO/DRA/DRI Reversal Technique 

Baseline Logic of Reversal Design

Prediction, Verification, Replication

• Prediction: In the absence of effective intervention, levels of performance will not change from baseline
• Verification: When the intervention is removed, performance returns to previously observed baseline levels
• Replication: Reintroducing the intervention changes behavior in the same direction as the initial implementation of the intervention

5 Main Experimental Designs

AKA: MC RAW

3. Reversal Design 

1. Repeated Reversal

• Extension of A-B-A-B
  • (i.e., A-B-A-B-A-B-A-B)
• More reversals → Stronger evidence for control
• *Redundancy may be a concern.

5 Main Experimental Designs

AKA: MC RAW

3. Reversal Design 

2. B-A-B Reversal

• 3 Phase reversal design:
  1. IV
  2. IV Removed
  3. IV Reintroduced
• Weaker than A-B-A design because it does not enable assessment of the effects of IV during baseline.
• Disadvantage:
  • Sequence effect: Levels of behavior during baseline (condition A) may be influenced by the presence of the IV in the condition before it (B).
• Best design when client displays dangerous and severe behaviors → implementing intervention does not need to wait.
• Also appropriate for when IV is already in place and you have limited time.

5 Main Experimental Designs

AKA: MC RAW

3. Reversal Design 

3. Multiple Treatment Design

• A type of reversal design that compares two or more IVs to baseline and/or to one another.
• Easy to determine when using Multiple Treatment, when phases (letters) are added (e.g., A-B-A-C-A-B-A-C, A-B-C-D-A-C-A-D
• Disadvantage: Sequence Effect

5 Main Experimental Designs

AKA: MC RAW

3. Reversal Design 

4. Non-Contingent Reinforcement Reversal

• An experimental technique for showing the effects of reinforcement by using NCR as a CONTROL condition INSTEAD of a baseline condition in which no reinforcement is provided.
• Allows examination of contingent reinforcement.
• The reinforcer is presented on a fixed or variable time schedule independent of the subject's behavior. 

5 Main Experimental Designs

AKA: MC RAW

3. Reversal Design 

5. DRO/DRI/DRA Reversal

• An experimental technique for showing the effects of reinforcement using DRO, DRA, or DRI as a CONTROL condition INSTEAD of a baseline condition, in which no reinforcement is provided. 
• DRO: Reinforcement following any behavior other than the target behavior.
• DRI: Reinforcement following any behavior that is physically incompatible with the target behavior.
• DRA: Reinforcement following an alternative behavior other than the target behavior.
• Allows examination of contingent reinforcement. 

• Advantages:
  • Clear demonstration of the existence or absence of a functional relation between the IV and DV.
  • Enable practitioners to count the amount of behavior change.
  • Return to baseline tells us we need to program for maintenance. 

• Disadvantages:
  • Ethical and educational issues can arise when effective treatment is removed.
  • Irreversibility

• The level of behavior observed in an earlier phase cannot be reproduced even though experimental conditions are the same as they were during the earlier phase.
  • Ex: Learning to ride a bike, so something that once learned, can never be un-learned. 

5 Main Experimental Designs

AKA: MC RAW

4. Alternating Treatments Design

AKA SCAMMM

• An experimental design in which two or more conditions are presented in rapidly alternating succession independent of the level of responding and the differential effects on teh target behavior are noted.
• Compares two or more IVs to one another to see which IV would be best to utilize with a client. 
• Based of stimulus discrimination (each IV has an obvious S^D signaling which IV is in effect at any given time).
• For each IV data are plotted separately on the same graph.
• IVs may be 
  • Alternated across daily sessions
  • Given in sessions occurring the same day
  • Implemented during each portion of the same session

• SCAMM:
  • Simultaneous Treatment Design
  • Concurrent Schedules Design
  • Alternating Treatments Design
  • Multi-Element Baseline Design
  • Multi-Element Design
  • Multiple Schedules Design

Baseline Logic of Alternating Treatments Design

Prediction, Verification, Replication

• Functional relation shown when:
  • One data path is consistently higher than the other.
  • No overlapping data paths
• The degree of differential effects produced by two different treatments is determined by the vertical distance between the respective data paths.
• Not identified in separate phases of teh design.
• Each successive data point in treatment plays all three roles.

5 Main Experimental Designs

AKA: MC RAW

4. Alternating Treatment

Designs

3 Variations of Alternating Treatment Design

1. Single Phase Without Baseline: No initial baseline phase.
2. With Baseline: Baseline should be conducted whenever possible, as it shows the change produced by each treatment compared to the natural level of performance without an intervention. 
3. With Baseline & Final Best Treatment: Most widely used.

1. Irreversibility
2. Sequence Effects
3. Unstable Data

• Advantages: 
  • Does not require treatment withdrawal
  • Speedy comparison
  • Minimizes irreversibility problem
  • Minimizes sequence effects
  • Can be used with unstable data
  • Can be used to assess generalization of effects
  • Intervention can begin immediately without baseline data

• Disadvantages:
  • Multiple Treatment Interference:
    • This is always a problem with this design, as multiple treatments are going on at the same time. 
  • Unnatural nature of rapidly alternating treatments.
  • Limited capacity of the design (suggested maximum comparison of four conditions, although more have been reported in research).
  • Selection of treatments: Should be significantly different from one another.

5 Main Experimental Designs

AKA: MC RAW

5. Withdrawal Design

• A design in which an effective treatment is sequentially or partially withdrawn to promote the maintenance of behavior changes.

2 Types of Validity

1. Internal Validity

2. External Validity

1. Internal Validity: The extent to which an experiment shows convincingly that changes in the behavior are a function of the IV and not the result of uncontrolled or unknown variables.
   • An internally valid study involves only one IV at a time. Multiple IVs are not confounded (i.e., presented at the same time). This is the best way to see the effect of the IV on the DV.

4 Threats to Internal Validity

MISS

1. Measurement Confounds
2. IV Confounds
3. Subject Confounds
4. Setting Confounds

4 Threats to Internal Validity

MISS

1. Measurement Confounds

• Measurement Confounds: Refers to the number and the intricacy of the behaviors you are targeting.  If numerous complicated behaviors are targeted, internal validity may be affected.
  • May occur due to:
    • Observer draft: When observers unknowingly alter the way they apply a measurement system.
    • Reactivity: Behavior of clients changing when being observed. Observers being changed by their observations being monitored.
      • To reduce reactivity: maintain baseline conditions long enough for reactivity to run its course.
    • Observer Bias: The observer's expectations that change follow in a particular direction.
      • To reduce observer bias: Keep observers naive to expected outcomes of a study.

4 Threats to Internal Validity

MISS

2. IV Confounds

• IVs are complicated and given together usually in a treatment package.
  • Ex: When giving someone money as a reinforcer, the person giving is also providing attention in addition to the money. Therefore it is hard to determine if money or attention (or combination) is maintaining reinforcer.
• To reduce IV confounds: Placebo control or double-blind control procedures (in which the subject is not aware if the IV Is present or not).

4 Threats to Internal Validity

MISS

3. Subject Confounds

• Maturation: Change in subject over course of study. 
• Repeated measurement detects uncontrolled variables. 

4 Threats to Internal Validity

MISS

4. Setting Confounds

• Studies in natural settings are more prone to confounding variables than in controlled laboratories. 
• You should hold all possible aspects of the study constant until repeated measurements again reveal stable responding.
• BOOTLEG REINFORCEMENT may also occur in the natural environment.
• BOOTLEG REINFORCEMENT → Secretive reinforcement that is not part of your behavior plan.

Confounding Variables

Extraneous Variables vs. Confounding Variables

• Generally, these terms are used as AKAs to refer to variables that exert an uncontrolled influence on a research study.
• The effects of these variables should be reduced or eliminated as much as possible in order to demonstrate experimental control.

• Extraneous Variables: Any aspect of the ENVIRONMENT that must be held constant to prevent unplanned environmental variation. 
  • Ex: Lighting, space, temperature of the room

• Confounding variables: Any uncontrolled factor known or suspected to exert influence on the independent variable.
  • Ex: Researcher analyzing test results of biology class with guided notes. Potential confounding variable would be students' interest in / background knowledge of topics of biology class. Notes may not have knowable / measurable effect on grades.

• Degree to which a study's results are generalizable to other subjects, settings, and / or behaviors (i.e., generalizable to EXTERNAL world).
• Degree to which a functional relation discovered in a study will hold under different conditions.
• External Validity is on a spectrum ranging from a little to a lot.
• Replication establishes external validity.

Scientific Replication

2 Methods Used in ABA:

1. Direct

2. Systematic

1. Direct Replication:
   • Researcher exactly duplicates a previous study.
   • Intrasubject direct replication = same subject used.
   • Intersubject direct replication = different subject used.
2. Systemic Replication:
   • Researcher purposefully varies one or more aspects of an earlier experiment.
   • Demonstrates reliability and external validity by showing the same effect can occur under different conditions.

• ABA research generally uses systematic replication

Treatment Integrity

AKA Procedural Fidelity

• Extent to which IV is implemented or carried out as planned.

• Ensuring High Level of Treatment Integrity:
  • Precise operational definition
  • Simplify, standardize and automate; Simple easy-to-implement treatments are more likely to be consistently delivered and socially validated.
  • Training and practice for mediators implementing experimental sessions.

• Assessing Treatment Integrity:
  • Collect treatment integrity data to measure how actual implementation of conditions matches written / expected implementation methods.
  • Observation and calibration give researcher ongoing ability to retrain and practice to ensure high treatment integrity.
  • Reduce, eliminate, or identify potential confounding variables.

• Low treatment integrity: Very difficult to interpret experimental results.
• Treatment Drift: When application of the IV in later phases differs from the original application.

1. Type I Error; (False Positive): Assuming the IV affected the DV, when it actually did NOT do so.
2. Type II Error; (False Negative): Assuming the IV did NOT affect the DV, when it actually did.

• Visual Analyses in ABA lean towards Type II errors.