Ch12 - Within-Subjects Designs: Small N

D. Reduced cost, training time, and animal use

Why are small N designs often preferred in animal research?

A. Higher generalizability

B. Easier counterbalancing

C. Greater statistical power

D. Reduced cost, training time, and animal use

C. Fisher's analysis of variance

Which development helped shift psychology toward large N designs?

A. Operant conditioning

B. Baseline methodology

C. Fisher's analysis of variance

D. Ethical review standards

A. Operant conditioning research

Small N designs have been used most extensively in which area?

A. Operant conditioning research

B. Survey research

C. Epidemiology

D. Cognitive neuroscience

B. Continuous behavior of individuals

What type of data did B. F. Skinner emphasize?

A. Group averages

B. Continuous behavior of individuals

C. Self-report measures

D. Test scores

D. To measure behavior without the independent variable

What is the primary function of a baseline in small N research?

A. To introduce treatment

B. To increase variability

C. To improve reliability

D. To measure behavior without the independent variable

C. Risk of relapse or harm

Why do clinical researchers sometimes avoid returning to baseline?

A. Statistical difficulty

B. Time constraints

C. Risk of relapse or harm

D. Equipment limitations

A. When relapse threatens health or safety

When is returning to baseline most ethically problematic?

A. When relapse threatens health or safety

B. When sample size is small

C. When treatment effects are weak

D. When behavior is unstable

B. Inability to rule out extraneous variables

What is the main drawback of not returning to baseline?

A. Reduced statistical power

B. Inability to rule out extraneous variables

C. Increased subject dropout

D. Lower reliability

D. Multiple baseline design

Which design introduces treatment sequentially across behaviors, settings, or subjects without withdrawal?

A. ABA design

B. Changing criterion design

C. Discrete trials design

D. Multiple baseline design

C. Behaviors, settings, or individuals

A multiple baseline design can be applied across

A. Only behaviors

B. Only subjects

C. Behaviors, settings, or individuals

D. Only laboratory conditions

A. Treatment is never withdrawn

Why is the multiple baseline design ethically advantageous?

A. Treatment is never withdrawn

B. Baselines are shortened

C. Fewer subjects are used

D. Statistical assumptions are avoided

B. Visual inspection of graphed data

How are results from small N designs most commonly evaluated?

A. Inferential statistics

B. Visual inspection of graphed data

C. Meta-analysis

D. Regression analysis

C. Statistical assumptions may be violated

Why is statistical analysis controversial in small N research?

A. It is unnecessary

B. It ignores baseline trends

C. Statistical assumptions may be violated

D. It inflates effect sizes

A. Changing criterion design

Which design reinforces behavior that gradually meets higher performance standards?

A. Changing criterion design

B. ABA reversal design

C. Multiple baseline design

D. Factorial design

D. Successive approximations

Changing criterion designs rely on reinforcement of

A. Random responses

B. Baseline behavior

C. Aggregate trends

D. Successive approximations

C. Discrete trials design

Which small N design uses no baseline and averages responses across many trials?

A. ABA design

B. Multiple baseline design

C. Discrete trials design

D. Changing criterion design

B. Hundreds or thousands of trials per subject

What distinguishes a discrete trials design from typical experiments?

A. Use of baselines

B. Hundreds or thousands of trials per subject

C. Large sample sizes

D. Counterbalancing

A. Large number of observations

Why do discrete trials designs produce highly reliable data?

A. Large number of observations

B. Random assignment

C. Matched groups

D. Statistical averaging

A. Small N design

A therapist measures the same child's behavior daily before and after intervention to determine whether the treatment works. Which approach is being used?

A. Small N design

B. Large N design

C. Survey design

D. Correlational design

A. ABA reversal design

A behavior improves when treatment is introduced, worsens when treatment is removed, and improves again when treatment returns. What design does this pattern demonstrate?

A. ABA reversal design

B. Multiple baseline design

C. Changing criterion design

D. Discrete trials design

B. Behavior may not reverse after treatment removal

A researcher avoids using an ABA design to teach reading because once learned, the skill will remain. Why is ABA inappropriate here?

A. Ethical review issues

B. Behavior may not reverse after treatment removal

C. Low statistical power

D. Lack of baseline

C. Risk of relapse or harm

A clinician refuses to withdraw treatment for severe self-injurious behavior. What concern prevents using a reversal design?

A. Sampling bias

B. Low reliability

C. Risk of relapse or harm

D. Time constraints

D. Multiple baseline design

Treatment is introduced at different times for different behaviors without removing treatment. Which design is being used?

A. ABA design

B. Changing criterion design

C. Discrete trials design

D. Multiple baseline design

A. Staggered introduction of treatment

What feature of the multiple baseline design allows causal conclusions without withdrawing treatment?

A. Staggered introduction of treatment

B. Random assignment

C. Long baselines

D. Visual inspection

B. Baselines are functionally independent

A multiple baseline study fails because all behaviors change at the same time. Which assumption was violated?

A. Stable measurement

B. Baselines are functionally independent

C. Ethical safeguards

D. Large sample size

A. Visual inspection of graphed data

A researcher judges treatment effectiveness by examining level, trend, and variability in graphs. What analysis method is used?

A. Visual inspection of graphed data

B. Inferential statistics

C. Meta-analysis

D. Regression analysis

A. Overlap between baseline and treatment data

Which graph feature weakens evidence that a treatment caused behavior change?

A. Overlap between baseline and treatment data

B. Replicated effects

C. Stable baseline

D. Immediate change in level

A. Immediate change in level

Which graph pattern most strongly supports a functional relationship?

A. Immediate change in level

B. Gradual drift

C. High variability

D. Random fluctuation

A. Changing criterion design

A therapist gradually increases required performance levels as behavior improves. Which design is being used?

A. Changing criterion design

B. ABA reversal design

C. Multiple baseline design

D. Discrete trials design

D. Close correspondence between criterion changes and behavior

What strengthens causal conclusions in a changing criterion design?

A. Random assignment

B. Large sample size

C. Long baselines

D. Close correspondence between criterion changes and behavior

D. Successive approximations

A child is reinforced for behaviors that increasingly resemble the target behavior. What principle is being applied?

A. Aggregate effects

B. Baseline correction

C. Counterbalancing

D. Successive approximations

C. Discrete trials design

A perception study averages thousands of trials from one participant instead of using a baseline. Which design is this?

A. ABA design

B. Multiple baseline design

C. Discrete trials design

D. Changing criterion design

B. Hundreds or thousands of trials per subject

Why can discrete trials designs produce reliable data with very few participants?

A. Random sampling

B. Hundreds or thousands of trials per subject

C. Treatment withdrawal

D. Counterbalancing

C. Repeated responses within a subject

In a discrete trials design, what is averaged to assess performance?

A. Group means

B. Baseline scores

C. Repeated responses within a subject

D. Treatment conditions

A. Repeated successful replications

How do small N researchers establish confidence in their findings across studies?

A. Repeated successful replications

B. Random sampling

C. Aggregate effects

D. Single-study inference

D. They require careful design and interpretation

A student assumes small N studies are easy because they use few subjects. Why is this incorrect?

A. They lack ethical oversight

B. They are outdated

C. They are inferior to large N designs

D. They require careful design and interpretation

D. Similarity of human sensory systems

Why can discrete trials research generalize from few subjects?

A. Ethical safeguards

B. Aggregate effects

C. Long baselines

D. Similarity of human sensory systems

B. When subjects are limited or clinical cases are studied

When is a small N design most appropriate?

A. When population generalization is required

B. When subjects are limited or clinical cases are studied

C. When random sampling is possible

D. When group comparison is essential

A. When many subjects are available and generality is desired

When is a large N design preferable?

A. When many subjects are available and generality is desired

B. When treatment withdrawal is unethical

C. When behavior is rare

D. When individual analysis is needed

C. Biased sampling

Why doesn't a large N design always guarantee generalizability?

A. Lack of baseline

B. Excessive averaging

C. Biased sampling

D. Limited power

D. Repeated successful replications

How do small N designs establish generality?

A. Random sampling

B. Statistical inference

C. Aggregate effects

D. Repeated successful replications

A. Functional relationships

What do small N researchers emphasize over statistical significance?

A. Functional relationships

B. Population estimates

C. Effect size indices

D. Aggregate trends

B. Individual control

What is the primary goal of a small N experiment?

A. Generalize to populations

B. Demonstrate experimental control within individuals

C. Maximize sample size

D. Reduce subject burden

C. Stability of baseline

Why must baseline data be stable before introducing treatment?

A. To reduce subject fatigue

B. To increase sample size

C. To attribute changes to the independent variable

D. To allow statistical testing

A. Reversal logic

What does an ABA design attempt to demonstrate?

A. That behavior changes systematically with introduction and removal of treatment

B. That behavior improves over time

C. That group means differ

D. That baselines are unnecessary

B. Prediction, verification, replication

According to the slides, what three elements establish experimental control in small N designs?

A. Randomization, matching, blocking

B. Prediction, verification, replication

C. Baseline, treatment, withdrawal

D. Reliability, validity, power

C. Visual analysis components

Which is part of visual inspection emphasized in the slides?

A. p-values

B. Confidence intervals

C. Level, trend, and variability

D. Regression coefficients

D. Immediate change in level

What pattern most strongly supports a treatment effect in a graph?

A. Gradual drift

B. High variability

C. Delayed change

D. Immediate change in level

A. Overlap between phases

What weakens the conclusion that a treatment caused behavior change?

A. Overlap between baseline and treatment data

B. Large number of observations

C. Stable baseline

D. Replicated effects

B. Carryover effects

Why can ABA designs be problematic for some behaviors?

A. Low reliability

B. Behavior may not reverse after treatment removal

C. Baseline cannot be measured

D. Too many subjects are required

C. Irreversibility

Which type of behavior is least appropriate for a reversal design?

A. Reaction time

B. Anxiety ratings

C. Learned skills that do not unlearn

D. Self-report scales

A. Staggered introduction

What is the defining feature of a multiple baseline design?

A. Staggered introduction of treatment

B. Removal of treatment

C. Random assignment

D. Repeated withdrawal

D. Temporal separation

Why does staggered treatment introduction strengthen causal inference?

A. It reduces variability

B. It increases sample size

C. It controls maturation

D. It separates treatment effects from time effects

B. Independence of baselines

What assumption is important for multiple baseline designs?

A. All baselines must be identical

B. Baselines are functionally independent

C. Subjects are randomly sampled

D. Treatments are reversible

C. Practical limitation

What is a limitation of multiple baseline designs noted in the slides?

A. Ethical concerns

B. Low reliability

C. Treatment must be introduced sequentially, which takes time

D. Need for large samples

A. Stepwise behavior change

What pattern is expected in a changing criterion design?

A. Stepwise changes corresponding to criterion shifts

B. Immediate return to baseline

C. Random fluctuation

D. Continuous decline

D. Criterion credibility

What strengthens conclusions in a changing criterion design?

A. Random assignment

B. Large N

C. Visual inspection alone

D. Close correspondence between criterion changes and behavior

B. No baseline phase

What distinguishes discrete trials designs from other small N designs?

A. Treatment withdrawal

B. No baseline phase

C. Visual inspection

D. Ethical concerns

C. Averaging within subjects

In discrete trials designs, what is averaged?

A. Group means

B. Baseline performance

C. Repeated responses within a subject

D. Treatment conditions

A. Psychophysical tradition

Discrete trials designs are most closely associated with which research tradition?

A. Psychophysics and sensory research

B. Clinical intervention research

C. Survey methodology

D. Developmental psychology

D. Replication across laboratories

According to the slides, how is confidence in discrete trials findings increased?

A. Random sampling

B. Counterbalancing

C. Statistical testing

D. Replication across labs and tasks

B. External validity concern

What is a common criticism of small N designs mentioned in the slides?

A. Poor measurement

B. Limited external validity

C. Low reliability

D. Excessive cost

A. Converging evidence

How do small N researchers respond to concerns about generality?

A. By accumulating converging replications

B. By increasing sample size

C. By using ANOVA

D. By averaging results

C. Slide emphasis

Why does the PowerPoint stress graphs so heavily?

A. Statistics are unnecessary

B. Graphs are easier to publish

C. Visual patterns reveal functional relationships

D. Graphs replace experimental control

D. Instructor warning

What caution about small N designs is explicitly stated in the slides?

A. They lack ethics approval

B. They are outdated

C. They are inferior to large N designs

D. They require careful design and interpretation