The "What are/should..." questions from lecture 4

Question 1

What are three key elements of a true experiment?

Answer 1

• The IV is manipulated in different ways across groups
• Random assignment is used to assign participants to groups (without, it’s quasi)
• Experimental control is exerted to keep variables outside of the IV constant

Question 2

What are the advantages to using pretest?

Answer 2

• Allows for matching
• May evaluate the matched variables
• Allows for more powerful statistical tests
• Permits assessment of clinically significant change
• Allows evaluation of attrition

Question 3

What is the key goal or purpose of a Solomon four-group design?

Answer 3

To assess the effect of pretesting on the effects obtained with an intervention. Two groups as reflected in a pretest-posttest control group design, and two groups as reflected in a posttest-only control group design.

Question 4

What is a factorial design?

Answer 4

It allows for simultaneous investigation of two or more factors (IV). Each factor must have at least two or more groups/conditions/levels. Multiple variables are included to address questions about separate (main effects) and combined (interaction) effects of different variables.

Question 5

How is the Solomon four group design a factorial design?

Answer 5

It looks at the effect of pretest and posttest vs just posttest. Factor 1=pretest vs no pretest, Factor 2=tx vs no tx

Question 6

When would a Latin square be used instead of a simple crossover design?

Answer 6

When there is an increasing number of treatments (usually more than 2) and you want to look at them in multiple orders. This allows us to select the tx sequence in advance, and then as subjects arrive to participate, they are randomly assigned to a sequence. This assures that a subset of tx order possibilities are each presented to a rough equivalent number of participants.

Question 7

What should be considered when choosing a comparison or control group?

Answer 7

• Interests of the investigator
• Previous research findings (e.g., evidence states that a no-treatment control is not necessary)
• Practical and ethical constraints

Question 8

What are the potential problems associated with a no-treatment control group?

Answer 8

• Ethical issues (withholding tx)

- Practical problems (explanation of rationale, attrition)

Question 9

What is the strengths of a wait-list control group?

Answer 9

• Not as difficult to get subjects
• Effect of tx is replicated
• Between-group and within-group comparisons

Question 10

What is the weakness of a wait-list control group?

Answer 10

• May not assess long-term impact of tx

- May still be ethically questionable

Question 11

What is the key purpose/use of a nonspecific-tx group?

Answer 11

–Rule out the threats to construct validity, specifically common factors associated with therapy (e.g., attending sessions, having contract with a therapist, etc.) that are not the active ingredients of the treatment.

Question 12

What are the four advantages to using a routine or standard treatment comparison group?

Answer 12

1. Meets ethical standards=all subjects receive active tx
2. Attrition is less likely
3. Controls for nonspecific factors of therapy
4. Clinicians more satisfied as study personnel and as consumers of these research designs