Deck 9: Experimental Design

Question 1

In a balanced Latin square design:

A) each treatment appears multiple times in each row
B) each treatment appears multiple times in each column
C) each treatment is more likely to be followed by a particular alternative treatment
D) each treatment precedes and follows every other treatment equally often

Answer 1

each treatment precedes and follows every other treatment equally often

Question 2

When would it be appropriate to completely counterbalance a set of conditions?

A) The order of the conditions is not expected to have an effect.
B) There are only a few conditions,and the order of conditions is expected to affect the dependent measure.
C) It is not known whether or not order of the conditions is important,and there are a large number of conditions.
D) Variables are expected to interact.

Answer 2

There are only a few conditions,and the order of conditions is expected to affect the dependent measure.

Question 3

Advantages of within- over between-subjects designs include all of the following except that:

A) there is less chance of contamination between treatments
B) fewer subjects are needed
C) there is less chance of differences between groups
D) each subject is her or his own control

Answer 3

there is less chance of contamination between treatments

Question 4

In a completely counterbalanced experimental design:

A) each subject group receives a different treatment
B) each subject receives each treatment in the same order
C) all possible treatment orders are used
D) the order of treatments is randomized

Question 5

Careful experiments should include:

A) non-active control conditions
B) active control conditions
C) control conditions,but not placebos
D) placebos,but not control conditions

Question 6

Counterbalancing is used:

A) in within-subjects designs to eliminate carryover effects
B) in between-subjects designs to produce equivalent groups
C) in within-subjects designs to distribute order effects evenly across treatments
D) in between-subjects designs to reduce the effects of demand characteristics

Question 7

For between-subjects designs,randomization and matching are techniques used in an attempt to:

A) prevent treatment carry-over effects
B) ensure that groups are equal at the start of the experiment
C) provide ways for counterbalancing for each condition
D) provide strong levels of the independent variable

Question 8

Which of these variables should not be included in the placebo group of a between-subjects experiment?

A) all extraneous factors
B) experiment-wide demand characteristic effects
C) treatment nonspecific effects
D) treatment-specific demand characteristic effects

Question 9

Randomization is usually preferred to matching for establishing group equivalence because:

A) we may not know all the relevant variables to match
B) there is less confounding involved in randomization
C) randomization guarantees group equivalence
D) counterbalancing is not required with randomization

Question 10

Which statement about matching along subject variables is true?

A) Scores along the variable are usually easy to measure.
B) Matching on one variable may cause a mismatch on another variable.
C) Matching procedures do not require many participants.
D) They always produce a selection bias.

Question 11

A major disadvantage of within-subjects designs is that:

A) they are less efficient
B) subject differences may obscure treatment effects
C) the effect of one treatment may alter the effectiveness of the other
D) one must use fewer independent variables

Question 12

Which of the following is not a reason for subject attrition?

A) reliance on random assignment of participants to conditions
B) the fact that the data of some participants cannot be interpreted
C) participants may simply refuse to complete the experiment
D) participants may mature beyond the developmental stage required for inclusion

Question 13

A major disadvantage of between-subjects designs is that:

A) the effects of one treatment may alter another
B) subject differences may obscure treatment effects
C) one must use fewer independent variables
D) subject variables (such as age and sex)cannot be studied

Question 14

Assume that a researcher is interested in determining the potential effect of alcoholic beverage intake on test performance.Each student agrees to drink either 0,1,2,4,or 8 beers the night before the exam,as assigned by the experimenter.The experimenter appears to be relying upon a ____ design.

A) within-subjects
B) between-subjects
C) mixed
D) counterbalanced

Question 15

What is the most effective way to minimize the differences between two groups of participants if you have already identified their important characteristics that could influence the dependent measure?

A) Match the groups along the important characteristics.
B) Randomize the assignment of participants to the two groups.
C) Randomize the order of levels along the independent variable(s).
D) Use a mixed design.

Question 16

In a Latin square design:

A) each subject receives each treatment in the same order
B) all possible treatment orders are used
C) each subject receives a different treatment
D) each treatment occurs equally often in each ordinal position of the experiment

Question 17

Dr.No is thinking of doing a controlled study on the effects of various levels of radiation on the health of his enemies.Why might he want to consider conducting it as a between-subjects study (rather than as a within-subjects study)?

A) It will be less time consuming.
B) It will require fewer enemies.
C) It will be more conclusive about the performance of each individual enemy.
D) One level of radiation will not influence performance along another level.

Question 18

In Brady,et al.'s (1958)experiments,"executive monkeys" could prevent shocks from being delivered to them and another ("helpless")monkey.Contrary to the original conclusions,it now appears that the "executives" died from ulcers because of:

A) a selection bias for how likely monkeys were to make the avoidance response.
B) the fact that shocks were randomly delivered.
C) an increase in stress induced by having control over the shocks.
D) stress induced by helpless monkeys on executives.

Question 19

To try to obtain equivalent groups in between-subjects designs in an unbiased way,it is generally best to:

A) randomly assign subjects to the treatment groups
B) attempt to perfectly match subjects on relevant variables
C) attempt to find subjects who are volunteers
D) conduct an experiment only using your colleagues as participants

Question 20

The difference between a within-subjects and a between-subjects design is:

A) there is no problem of group equivalence with between-subject designs
B) confounding cannot occur with a between-subjects design
C) each subject serves as his or her own control in a within-subjects design
D) a given subject's behavior is only measured once in a within-subjects design

Question 21

In an experiment designed to test the effects of alcohol on appetite,if drinks X and Y contain .5 and 1.0 ounces of vodka in orange juice,respectively,and drink Z contains only orange juice,then the control group in the study should receive:

A) drink X
B) drink Y
C) drink Z
D) no drink

Question 22

The confounded variables in the executive monkey experiment were response rate and the independent variable.

Question 23

Randomized assignment to conditions guarantees that groups will be equivalent in a between-subjects design.

Question 24

If your experimental treatment produces a permanent effect on your subjects,you should use:

A) a within-subjects design with counterbalancing
B) a within-subjects design without counterbalancing
C) a between-subjects design
D) a mixed design

Question 25

A control group or control condition is included in an experiment to:

A) allow counterbalancing of the levels of the independent variables of interest
B) provide a baseline to which the variable of interest can be compared
C) prevent ceiling or floor effects
D) evaluate experimenter effects and other confounding

Question 26

Beaver trappers preferred the continuous payment schedule to the variable one.

Question 27

If you did an experiment and expected both permanent carry-over effects and large individual differences among your subjects,you should:

A) use a within-subjects design
B) use a between-subjects design
C) use a mixed design
D) do the experiment twice,once between and once within

Question 28

One difficulty with trying to match groups is that there may be subject attrition.

Question 29

Meta-analyses have revealed that cortisol hormone in human saliva is impacted by stress from cognitive tasks,but not stress induced by noise.

Question 30

One of the greatest assets of within-subjects procedures is that:

A) they eliminate carryover effects.
B) less time is required with a given participant.
C) the researcher no longer has to worry about randomizing conditions.
D) participants act as their own control group.

Question 31

A complete counterbalancing procedure would be more reasonable and preferred relative to incomplete counterbalancing methods for a within-subjects design composed of six treatments.

Question 32

Jarrard controlled for carryover effects in his experiments on LSD by using a between-subjects design.

Question 33

Counterbalancing is used only to assign levels of the independent variable in within-subjects designs.

Question 34

The control group:

A) receives all levels of the control variable
B) does not receive the independent variable
C) does not receive the level of interest of the independent variable
D) is included in a within-subjects design

Question 35

You would most likely use a within-subjects design if your independent variable were:

A) time
B) sex
C) age
D) brain damage

Question 36

In a between-subjects design,participants receive more than one level of an independent variable.

Question 37

A mixed design is one in which:

A) there is one independent and one dependent variable
B) one independent variable is tested within subjects and another is tested between subjects
C) one independent variable is ex post facto and the other is manipulated
D) carry-over effects are stronger in one direction than in another

Question 38

In a balanced Latin square,each treatment precedes and follows every other treatment equally often.

Question 39

Which of the following variables is least susceptible to carryover effects?

A) brain damage
B) age
C) amount of practice with a task
D) pitch of a tone

Question 40

When would it be wisest to rely on a between-subjects design rather than a within-subjects design?

A) The independent variable is likely to have a permanent effect.
B) You are interested in studying practice effects.
C) There are likely to be large individual differences in performance.
D) You wish to track the effects of learning over time.

Question 41

If you were interested in differences in the behavior of men and women on some task,you must use a between-subjects design.

Question 42

Mixed designs are more efficient than within-subjects designs.

Question 43

Mixed designs must have at least one within-subjects variable.

Question 44

The control group serves as a standard of comparison for the experimental group.

Question 45

Within-subjects designs are generally more sensitive than between-subjects designs to effects of independent variables.