Ch. 11

complete counterbalancing

all possible order sequences in which participants receive different treatments, or participate in different groups, are balanced or offset (used when # of treatments or groups is 2 or 3)

18. All of the following are strategies used to control for order effects except? a. Control order b. Control timing c. Counterbalancing d. Randomized assignment

d. Randomized assignment

two types of counterbalancing

complete counterbalancing partial counterbalancing

A related sample is selected when: a. the dependent variable is related to sampling error. b. only one level of an independent variable is manipulated. c. different participants are observed in each group. d. the same or matched participants are observed in each group.

d. the same or matched participants are observed in each group.

three groups complete counterbalancing example

- Soccer in fall, basketball in winter, volleyball in spring - Basketball in fall, volleyball in winter, soccer in spring - Volleyball in fall, soccer in winter, basketball in spring

matched samples design

A within-subjects research design in which participants are matched, experimentally or naturally, based on shared, preexisting characteristics

Which of the following is a key reason that researchers use a within-subjects design? a. To ensure that random assignment is used b. To manage sample size c. To observe changes in behavior over time d. To manage sample size and to observe changes in behavior over time

d. To manage sample size and to observe changes in behavior over time

F =

variability between groups over variability attributed to error

related-samples t test

statistical procedure used to test difference in interval or ratio scale data for two related samples

How many order sequences are possible when participants are observed in each of 2 groups? a. 1 b. 2 c. 3 d. 4

b. 2

Each of the following is a source of variation measured by a test statistic using the within-subjects design, EXCEPT: a. between-groups variability. b. between-persons variability. c. within-persons variability. d. within-groups variability.

c. within-persons variability.

23. How many order sequences are possible when participants are observed in each of 5 groups? a. 5 b. 25 c. 60 d. 120

d. 120

Which of the following is TRUE about the Solomon four-group design? a. It is an experimental research design. b. It does not include a posttest group. c. It is associated with low internal validity. d. Its main strength is the complexity of the design itself.

a. It is an experimental research design.

A researcher studies pairs of identical twins. The twins then participate in a study in which the differences in scores for each pair of identical twins are compared. What type of matched pairs is described in this example? a. Naturally occurring matched pairs b. Experimentally matched pairs c. Differentially matched pairs d. Statistically matched pairs

a. Naturally occurring matched pairs

A procedure in which the order that participants receive different treatments or participate in different groups is balanced or offset in an experiment is called: a. counterbalancing. b. median positioning. c. carryover effects. d. internal validity.

a. counterbalancing.

Which sampling design can be used when the same participants are observed across more than 2 groups? a. Matched samples design b. Repeated measures design c. Pre-post design d. Case study

b. Repeated measures design

For a one-way within-subjects ANOVA, the mean difference attributed to the manipulation is in the ________, and the mean difference attributed to individual differences is in the ________ of the test statistic. a. numerator; numerator b. denominator; numerator c. numerator; denominator d. denominator; denominator

c. numerator; denominator

Researchers can control timing by controlling: a. the interval between treatments or groups. b. the total duration of an experiment. c. the time it takes to randomly assign participants to groups . d. the interval between treatments or groups and the total duration of an experiment.

d. the interval between treatments or groups and the total duration of an experiment.

reasons for within subject-design

to compare responses of one individual to different exposures/treatments at one time to observe changes over time to limit error variance to limit sample size

within-subjects factor

type of factor in which the same participants are observed in each group, or at each level of the factor

For a related samples t-test, the mean difference attributed to the manipulation is measured as: a. the mean difference between groups. b. the difference among participant difference scores. c. within-groups variability. d. between-persons variability.

a. the mean difference between groups.

participant fatigue

added internal validity threat in within-subjects design can be a factor that influences the dependent variable

When the number of groups is greater than 3, ________ counterbalancing is most commonly used to control for possible order effects. a. complete b. partial c. grouped d. sequential

b. partial

within-subjects design

Design in which the same participants are observed one time in each group, or more than one time at each level of the factor

one-way within subjects ANOVA example

Does price of wine affect perceived taste/quality of the wine? * taste 3 glasses of wine with varying prices * actual wine is the same in the 3 glasses

What strategy is used to eliminate between-persons variability from the error term in the denominator of a test statistic when using a within-subjects design with 2 groups? a. The variability between-groups is not calculated. b. Difference scores are computed. c. An error term is not computed. d. Only the between-persons variability is computed.

b. Difference scores are computed.

Which test statistic is appropriate for analyzing the mean difference between 2 groups in which the same participants are observed in each group and the data are measured on an interval or ratio scale of measurement? a. Two-independent sample t-test b. Related samples t-test c. One-independent sample t-test d. None of the above

b. Related samples t-test

Which of the following is an example of counterbalancing for a two-group design in which participants are observed in Group A and Group B? a. The same participants are observed in Group B, then in Group A. b. The same participants are observed in Group A, then in Group B. c. Half the participants are observed in Group A, then in Group B; the other half of participants are observed in Group B, then in Group A. d. Half the participants are observed in Group A, then in Group B; the other half of participants are not observed in either group.

c. Half the participants are observed in Group A, then in Group B; the other half of participants are observed in Group B, then in Group A.

Which of the following is a common procedure used with partial counterbalancing? a. Random balancing b. Cross manipulation c. Latin square d. Sequential monitoring

c. Latin square

babies within-subjects experimental design

orientation/attention measured by the amount of time gazing at an object babies showed two pictures (mother, stranger) and # of seconds looking at each is recorded

The variability in a dependent measure that is caused by or associated with individual differences or differences in participant responses across all groups is assumed to be ________ in the test statistic for a within-subjects design. a. equal to 0 b. significant c. responsive d. large

a. equal to 0

A researcher uses a within-subjects design to observe 10 participants in each of 3 groups. How many total participants were observed? a. 10 b. 20 c. 30 d. 60

a. 10

Which of the following groups is NOT included in the Solomon four-group design? a. A group that receives a pretest only. b. A group that receives only a pretest then a posttest, but no treatment. c. A group that receives a pretest, treatment, and then a posttest. d. A group that receives a posttest only.

a. A group that receives a pretest only.

Source of variability measured by a test statistic that have nothing to do with having different groups are called: a. group means b. non-variability c. error d. significance

c. error

All of the following groups is included in the Solomon four-group design except? a. A group that receives a posttest only. b. A group that receives only a pretest then a posttest, but no treatment. c. A group that receives a pretest, treatment and then a posttest. d. A group that receives pretest only.

d. A group that receives pretest only.

A researcher selects one group of participants and observes them before and after a treatment meant to improve mood. What type of sampling design is described in this example? a. Between-subjects design b. Completely crossed design c. Matched samples design d. Pre-post design

d. Pre-post design

2 sources of control in experimental designs

-quasi-experimentation (statistical) -experimental - methodological (control order, timing) and statistical (compute test statistic)

A researcher observes the same participants in each of 4 groups: A, B, C, D. Which of the following is a representative set of four order sequences? Hint: The correct sequence was computed using a Latin square procedure. a. ABDC BCAD CDBA DACB b. ABCD DACB BDCA ABDC c. AABB BBCC CCDD DDAA d. DCBA ABCD DCAB

a. ABDC BCAD CDBA DACB

For a related samples t-test, the mean difference attributed to the manipulation is in the ________, and the mean difference attributed to individual differences is in the ________ of the test statistic. a. numerator; denominator b. denominator; numerator c. numerator; numerator d. denominator; denominator

a. numerator; denominator

threats to ______ validity especially occur in within-subjects design and affects the _________ variable

internal, dependent

two times within-subjects design

iv = time levels = each time, pretest to posttest knowledge acquisition, changes in mood, attitudes, behavior

two tests to compare two-related samples

related-samples t test one-way within-subjects analysis of variance

within groups variability

source of variance in a dependent measure that is caused by, or associated with, observing different participants within each group

between groups variability

source of variance in a dependent variable that caused by, or associated with, the manipulation of independent variable

partial counterbalancing

A procedure in which some, but not all, possible order sequences in which participants receive different treatments, or participate in different groups, are balanced or offset (when # of treatments is > 3)

between persons variability

Source of variance in a dependent measure (variable) that is caused by, or associated with, individual differences in responses across groups (assumed to be zero in a within-subjects design)

one time within subjects design

a study involving favorability ratings of different restaurants iv = type of restaurant levels = each restaurant dv = favorability

Why is a matched samples design not an experiment? a. Because groups are created based on preexisting characteristics of the participants, and not on a manipulation made by the researcher. b. Because two or more factors are observed at the same time and it is not possible to determine which factors is causing changes in the dependent variable. c. Because the same participants are observed in each group and it is not possible to control for order effects. d. Because the levels of the independent variable are manipulated and participants are randomly assigned to different groups.

a. Because groups are created based on preexisting characteristics of the participants, and not on a manipulation made by the researcher.

75. Which source of error is computed in the denominator of the test statistic for the between-subjects design, but not the within-subjects design? a. Between-persons b. Within-groups c. Between-groups d. Within-persons

a. Between-persons

A procedure in which all possible order sequences that participants receive different treatments or participate in different groups is balanced or offset in an experiment is called: a. complete counterbalancing. b. partial counterbalancing. c. median counterbalancing. d. intrinsic counterbalancing.

a. complete counterbalancing.

What is the source of variation that is removed from the error term in the denominator of the test statistic when using a within-subjects design? a. Between-groups variability b. Between-persons variability c. Within-persons variability d. Within-groups variability

b. Between-persons variability

When we compute a one-way within-subjects ANOVA, what strategy is used to reduce the value of error in the denominator? a. Difference scores are computed. b. Variability between-persons is computed and removed from the error term. c. All possible pairwise comparisons are made following a significant ANOVA. d. Variability within-groups is computed and removed from the error term

b. Variability between-persons is computed and removed from the error term.

A threat to internal validity in which the order that participants receive different treatments or participate in different groups causes changes in the dependent variable is called: a. sampling effects. b. order effects. c. counterbalancing. d. constant change.

b. order effects.

A procedure in which some, but not all, possible order sequences that participants receive different treatments or participate in different groups is balanced or offset in an experiment is called: a. complete counterbalancing. b. partial counterbalancing. c. median counterbalancing. d. intrinsic counterbalancing.

b. partial counterbalancing.

For a related samples t-test, the mean difference attributed to individual differences is measured as: a. between-persons variability. b. the difference among participant difference scores. c. between-groups variability. d. between-persons variability and the difference among participant difference scores.

b. the difference among participant difference scores.

Which of the following is NOT a requirement for constructing a Latin square? a. The number of order sequences equals the number of treatments. b. Each treatment appears equally often in each position. c. All possible order sequences are included and fully balanced. d. Each treatment precedes and follows each treatment one time.

c. All possible order sequences are included and fully balanced.

matched samples design ( can | cannot ) be used in an experiment

cannot because groups are created based on preexisting characteristics and not on a manipulation made by the researcher

another name for related-samples t test

paired samples t test dependent groups t test

carryover effects

participation in one group carries over, or causes changes in the performance of a second group (like testing effect)

Which source of variation measured by a test statistic is a measure of the mean difference caused by a manipulation? a. Between-groups variability b. Between-persons variability c. Within-persons variability d. Within-groups variability

a. Between-groups variability

three sources of variability

-between groups variability -within groups variability -between-persons variability

For a one-way within-subjects ANOVA, the mean difference attributed to the manipulation is measured as variability ________; the mean difference attributed to individual differences is measured as variability ________. a. between-groups; within-groups b. between-groups; between-persons c. within-groups; between-groups d. between-persons; within-persons

a. between-groups; within-groups

Counterbalancing does not ________ order effects, rather it makes possible order effects ________ in each treatment or group. a. eliminate; the same b. eliminate; different c. balance; variable d. balance; more likely

a. eliminate; the same

A state of physical or psychological exhaustion resulting from intense research demands typically due to observing participants too often, or requiring participants to engage in research activities that are too demanding is called: a. participant fatigue. b. schedule exhaustion. c. within-subjects demands. d. mixed emotions.

a. participant fatigue.

When the same participants are observed in each group, individual differences between groups are: a. the same. b. different. c. variable. d. unequal.

a. the same.

when the same participants are observed in each group, the individual differences of participants are _____________ in each group

also the same

Which of the following is an example of a within-subjects design? a. Participant health scores in a sample are compared to national health averages in the population. b. A researcher records the time that a sample of children play with each of four different toys. c. One sample of adults are selected and randomly assigned to one of three feedback conditions. d. A researcher records the time it takes police officers at two different precincts to respond to a similar emergency call.

b. A researcher records the time that a sample of children play with each of four different toys.

Which source of variation measured by a test statistic is a measure of individual differences between groups? a. Between-groups variability b. Between-persons variability c. Within-persons variability d. Within-subjects variability

b. Between-persons variability

Which research design allows for the use of randomization, manipulation, and comparison? a. Within-groups design b. Between-subjects design c. Within-subjects design d. Between-subjects design and within-subjects design

b. Between-subjects design

A researcher measures intelligence in a sample of children, and then matches them based on their scores. Participants with the two highest scores are paired, then the next two highest scores are paired, and so on. Children then participate in a study in which the differences in scores for each matched pair are compared. What type of matched pairs is described in this example? a. Naturally occurring matched pairs b. Experimentally matched pairs c. Differentially matched pairs d. Statistically matched pairs

b. Experimentally matched pairs

Find X in the following formula for error when using the within-subjects design: Error = X + 0. a. Between-groups variability b. Within-groups variability c. Between-persons variability d. Within-persons variability

b. Within-groups variability

76. A test statistic for a within-subjects design will detect ________ mean differences between groups compared to a test statistic for the between-subjects design. a. zero b. smaller c. all d. more obvious

b. smaller

What are the two types of counterbalancing? a. Grouped and ungrouped b. Same and different c. Complete and partial d. Balanced and unbalanced

c. Complete and partial (latin square)

Anytime the same participants are observed in each group, the design qualifies as a within-subjects experimental design. a. True b. False, a within-subjects design can never be experimental c. False, added controls are needed for time-related factors d. True, this is the definition of a within-subjects experimental design

c. False, added controls are needed for time-related factors

Which test statistic is appropriate for analyzing the mean difference between 2 or more groups in which the same participants are observed in each group and the data are measured on an interval or ratio scale of measurement? a. Two-independent sample t-test b. Related samples t-test c. One-way within-subjects ANOVA d. One-way between-subjects ANOVA

c. One-way within-subjects ANOVA

Which research design is associated with greater power to detect an effect? a. Within-groups design b. Between-groups design c. Within-subjects design d. Between-subjects design

c. Within-subjects design

Two sources of error that cannot be attributed to having different groups or treatments are called: a. between-groups variability and within-groups variability. b. between-persons variability and between-groups variability. c. between-persons variability and within-groups variability. d. between-groups variability and across-groups variability.

c. between-persons variability and within-groups variability.

A threat to internal validity in which participation in one group causes changes in performance in a second group is called: a. sampling effects. b. counterbalancing. c. carryover effects. d. constant change.

c. carryover effects.

A researcher matches participants based upon the common characteristics or traits that they share. The type of sampling design described in this example is: a. random sampling design. b. repeated measures design. c. matched samples design. d. pre-post design.

c. matched samples design.

A within-subjects research design in which participants are matched, experimentally or naturally, based on common characteristics or traits that they share, is called: a. between-subjects design. b. completely crossed design. c. matched samples design. d. pre-post design.

c. matched samples design.

Using a within-subjects design, individual differences are the same between groups because: a. random assignment was used. b. different participants are represented in each group. c. the same participants are represented in each group. d. the same dependent variable was measured in each group.

c. the same participants are represented in each group.

The between-persons variability is removed from the error term in the denominator of a test statistic when using a within-subjects design for all the following reasons except? a. Because the same participants are observed in each group. b. Because individual differences are the same between groups. c. Because we will assume that the value of the between-persons variability is 0. d. Because different participants are observed in each group.

d. Because different participants are observed in each group.

60. What is the most appropriate way to sampling participants using the within-subjects design? a. Participants are selected from a single population and are observed in one and only one group. b. Participants are selected from two or more populations and each sample selected constitutes a group in the experiment. c. Participants are selected from a single population and randomly assigned to multiple groups. d. Participants are selected from a single population and observed in multiple groups.

d. Participants are selected from a single population and observed in multiple groups.

All of the following are examples of time-related factors discussed in your textbook except? a. Testing effects b. Participant fatigue c. Regression toward the mean d. Researcher fatigue

d. Researcher fatigue

Which of the following is an advantage of the within-subjects design compared to the between-subjects design? a. The within-subjects design, but not the between-subjects design, allows for random assignment of participants to the levels of an independent variable. b. The within-subjects design requires a larger sample size to detect an effect compared to the between-subjects design. c. The within-subjects design, but not the between-subjects design, allows for the comparison of differences between group means. d. The within-subjects design has great power to detect an effect compared to the between-subjects design.

d. The within-subjects design has great power to detect an effect compared to the between-subjects design.

We compute a test statistic to: a. check that individual differences can be matched between groups. b. determine whether a within-subjects design or a between-subjects design is most likely to account for differences observed between groups. c. test the hypothesis that participants were assigned to groups at random. d. determine whether some manipulation or individual differences are likely to account for mean differences observed between groups.

d. determine whether some manipulation or individual differences are likely to account for mean differences observed between groups.

To qualify as an experiment, a within-subjects design must meet all of the following except: a. include manipulation and comparison. b. take added measures to control for order. c. take added measures to control for time-related factors. d. exclude manipulation and comparison.

d. exclude manipulation and comparison.

A Latin square is a matrix design in which a limited number of order sequences are constructed where all of the following occur except: a. the number of order sequences equals the number of treatments. b. each treatment appears equally often in each position. c. each treatment precedes and follows each treatment one time. d. the number of order sequences are higher than the number of treatments.

d. the number of order sequences are higher than the number of treatments.

Each of the following is an advantage of the within-subjects design compared to the between-subjects design, EXCEPT: a. the within-subjects design requires a smaller sample size. b. the within-subjects design has great power to detect an effect. c. the within-subjects design can be used to study small populations. d. the within-subjects design can only be used to study large populations.

d. the within-subjects design can only be used to study large populations.

A researcher has the same soldiers listen to a high-ranking officer give a verbal command in a low and in a high tone. The time it took soldiers to respond to the commands was recorded. The verbal command factor (low, high tone) can best be described as a: a. between-subjects factor. b. matches samples factor. c. within-groups factor. d. within-subjects factor.

d. within-subjects factor.

We assume that the between-persons variability is equal to ____ in a within-subjects design because ________. a. any positive value; different participants are observed in each group b. any positive value; the same participants are observed in each group c. zero; different participants are observed in each group d. zero; the same participants are observed in each group

d. zero; the same participants are observed in each group

latin squares design

is a matrix design in which a limited number of order sequences are constructed (1) the number of order sequences equals the number of treatments (2) each treatment appears equally often in each position (3) each treatment precedes and follows each other treatment one time

one-way within-subjects analysis of variance

is used to test for differences in group means for two or more levels or groups * The results inform us that at least one group is different from another group - it does not tell us which pairs of groups differ *posthoc tests are used when more than two groups exist

counterbalancing

researchers control order and carryover effects by balancing, or offsetting, the order in which participants receive different treatments in an experiment

order effects

the order of exposure influences dependent variable, these are controlled in an experiment could be time could also be sequence of exposure

Using a within-subjects experimental design, why must the researcher control for time related factors? a. Because the dependent variable is observed in only one group. b. Because the levels of the independent variable are the same, not different. c. Because the order that participants are observed can co-vary with the levels of the independent variable. d. Because there are no threats to internal validity when the same participants are observed in each group.

c. Because the order that participants are observed can co-vary with the levels of the independent variable.

The Solomon four-group design is an experimental research design in which different participants are assigned to each of 4 groups in such a way that comparisons can be made to: a. determine if a treatment causes changes in posttest measure. b. control for possible confounds or extraneous factors related to giving a pretest measure and observing participants over time. c. strengthen power by reducing the number of participants needed to be able to observe an effect. d. determine if a treatment causes changes in posttest measure and control for possible confounds or extraneous factors related to giving a pretest measure and observing participants over time.

d. determine if a treatment causes changes in posttest measure and control for possible confounds or extraneous factors related to giving a pretest measure and observing participants over time.

A post hoc test is used for all of the following except: a. following a significant ANOVA. b. to determine which pairs of group means were significantly different. c. to evaluate all possible pairwise comparisons. d. following any non-significant test result.

d. following any non-significant test result.

t =

mean differences between groups over mean differences attributed to error