Question 1

A Greenhouse and Geisser correction is a correction applied to

Accepted Answer

The Greenhouse-Geisser correction is applied to correct the degrees of freedom in repeated measures ANOVA. It assumes that the sphericity assumption (homogeneity of variances between conditions) is violated, and it adjusts the degrees of freedom to make the test more conservative. The correction is not applied to the mean, variance or interpretation.

Question 2

The text used an example in which the author rearranged the data points to look as if they came from a repeated-measures design. In real life we would not move our data points around so that we could analyze them as repeated measures. Why not?

Accepted Answer

It would be unethical to alter data in that way. Altering the order of data points or manipulating data in any way to fit a desired statistical analysis is considered scientific misconduct and goes against the ethical principles of research. It is important to accurately report the data as it was collected, even if it may not perfectly fit with the desired statistical analysis.

Question 3

In the printout of results for a repeated-measures analysis of variance, an F score for "mean" or "constant" sometimes appears. Why is this statistic often not interesting even if it is significant?

Accepted Answer

The F score for "mean" or "constant" shows whether the population mean is or is not equal to zero, which is often not of interest in the analysis. Therefore, even if it is significant, it may not be practically meaningful.

Question 4

A _______ design is one in which subjects are measured repeatedly over time.

Accepted Answer

A repeated-measures design involves measuring the same subjects at multiple points in time, allowing for an analysis of within-subject changes. The other options - between-subjects, factorial, and matched groups - do not involve repeated measurements of the same subjects.

Question 5

If a repeated-measures analysis of variance usually has an error term that is smaller that the error term in the corresponding between-subjects design, then we can assume that

Accepted Answer

The smaller error term in a repeated-measures design indicates that there is less variability in the data, which in turn increases the power of the design compared to a between-subjects design. Therefore, repeated-measures designs have greater power.

Question 6

In a typical learning experiment, a carry-over effect is

Accepted Answer

A carry-over effect is when something from one phase of an experiment affects the results of a subsequent phase, such as learning from an earlier test affecting performance on a later test. In many learning experiments, studying carry-over effects is actually the main focus, so it is what is being studied rather than something to be avoided or seen as a necessary evil. Option C is incorrect because carry-over effects are common and likely to be present in many types of learning experiments.

Question 7

Which of the following demonstrates the similarities of a repeated-measures analysis of variance for two trials and a t test for related means?

Accepted Answer

In a repeated-measures ANOVA for two trials, the F statistic is equivalent to the square of the t statistic from a t test for related means.

Question 8

If both the Greenhouse and Geisser and the Huynh and Feldt corrections lead to significant results we should

Accepted Answer

If both corrections lead to significant results, it suggests that violating the assumptions of sphericity may not have had a significant impact on the analysis. Therefore, we can still consider the results valid and not have to worry too much about the assumptions.

Question 9

Counterbalancing is a technique to

Accepted Answer

Counterbalancing is a technique used to evenly distribute any carry-over effects (effects from the previous condition) across the data. This helps to reduce the impact of any confounding variables and ensures that the results are more reliable and valid.

Question 10

By shifting the data around the way the author did at the end of the repeated measures chapter, he was able to show that

Accepted Answer

By shifting the data around, the author was able to remove the differences due to subjects from the error term, which led to a smaller error term and therefore a higher F value. The means themselves did not change, so A is incorrect. The F did not decrease, so C is incorrect. Therefore, the best choice is B.

Question 11

In a repeated-measures ANOVA, tests to correct the degrees of freedom, such as Greenhouse-Gelsser and Huynh-Feldt, should be used if

Accepted Answer

Tests to correct degrees of freedom, such as Greenhouse-Gelsser and Huynh-Feldt, are used when the assumption of sphericity is violated, which occurs when the correlations between the repeated measures are not constant. Choice A correctly identifies this situation.

Question 12

In a learning study using repeated measures, the correlation between early and later times will likely be low. Analyzing fewer levels of the independent variable would help to avoid violating the assumption of

Accepted Answer

The assumption of constant correlations among pairs of levels of the repeated variables is known as compound symmetry. When analyzing more levels of the independent variable, the assumption of compound symmetry may be violated, leading to low correlations between early and later times. Therefore, analyzing fewer levels of the independent variable would help to avoid violating this assumption.

Question 13

The major disadvantage with repeated-measures designs is that they

Accepted Answer

Repeated-measures designs expose participants to multiple conditions, so there is a risk of carry-over effects, in which an earlier condition affects performance on a later condition. This can lead to confounding and reduce the validity of the results.

Question 14

If the assumption of constant correlations in a repeated-measures ANOVA is violated, which of the following is true?

Accepted Answer

When the assumption of sphericity (constant correlations) is violated in a repeated-measures ANOVA, the degrees of freedom should be adjusted using corrections like Greenhouse-Geisser or Huynh-Feldt to maintain the validity of the test.

Question 15

In an example in the text, an independent samples analysis of variance example from a previous chapter was converted to be used in a repeated-measures analysis of variance. Recalculating the F value with a repeated-measures analysis of variance yields an F value that is

Accepted Answer

Repeated-measures ANOVA typically results in a greater F value compared to independent measures ANOVA because it accounts for variance due to individual differences, thereby reducing error variance and potentially increasing the F ratio.

Question 16

The typical way to control sequence effects is called

Accepted Answer

Counterbalancing involves using different sequences of conditions across participants to control for any sequence effects. This is the most typical way to control sequence effects. A is incorrect because block randomization doesn't necessarily control for sequence effects. B is incorrect because cross-sectional experimentation refers to a type of research design, not a method for controlling sequence effects. C is incorrect because asymmetrical transfer is not a method for controlling sequence effects.

Question 17

If any reasonable person would expect that with 4 trials the last trial is almost certain to be significantly different from the first, then Fisher's LSD test

Accepted Answer

Fisher's LSD test has a smaller degree of protection against a high familywise error rate because it does not take into account the increased probability of making a Type I error when conducting multiple tests on the same data set. With 4 trials, the likelihood of finding a significant difference by chance alone increases, and Fisher's LSD test may falsely identify a significant difference when in reality there is none. Therefore, it is important to use a correction method such as the Bonferroni correction or the false discovery rate adjustment to control for the familywise error rate.

Question 18

A design in which each subject receives all levels of an independent variable is called a(n)

Accepted Answer

A repeated-measures design involves testing the same group of participants under different experimental conditions, with each participant receiving all levels of the independent variable. Independent samples t-test and between-subjects design involve different groups of participants for different conditions. Correlation involves measuring the strength and direction of the relationship between two variables, and does not involve experimental manipulation.

Question 19

Some summary tables include a term labeled "mean" or "constant," with a corresponding F test. This tests the hypothesis that

Accepted Answer

The term "mean" or "constant" in summary tables, when associated with an F test, is typically testing the hypothesis that the population mean is 0.00. This is a common hypothesis test in statistical analysis to determine if there is a significant deviation from a hypothesized value, in this case, zero.

Question 20

A researcher wanted to see how watching movies influenced subjects' IQ scores. She gave IQ tests to subjects following each of two movies. Half of the subjects first saw Titanic followed by Schindler's List , while the other half first saw Schindler's List and then Titanic . Varying the movie order is an example of

Accepted Answer

Varying the movie order is an example of counterbalancing, which is a technique used to control for order effects in experimental designs. By administering the two movies in different order to different groups, the researcher can ensure that any observed differences in IQ scores are not simply due to the order in which the movies were viewed. Random sampling is a technique used to select participants for a study, selection bias refers to the distortion of results due to non-random selection of participants, and practice effects refer to improvements in performance on a task due to repeated exposure. None of these are relevant to the manipulation of movie order in this study.

Quiz 18: Repeated-Measures Analysis of Variance