STAT Exam 2

Which of the following p values would be stronger evidence against the null hypothesis? A. .01. B. .90.

.01

If the null hypothesis is true, the z for a sample mean, single sample t test, related samples t test, and the independent t test all expect an obtained value close to +1.65. +1.96. +1.00. 0.

0

The "point-and-whisker" plot in Figure 6.1 displays the mean, median, and ___________ for each condition. A. 95% CI around the mean B. standard deviation

95% CI around the mean

In this research situation, which of the following results would be consistent with the scientific hypothesis? A. A higher mean in the VTTT condition and a small p value. B. A higher mean in the keyboard condition and a small p value. C. A higher mean in the VTTT condition and a large p value. D. A higher mean in the keyboard condition and a large p value.

A higher mean in the keyboard condition and a small p value.

the number [.12] in the character string "t (24) = 2.73, p = .01, 95% CI [.76, 5.50], d= .55, [.12, .96]" is the A. LB of the confidence interval for d. B. UB of the confidence interval for d. C. LB of the confidence interval for the mean difference. D. UB of the confidence interval for the mean difference.

A. LB of the confidence interval for d.

Values closer to the observed mean difference (i.e., the point estimate) are more plausible estimates of the population mean difference than values closer to the LB or UB. A. True B. False

A. True

A smaller p value reflects stronger evidence ___________ the null hypothesis. A. against B. for

A. against

One-tailed hypothesis tests are appropriate if A. an outcome in the opposite direction as you predicted does not have any implications for the population. B. you have a research/scientific hypothesis with a clear prediction in one direction.

A. an outcome in the opposite direction as you predicted does not have any implications for the population.

The major advantage of d as an effect size measure is that A. it is easily compared to other ds from other studies. B. it is always the best way to think about the effect size of a study.

A. it is easily compared to other ds from other studies.

Wider confidence intervals provide ___________ precise estimates of the population parameter. A. less B. more

A. less

The SEMs estimates the A. mean difference one should expect in a study due to sampling error given the sample size. B. likelihood the null hypothesis is true. C. likelihood the research hypothesis is true.

A. mean difference one should expect in a study due to

The traditional threshold approach to p values is flawed because (Choose all that apply) A. nearly identical p values can lead to opposite scientific conclusions. B. p values vary along a continuous range from p = 1 to p = 0 and dichotomizing these values into "significant" and "not significant" categories can frequently mischaracterize the statistical evidence. C. the research hypothesis is frequently false.

A. nearly identical p values can lead to opposite scientific conclusions. B. p values vary along a continuous range from p = 1 to p = 0 and dichotomizing these values into "significant" and "not significant" categories can frequently mischaracterize the statistical evidence.

The p value from a hypothesis test provides information about A. the likelihood that an outcome occurred due to sampling error. B. the magnitude of the difference between the sample mean and the population mean.

A. the likelihood that an outcome occurred due to sampling error.

A p value is the probability of getting the sample mean or a more extreme sample mean assuming that A. the null hypothesis is true. B. the null hypothesis is false.

A. the null hypothesis is true.

Researchers need to be very cautious when interpreting null results A. but if multiple well-conducted studies report similar null results it is appropriate to suggest a theory should be revised or abandoned. B. because a null result might occur because of a problem with the study's experimental procedure. C. because even if the null hypothesis is false a null result can occur if the sample size is too small. D. All of the above.

All of the above.

When formulating scientific conclusions, you should consider the p value from the hypothesis test. the effect size. the CIs. the methodological rigor of the study. the evidence provided by previous researchers in the scientific literature. All of the above.

All of the above.

When you get a large p value, how should you interpret a small effect size? A. It depends. Small effect sizes can be important. B. Although small effect sizes can be important, if they are accompanied by a large p value, they should not be considered informative.

Although small effect sizes can be important, if they are accompanied by a large p value, they should not be considered informative.

Which of the following is a correct interpretation of a p value of .02? A. The null hypothesis has only a 2% chance of being true. B. If the null hypothesis is true, the probability of the obtained t value or a more extreme t value is .02.

B. If the null hypothesis is true, the probability of the obtained t value or a more extreme t value is .02.

Which of the following information is provided by CIs and not other statistics? A. The probability that the observed result occurred due to sampling error. B. The precision of population estimates (i.e., how precisely the sample estimates the population parameters). C. The probability that the sample mean is between the upper and lower bounds.

B. The precision of population estimates (i.e., how precisely the sample estimates the population parameters).

How do you obtain the p values for a single sample t test? A. Look them up in the unit normal table. B. Use statistical software to compute them.

B. Use statistical software to compute them.

You can use a single sample t test to compare A. three or more sample means to each other. B. a sample mean to a known value of interest (e.g., a population mean).

B. a sample mean to a known value of interest (e.g., a population mean).

Basing your scientific conclusions on all four pillars of scientific reasoning is a good idea because it encourages you to make A. scientific conclusions with absolute certainty. B. appropriately cautious scientific conclusions. C. shacks or mansions. I'm not really sure what the authors were talking about.

B. appropriately cautious scientific conclusions.

The number in the parentheses in the character string "t (24) = 2.73, p = .01, 95% CI[.76, 5.50], d = .55, [.12, .96]" is the A. number of participants in the study. B. degrees of freedom. C. critical t value.

B. degrees of freedom.

One of the reasons confidence intervals are so valuable to scientific reasoning is that they encourage researchers to A. determine if a p value is significant or not significant. B. interpret their results cautiously by making them consider the range of possibilities that might reasonably exist in the population. C. make bold scientific statements that will grab newspaper headlines.

B. interpret their results cautiously by making them consider the range of possibilities that might reasonably exist in the population.

In general, the smaller the effect you are trying to detect, the ___________ your sample size needs to be. A. smaller B. larger

B. larger

There are three kinds of confidence intervals but all three estimate the range of values one might expect in the population based on a A. hypothesis test. B. margin of sampling error around a point estimate from the sample. C. margin of effect size around a hypothesis test.

B. margin of sampling error around a point estimate from the sample.

Researchers sometimes report a p value of .041 as p < .05 rather than p = .041. Which is a better, more-informative way to present p values? A. p < .05. B. p = .041.

B. p = .041.

When computing an effect size, you are getting information on the A. sampling error. B. practical importance (i.e., magnitude of the effect).

B. practical importance (i.e., magnitude of the effect).

One-tailed p values are ___________ two-tailed p values for the same t statistic. A.larger than B. smaller than C. the same size as

B. smaller than

When interpreting 95% CIs you should determine if A. the lower boundary value surpasses your idea of practical importance. B. the lower and upper boundary values suggest similar or different interpretations. C. Both of the above responses are correct.

C. Both of the above responses are correct.

Your written scientific conclusion should include all of the statistical evidence (i.e., exact p value, effect size, CI) and then it should also provide an interpretation that considers A. the scientific literature. B. the methodological rigor of the study. C. Both of the above responses are correct.

C. Both of the above responses are correct.

Which of the following is a correct interpretation of a p value of .06? A. The probability of the obtained t is .06. B. The probability of the obtained t or a more extreme t is .06. C. The probability of the obtained t or a more extreme t is .06 if the null hypothesis is true.

C. The probability of the obtained t or a more extreme t is .06 if the null hypothesis is true.

The statistical hypothesis is often referred to as the ___________ hypothesis. A. research B. scientific C. null

C. null

When reporting results in APA style, you should include information about A. the hypothesis test (i.e., p value). B. practical importance (i.e., effect size). C. plausible parameters (i.e., LB to UB range). D. All of the above responses are correct.

D. All of the above responses are correct.

When interpreting p values using three-valued logic, you can reach one of three conclusions. Which of the following is NOT one of these conclusions? A. Suspend judgment about the difference. B. The difference is probably negative. C. The difference is probably positive. D. There is no difference.

D. There is no difference.

When performing a single sample t test, the ___________ assumption is the most difficult to assess because you do not know the population standard deviation. A.data independence B. appropriate measurement of the IV and DV C. normality of the distribution of sample means D. homogeneity of variance

D. homogeneity of variance

Which of the following is NOT a pillar of scientific reasoning? A. Hypothesis testing. B. Effect sizes. C. Confidence intervals. D. Contextualizing the results by considering the methodological rigor and the scientific literature. E. Your own personal beliefs and political ideology.

E. Your own personal beliefs and political ideology.

Difference scores will always be positive. A. True B. False

False

Which of the following common statistical assumptions is NOT an assumption of the related samples t test? A. Data independence. B. Appropriate measurement of the variables. C. The distribution of sample mean differences must have a normal. D. Homogeneity of variance.

Homogeneity of variance.

How should the existing scientific literature influence your interpretation of a null result? A. It should not. Your scientific conclusion should be based solely on the data you collected in your study. B. If multiple studies investigating the same theory report null results, it should decrease your confidence in that theory. It may even cause you to reject that theory entirely.

If multiple studies investigating the same theory report null results, it should decrease your confidence in that theory. It may even cause you to reject that theory entirely.

Which test statistic should you use to determine the likelihood that the difference between two unrelated samples is due to sampling error? A. z for a sample mean. B. Single sample t test. C. Independent t test.

Independent t test.

Which of the following values is a measure of sampling error? A. SSD B. SDD C. SEMr

SEMr

When you get a large p value, how should you interpret a large effect size? A. The large effect size should be ignored. B. The large effect size should be used to argue in favor of the scientific hypothesis. C. The only way you can get a large p value and a large effect size is if your sample size is too small, so you should redo the study with a larger sample size.

The only way you can get a large p value and a large effect size is if your sample size is too small, so you should redo the study with a larger sample size.

Which of the following is the best summary of the two-tailed null hypothesis? A. People in the verbal description group will not have higher memory scores than people in the no-verbal description group. B. The people in the verbal description group will have the same memory scores as people in the no-verbal description group.

The people in the verbal description group will have the same memory scores as people in the no-verbal description group.

The two effect sizes computed in this section (dz = 1.56 and gav = .51) were both computed from the same data but using different formulas. Why is it important to report which effect size formula you used? A. The two formulas often produce dramatically different effect size estimates with dramatically different interpretations. B. The dz tends to produce smaller effect size estimates than the gav.

The two formulas often produce dramatically different effect size estimates with dramatically different interpretations.

The p value is the probability of getting ___________ if the null hypothesis is true and there are no methodological flaws in the study. A. a t value as extreme or more extreme than the one that was computed from the sample data B. a t value exactly equal to the one that was computed from the sample data

a t value as extreme or more extreme than the one that was computed from the sample data

When constructing a scientific conclusion, you need to consider A. the statistical evidence. B. the methodological rigor of the control procedures used to collect the data. C. the results of other similar studies in the scientific literature. D. all of the above.

all of the above

The estimated standard error of the mean difference is A. used to find the numerator for the t test. B. an estimate of how different the two sample means are expected to be due to sampling error. C. Both (a) and (b) are correct.

an estimate of how different the two sample means are expected to be due to sampling error.

The related samples t test can be used for a study that is using A. a matching approach. B. a pre-post approach. C. both a matching and a pre-post approach.

both a matching and a pre-post approach.

As with all types of t tests (e.g., single sample t test and others), a t value that is close to zero suggests that the data are A. compatible with the null hypothesis. B. incompatible with the null hypothesis.

compatible with the null hypothesis.

The Levene's test will help you determine the probability that the observed difference between two sample means is due to sampling error. A. if the two conditions have similar variances or variances that are very different (i.e., if the homogeneity of variance assumption is met or violated). B. if the sample size is sufficiently large.

if the sample size is sufficiently large.

One of the reasons confidence intervals are so valuable to scientific reasoning is that they encourage researchers to A. determine if a p value is significant or not significant. B. interpret their results cautiously by making them consider the range of possibilities that might reasonably exist in the population. C. make bold scientific statements that will grab newspaper headlines.

interpret their results cautiously by making them consider the range of possibilities that might reasonably exist in the population.

The p value from the related samples t test (p < .001) A. indicates that the VTTT's superior performance could not have occurred due to sampling error. B. proves that VTTT is superior to keyboard texting. C. is compelling evidence of the superiority of VTTT as long as the study had no methodological flaws.

is compelling evidence of the superiority of VTTT as long as the study had no methodological flaws.

The study's p value __________ (is/is not) compelling evidence against the statistical null hypothesis.

is not

The study's obtained t value suggests that the mean difference was __________ (less/more) than would be expected due to sampling error.

less

Both CIs described in this section estimate the range of values one might expect in the population based on a A. hypothesis test. B. margin of expected sampling error around a point estimate from the sample. C. margin of effect size around a hypothesis test.

margin of expected sampling error around a point estimate from the sample.

If the p value (i.e., in this case, p < .001) is small, the difference between the two means is A. likely to be due to sampling error. B. not likely to be due to sampling error.

not likely to be due to sampling error.

In general, the more the two confidence intervals overlap in a graph comparing two treatment conditions, the closer to ___________ the p value in the hypothesis test. A. zero B. one

one

The research situation described here is using a A.matched design. B. repeated measures design.

repeated measures design.

The independent t test is a ratio of the difference between two sample means over an estimate of A. sampling error. B. the standard deviation of the scores. C. variability.

sampling error.

The d is interpreted as the distance between two means in A. standard deviation units. B. standard error units.

standard deviation units.

The effect size (dz = 1.56) suggests (think back to ex in textbook) A. that the number of off-road glances generated by keyboard texting was 1.56 of a standard deviation higher than that generated by VTTT. B. The number of off-road glances generated by keyboard texting was 1.56 higher than the number generated by VTTT.

that the number of off-road glances generated by keyboard texting was 1.56 of a standard deviation higher than that generated by VTTT.

in general, t tests with low p values provide evidence A. that the null hypothesis is false. B. that the result would be unlikely to occur if the null hypothesis were true.

that the result would be unlikely to occur if the null hypothesis were true.

To compute the effect size, you divide the observed deviation between the means by A. the standard deviation of the difference scores. B. the SEM. C. the obtained t value.

the standard deviation of the difference scores.

The denominators of the single sample t test and the related samples t test are both A. expected to be 0 if the null is true. B. the typical amount of sampling error expected in the study.

the typical amount of sampling error expected in the study.

You use a related samples t statistic when there are two matched samples and the outcome variable is measured on an interval/ratio scale OR A. there are two independent samples and the outcome variable is measured on an interval/ratio scale. B. there is one sample, the outcome variable is measured on an interval/ratio scale, and the outcome variable is measured twice from that same sample each time in a different condition. C. there is one sample and the outcome variable is measured on an interval/ratio scale and you do not know the population standard deviation.

there is one sample, the outcome variable is measured on an interval/ratio scale, and the outcome variable is measured twice from that same sample each time in a different condition.

Researchers use the related samples t test to determine if ___________ differ more than would be expected by sampling error. A. two related sample means B. a sample mean and a population mean

two related sample means

The numerator of the independent samples t test is the difference between A. two sample means. B. a sample mean and a population mean. C. a sample mean and the null hypothesis.

two sample means.

When you get a large p value you should A. conclude the null hypothesis is true. B. withhold judgment until you consider other possibilities (e.g., sample size and methodological rigor).

withhold judgment until you consider other possibilities (e.g., sample size and methodological rigor).

Which of the following represents the null hypothesis when doing a two-tailed independent test? A. µ1 = µ2 B. µ1 ≠ µ2

µ1 = µ2

Which of the following best represents the null hypothesis for a two-tailed related samples t test? A. µD ≠ 0. B. µD = 0.

µD = 0.