STATS Compiled Quiz Questions/Answers

Given the following values for a desirable outcome variable such as self-esteem, the effect size is: Experimental group mean = 70 Control group mean = 60 Control group standard deviation = 20 A. +10 B. -10 C. +.5 D. -.5

+.5

Given the following values, the z score is: Raw score = 55 Mean = 50 Standard deviation = 5 A. +1 B. +5 C. +.1 D. -1

+1

Given the following values for an undesirable outcome variable such as number of incidents of verbal abuse, the effect size is: Experimental group mean = 5 Control group mean = 8 Control group standard deviation = 2 A. +3 B. -3 C. +1.5 D. -1.5

+1.5

Given the following values, the percentile is: Raw score = 30 Mean = 30 Standard deviation = 5 A. 30 B. 50 C. 0 D. 5

50

Evidence-base practice: (Ch.2-3) A. Is a list of empirically supported interventions that practitioners should employ regardless of their practice judgment. B. Is a process for making practice decisions based on integrating the best research evidence with practice expertise and knowledge of client attributes. C. Is a process for making practice decisions based solely on research evidence. D. Assures practice effectiveness.

Is a process for making practice decisions based on integrating the best research evidence with practice expertise and knowledge of client attributes.

The number appearing most frequently in a distribution is the: A. Mean B. Median C. Mode D. None of the above

Mode

Our risk of a Type II error increases the most when: A. Our sample size decreases, and we select a lower significance level (such as .01). B. Our sample size increases, and we select a higher significance level (such as .10). C. Our sample size decreases, and we select a higher significance level (such as .10). D. Our sample size increases, and we select a lower significance level (such as .01).

Our sample size decreases, and we select a lower significance level (such as .01).

Displays of the proportions or percentages of cases per category are called: A. Absolute frequency distributions B. Relative frequency distributions. C. Cumulative frequency distributions. D. Grouped frequency distributions.

Relative frequency distributions.

The probability of a particular outcome occurring is equal to: A. The number of ways that particular outcome can occur divided by the total number of all possible outcomes. B. The total number of all possible outcomes divided by the number of ways that particular outcome can occur. C. The number of ways that particular outcome can occur multiplied by the number of ways that particular outcome can occur. D. The total number of all possible outcomes minus the number of ways that particular outcome can occur.

The number of ways that particular outcome can occur divided by the total number of all possible outcomes.

As sample size increases: A. The probability of flukes in random selection or random assignment increases. B. The probability of flukes in random selection or random assignment decreases. C. Sampling error increases. D. a and c, only, above are correct

The probability of flukes in random selection or random assignment decreases.

If a normal curve has a mean of 50 and a standard deviation of 9, then the value at one standard deviation below the mean is: A. 9 B. 41 C. 47 D. 32

41

Given the following values, the range is (use Rubin's formula from the book): 2, 2, 6, 10, 10 A. 2 B. 8 C. 9 D. 10

9

Pie charts: A. Portray frequency distribution data in terms of percentages represented by slices of a pie or sections of a circle. B. Show bigger slices of pie for categories with the higher percentages of cases. C. Work best when the number of categories being portrayed is not extensive. D. All of the above

All of the above

When using an independent-samples t-Test, which of the following is considered when calculating the degrees of freedom? A. The number of values that are free to vary in each group if we know the mean and sample size of each group. B. The number of values we would need to know in each group in order to deduce the remaining values, in light of the mean and sample size of each group. C. Each group's sample size minus 1. D. When combining both groups, the overall sample size minus 2. E. All of the above

All of the above

Given the following frequency distribution, the distribution is: Value Frequency 1 10 2 15 3 20 4 15 5 10 6 15 7 20 8 15 9 10 A. Normal B. Positively skewed C. Negatively skewed D. Bimodal

Bimodal

In a study comparing 4 group means, the number of the between-groups degrees of freedom is: A. the total sample size B. 1 C. 3 D. 4

C. 3

When evaluating the effectiveness of an intervention, it would be appropriate to conduct a multiple analysis of variance (MANOVA) when: A. There is more than one dependent variable. B. We want to detect significant relationships to combined dependent variables. C. Both of the above are reasons for conducting a MANOVA. D. None of the above is correct.

C. Both of the above are reasons for conducting a MANOVA.

Given the following age distribution, the mean would be _____ the median. 4, 4, 5, 5, 5, 6, 12 A. Less than B. Greater than C. Equal to D. None of the above

Greater than

An administrator working in a child guidance center tests the hypothesis that family income will be related to number of treatment sessions attended. Her sample size is large, and her level of significance is .05. How should her critical region appear in her theoretical sampling distribution? A. It should be split between the right and left tails, with .05 appearing in each tail. B. It should be split between the right and left tails, with .025 appearing in each tail. C. It should appear in the tail signifying a positive relationship, with .05 in that tail. D. It should appear in the tail signifying a negative relationship, with .05 in that tail.

It should be split between the right and left tails, with .025 appearing in each tail.

At what level of measurement is the variable number of future incidents of child neglect?(Ch.2-3) A. Nominal. B. Ordinal. C. Ratio. D. Interventional.

Ratio

Given the following values, the variance is: 1, 1, 5, 9, 9 A. 2 B. 4 C. 16 D. 64

16

If a correlation coefficient equals .40, then: A. The relationship is weak. B. 16 percent of the dependent variable variation is explained. C. 40 percent of the dependent variable variation is explained. D. None of the above

16 percent of the dependent variable variation is explained.

In an evaluation of an intervention that seeks to increase self-esteem scores, the experimental group mean is 40, and the control group mean is 22. The standard deviation of the control group is 6. Therefore, Cohen's d equals: A. 0.60 B. 1.0 C. 3.0 D. 18

3.0

Given the following values, the standard deviation is: 2, 2, 6, 10, 10 A. 2 B. 4 C. 16 D. 64

4

To simplify a frequency distribution for a variable that contains a large number of categories, it is often helpful to create: A. An absolute frequency distribution. B. A relative frequency distribution. C. A cumulative frequency distribution. D. A grouped frequency distribution.

A grouped frequency distribution.

Two cells in a 2 by 2 table contain expected frequencies of 8. The other two cells contain expected frequencies of 12. Which of the following statements is/are true about this table? A. The Correction for Continuity should be used in testing the statistical significance of the results. B. The Fisher's Exact Test should be used in testing the statistical significance of the results. C. Pearson's chi-square statistic should be used in testing the statistical significance of the results. D. None of the above.

A. The Correction for Continuity should be used in testing the statistical significance of the results.

An analysis of covariance (ANCOVA) is conducted for a study of two groups (IV) using the pretest (Covariate) and posttest scores (DV) of two groups. The F-ratio is statistically significant. What does this mean? A. There is a statistically significant difference between the two groups on the posttest scores when the effects of the pretest scores are controlled. B. There is a statistically significant difference between the two groups on the pretest scores when the effects of the posttest scores are controlled. C. There are statistically significant differences between the two groups on both the pretest and the posttest scores. D. All of the above.

A. There is a statistically significant difference between the two groups on the posttest scores when the effects of the pretest scores are controlled.

It is appropriate to use ANOVA when: A. We want to compare the means of three or more groups. B. The dependent variable is at the nominal level of measurement. C. The dependent variable has three or more categories. D. All of the above.

A. We want to compare the means of three or more groups.

Displays of simple counts of the number of cases per category are called: A. Absolute frequency distributions. B. Relative frequency distributions. C. Cumulative frequency distributions. D. Grouped frequency distributions.

Absolute frequency distributions.

In a 95 percent confidence interval: A. The 95 percent is the confidence level. B. Shows that there is a 95 percent probability that the true population mean falls somewhere between plus and minus 1.96 standard errors of the sample mean. C. There is still a .05 probability that the true population mean falls outside the plus and minus 1.96 standard errors of the sample mean. D. All of the above

All of the above

The cutoff point that separates the critical region probability from the rest of the area of the theoretical sampling distribution can be called the: A. Level of significance. B. Rejection level. C. Alpha level. D. All of the above

All of the above

We would increase statistical power if we: A. Increase the sample size. B. Assume a larger effect size in the population. C. Increase the significance level from .05 to .10. D. All of the above

All of the above

Learning about statistics:(Ch.1) A. Will help you be more effective in marshalling data to advocate for a new policy or program. B. Will help you see through the misleading uses of statistics by your adversaries and to show others how their use of those statistics is misleading. C. Will help you evaluate the effectiveness of your own practice. D. All of the above are true.

All of the above are true.

Line graphs can be misleading by: A. Changing the spacing between categories on the vertical or horizontal axis so as to convey a more dramatic pattern or perhaps a less dramatic pattern. B. Spreading out the distance between intervals on the vertical axis, and squeezing the intervals on the horizontal axis closer together. C. Squeezing the intervals on the vertical axis closer together while spreading out the intervals on the horizontal axis. D. All of the above.

All of the above.

Two cells in a 2 by 2 table contain expected frequencies of 4. The other two cells contain expected frequencies of 6. Which of the following statements is/are true about this table? A. The Correction for Continuity should be used in testing the statistical significance of the results. B. The Fisher's Exact Test should be used in testing the statistical significance of the results. C. Pearson's chi-square statistic should be used in testing the statistical significance of the results. D. None of the above.

B. The Fisher's Exact Test should be used in testing the statistical significance of the results.

The median test should be used when: A. We have more than two variables. B. We have a nominal dichotomous independent variable and a severely skewed dependent variable that is at the ordinal, interval or ratio level of measurement. C. We have a nominal dichotomous independent variable and a normally distributed dependent variable that is at the ordinal, interval or ratio level of measurement. D. We want to compare sample proportions on a single variable to proportions known to exist in the broader population.

B. We have a nominal dichotomous independent variable and a severely skewed dependent variable that is at the ordinal, interval or ratio level of measurement.

The term frequency can refer to: A. The number of cases in a particular category of a particular variable. B. The percentage of cases in a particular category of a particular variable. C. Both a and b above are true. D. None of the above is true.

Both a and b above are true.

The goodness of fit test should be used when: A. We have more than two variables. B. We have exactly two variables. C. We want to compare sample proportions on a single variable to proportions known to exist in the broader population. D. All of the above are reasons for using the goodness of fit test

C. We want to compare sample proportions on a single variable to proportions known to exist in the broader population.

McNemar's test should be used when: A. We have more than two variables. B. We have a nominal dichotomous independent variable and a severely skewed dependent variable that is at the ordinal, interval or ratio level of measurement. C. We want to examine change from pretest to posttest within one group on a nominal variable. D. We want to compare sample proportions on a single variable to proportions known to exist in the broader population.

C. We want to examine change from pretest to posttest within one group on a nominal variable.

Descriptive statistics: (Ch.2-3) A. Tell us the probability that a given result can be attributed to chance. B. Can include frequency distributions or measures of central tendency and dispersion. C. Typically involves analysis of variance (ANOVA). D. All of the above.

Can include frequency distributions or measures of central tendency and dispersion.

The most appropriate significance level in evidence-based practice research: A. Should always be .05. B. Should always be .10. C. Is determined by mathematical theory. D. Can vary, depending upon the sample size and judgments about the relative seriousness of Type I and Type II errors.

Can vary, depending upon the sample size and judgments about the relative seriousness of Type I and Type II errors.

A finding that is statistically significant means that: A. Chance is NOT a plausible explanation for our finding. B. Our research hypothesis is true. C. Flaws in our research design become less relevant. D. All of the above.

Chance is NOT a plausible explanation for our finding.

It is appropriate to use the t-Test when: A. Comparing the means of two groups. B. Comparing the medians of two groups. C. Comparing the means of three or more groups. D. All of the above.

Comparing the means of two groups.

If normal curve A has a Kurtosis number of 50 and a Kurtosis standard deviation of 5, and normal curve B has a Kurtosis number of 50 and a standard deviation of 10, then: A. Curve A has more kurtosis than curve B. B. Curve A has less kurtosis than curve B. C. Because both curves are normal, they have the same degree of kurtosis. D. None of the above.

Curve A has more kurtosis than curve B.

It is appropriate to use parametric tests of statistical significance when: A. At least one variable in the test has an interval or ratio level of measurement. B. The tested parameters of the interval or ratio variables are distributed normally in the population. C. The groups being compared are independent of each other. D. All of the above.

D. All of the above.

The F-ratio: A. Reflects the variation among the means of several groups in relation to the variation within the groups. B. Contains a numerator that consists of the variation between the means of each group divided by the between-groups degrees of freedom. C. Contains a denominator that consists of the variation in the dependent variable among the individual cases within each group divided by the within-groups degrees of freedom. D. All of the above.

D. All of the above.

A two-factor ANOVA is conducted to evaluate the effectiveness of exposure therapy in treating civilians and combat veterans who have PTSD. Both groups of clients are randomly assigned to receive either exposure therapy or routine care. A significant interaction effect is found in the two-factor ANOVA. Which of the following interpretations is most appropriate in light of these results? A. Exposure therapy is more effective than routine care. B. Both routine care and exposure therapy are effective. C. The comparative effectiveness of the two treatment conditions varies, depending upon whether the clients are civilians or combat veterans. D. None of the above

D. None of the above

Which of the following statements is/are true about nonparametric tests of statistical significance? A. They are preferable to parametric tests. B. They require the same assumptions as parametric tests. C. They require variables at the interval or ratio level of measurement. D. None of the above.

D. None of the above.

Last year, researchers at Ohio State University (Links to an external site.) examined the link between loneliness and compulsive use of dating apps—interviewing college students who spent above-average time swiping—and found a terrible feedback loop: The lonelier you are, the more doggedly you will seek out a partner, and the more negative outcomes you're likely to be faced with, and the more alienated from other people you will feel. This happens to men and women in the same way. "We found no statistically significant differences for gender at all," the lead author, Katy Coduto, said in an email. "Like, not even marginally significant." https://www.theatlantic.com/family/archive/2020/02/modern-dating-odds-economy-apps-tinder-math/606982/ (Links to an external site.) Let's assume the researchers developed multiple metric level DVs representing: alienation, loneliness, and negative outcomes. Which statistical test would they have used to establish there was "no statistically significant differences for gender at all"? A. The one way ANOVA test B. The ANCOVA test C. The Super NOVA test D. The MANOVA test

D. The MANOVA test

The t-Test formula involves calculating a t-score by: A. Dividing the difference between two means by the standard deviation of the experimental group. B. Dividing the difference between two means by the standard error of the difference between means. C. Dividing the difference between two means by the standard deviation of the control group. D. Dividing the difference between two standard deviations by the difference between two means.

Dividing the difference between two means by the standard error of the difference between means.

A post hoc test is conducted to make multiple comparisons between the mean scores of three groups of clients in a child guidance center. Group A receives play therapy, only. Group B receives family therapy, only. Group C receives both play and family therapy. The significance level is .05. The p value for the difference between Groups A and B is .66. The p value for the difference between Groups A and C is .01. The p value for the difference between Groups B and C is .01. Which of the following interpretations is most appropriate in light of these results? A. Play therapy and family therapy appear to be equally effective. B. Play therapy appears to be effective. C. Family therapy appears to be effective. D. All of the above. E. The combination of play and family therapy is statistically significant and appears to be more effective than either play therapy alone or family therapy alone.

E. The combination of play and family therapy is statistically significant and appears to be more effective than either play therapy alone or family therapy alone.

All cells in a 2 by 2 table contains 20 cases. Which of the following statements is/are true about these results? A. The results are statistically significant. B. The results are NOT statistically significant. C. The chi-square statistic equals zero. D. The Fisher's Exact Test should be used. E. b and c, only, are true.

E. b and c, only, are true.

The standard error in estimating parameters: A. Equals the standard deviation of the sample divided by the square root of the sample size. B. Equals the standard deviation of the population divided by the standard deviation of the sample. C. Equals the standard deviation of the sample multiplied by the square root of the sample size. D. Equals the standard deviation of the sample divided by the sample size.

Equals the standard deviation of the sample divided by the square root of the sample size.

We commit a Type II error when we: A. Reject a true null hypothesis. B. Fail to reject a false null hypothesis. C. Fail to reject a false research hypothesis. D. None of the above.

Fail to reject a false null hypothesis.

Learning about statistics pertains primarily to levels of practice dealing with policy analysis, and is of much less relevance to clinical practice. (Ch.1) True False

False: Has equal relevance to clinical practice

The safest/most reliable way to obtain a representative sample is by using non-probability sampling procedures. (Ch.2-3) True False

False: Probability sampling is the safest/most reliable way to obtain a representative sample

Because anyone can manipulate and distort statistics to support whatever point they are trying to make, it is best to ignore statistics rather than understand them. (Ch.1) True False

False: Should always seek to understand statistics

Statistics can only be used to describe data. (Ch.1) True False

False: Statistics can also be used to predict data (Inferential)

Which of the following variables could NOT be collapsed to a lower level of measurement?(Ch.2-3) A. Number of child neglect incidents. B. Level of satisfaction with agency services. C. Gender. D. Severity of trauma symptoms.

Gender

Measures of dispersion show: A. How spread out data are. B. Where most data are located in a distribution C. What values in a distribution are most important D. All of the above

How spread out data are.

The term parameter: A. Applies only to sample statistics. B. Is synonymous with the term perimeter. C. Is used instead of the term statistic when referring to a summary statistic for an entire population. D. Can be used interchangeably with the term statistic regardless of whether we are referring to a sample or a population.

Is used instead of the term statistic when referring to a summary statistic for an entire population.

An experiment with a small sample is conducted to test the effectiveness of a promising new intervention for treating substance abuse. The experimental group's outcome is better than the control group's outcome, but the results are not statistically significant. The implication of this finding for evidence-based practice is: A. The new intervention was ineffective. B. The new intervention was effective, but not as effective as predicted. C. It is conceivable that the new intervention is effective, although we cannot rule out sampling error as the explanation for the research finding. Additional testing of this intervention with a larger sample size would be in order. D. None of the above.

It is conceivable that the new intervention is effective, although we cannot rule out sampling error as the explanation for the research finding. Additional testing of this intervention with a larger sample size would be in order.

Which of the following statements is true about the interquartile range? A. It shows the middle quarter of values in a rank ordered distribution. B. It shows the range of values falling between the 50th and 75th percentiles. C. It has virtually no relevance to practitioners. D. It shows the range of values falling between the 25th and 75th percentiles.

It shows the range of values falling between the 25th and 75th percentiles.

Learning about statistics: (Ch.1) A. Is risky. B. It will help one avoid being misled by those who misuse statistics as a way to propagandize their political agenda. C. Is important despite its lack of relevance to practice. D. Can interfere with one's capacity to be a warm, compassionate practitioner.

It will help one avoid being misled by those who misuse statistics as a way to propagandize their political agenda.

Histograms: A. Work best with nominal level variables. B. Look like bar graphs with bars that touch each other. C. Never can be used with values that are collapsed into grouped categories. D. Always have bars of equal width.

Look like bar graphs with bars that touch each other.

Given the following age distribution, 7 is the: 4, 5, 6, 7, 8, 12 A. Mean B. Median C. Mode D. All of the above

Mean

The number in a distribution that is vulnerable to the influence of extreme values is the: A. Mean B. Median C. Mode D. None of the above

Mean

Given the following age distribution, 24 is the: 20, 22, 23, 25, 30, 36 A. Mean B. Median C. Mode D. None of the above

Median

The vertical line on a graph: A. Is called the x-axis. B. Never displays the number or percentages of cases for each value of a variable. C. Might display different levels of a second variable (or frequency of X), thus showing whether changing levels of categories on the variable on the horizontal axis move in a consistent fashion with changing levels of the second variable. D. Is always a variable.

Might display different levels of a second variable (or frequency of X), thus showing whether changing levels of categories on the variable on the horizontal axis move in a consistent fashion with changing levels of the second variable.

Given the following frequency distribution, the distribution is: Value Frequency 1 1 2 2 3 3 15 10 16 15 17 20 18 40 19 20 20 10 A. Normal B. Positively skewed C. Negatively skewed D. Bimodal

Negatively skewed

At what level of measurement is the variable ethnicity?(Ch.2-3) A. Nominal. B. Ordinal. C. Ratio. D. Interval.

Nominal.

Randy wants to see whether Intervention A is more effective than Intervention B in improving self-esteem scores. Randy conducts an experiment to see if recipients of Intervention A improve more in self-esteem from pretest to posttest than recipients of Intervention B, using the .05 level of significance. Randy conducts two paired-sample t-Tests and finds a p value of .04 for Intervention A's improvement and a p value of .06 for Intervention B's improvement. Randy then conducts an independent-samples t-Test of the posttest scores and finds a p value of .55. Randy should conclude: A. Intervention A is more effective than Intervention B in improving self-esteem scores. B. Both interventions are effective in improving self-esteem scores. C. Both a and b, above, are correct. D. None of the above

None of the above

Suppose a newspaper reports that the average number of times students in your college or university engage in binge drinking during the academic year is twice. What is appropriate to conclude? (Ch.1) A. The typical student binge drinks approximately twice per year B. Most students binge drink approximately twice per year. C. Both of the above are appropriate conclusions. D. None of the above is an appropriate conclusion.

None of the above is an appropriate conclusion.

Given the following frequency distribution, the distribution is: Value Frequency 1 30 2 40 3 50 4 40 5 20 6 10 10 4 15 2 20 1 A. Normal B. Positively skewed C. Negatively skewed D. Bimodal

Positively skewed

The best way to facilitate and simplify the interpretation of data collected in a large survey is to: A. Display the spreadsheet of raw data. B. Write a narrative detailing the number of cases for each attribute of each variable. C. Present a frequency distribution. D. All of the above.

Present a frequency distribution.

The term chance: A. Refers to sampling errors that result from biased sampling procedures. B. Refers to sampling errors that inevitably occur in random sampling. C. Refers to errors that are avoided when random sampling is used. D. a and c above, only, are true.

Refers to sampling errors that inevitably occur in random sampling.

We commit a Type I error when we: A. Reject a true null hypothesis. B. Fail to reject a false null hypothesis. C. Reject a true research hypothesis. D. Fail to reject a false research hypothesis.

Reject a true null hypothesis.

Cross-tabulation tables: A. Show the relationship between two or more variables. B. Always have only two rows and two columns. C. Always have more than two rows and two columns. D. Always display frequencies, only, and NOT percentages.

Show the relationship between two or more variables.

Which of the following statements best depicts research findings on the effectiveness of interventions that have been popular among helping professionals and that have seemed theoretically sound? (Ch.1) A. Some were found to be ineffective B. None were found to be harmful C. Earning a professional degree assures that your efforts to help people will be effective D. All of the above are true

Some were found to be ineffective

If Study A reports a Cohen's d of .60, and Study B reports a correlation coefficient of .60, then: A. Both studies have reported equal effect sizes. B. Study A's effect size is stronger than Study B's effect size. C. Study B's effect size is stronger than Study A's effect size. D. None of the above.

Study B's effect size is stronger than Study A's effect size.

Inferential statistics: (Ch.2-3) A. Are limited to describing a population. B. Always require the use of parametric tests. C. Always require the use of nonparametric tests. D. Tell us the probability that a given result can be attributed to chance.

Tell us the probability that a given result can be attributed to chance.

Last year, researchers at Ohio State University (Links to an external site.) examined the link between loneliness and compulsive use of dating apps—interviewing college students who spent above-average time swiping—and found a terrible feedback loop: The lonelier you are, the more doggedly you will seek out a partner, and the more negative outcomes you're likely to be faced with, and the more alienated from other people you will feel. This happens to men and women in the same way. "We found no statistically significant differences for gender at all," the lead author, Katy Coduto, said in an email. "Like, not even marginally significant." https://www.theatlantic.com/family/archive/2020/02/modern-dating-odds-economy-apps-tinder-math/606982/ (Links to an external site.) Assuming that the researchers developed a single metric level DV that represented the "feedback loop" discussed above, which t-Test would they have used to establish there was "no statistically significant differences for gender at all"? A. The Independent-samples t-Test B. The Paired-samples t-Test C. The One-sample t-Test D. The Big-sample t-Test

The Independent-samples t-Test

It is appropriate to use the t-Test when: A. The independent and dependent variables are both at the nominal level of measurement. B. The independent and dependent variables are both at the ordinal level of measurement. C. The independent and dependent variables are both at the ratio level of measurement. D. The independent variable is nominal and dichotomous and the dependent variable is at the interval or ratio level of measurement.

The independent variable is nominal and dichotomous and the dependent variable is at the interval or ratio level of measurement.

Chris wants to test the significance of the difference in the number of treatment sessions attended by clients who have no connection to one another and who have been randomly assigned to either Group A and Group B. Chris should use: A. The one-sample t-Test. B. The paired-samples t-Test. C. The independent-samples t-Test. D. An independent-samples t-Test with change scores.

The independent-samples t-Test.

In a pilot study, Dana wants to test the significance of the improvement in mean scores from pretest to posttest. If Dana does not compute a change score variable what t-test should she use: A. The one-sample t-Test. B. The paired-samples t-Test. C. The independent-samples t-Test. D. An independent-samples t-Test with change scores.

The paired-samples t-Test.

z scores enable us to compare outcomes of evaluations that use very different outcome measures of the same concept (e.g. PTSD) A. True B. False

True

A two-factor ANOVA identifies the main effect of each independent variable on the dependent variable as well as any interaction effect between the two of them on the dependent variable. True False

True: A two-factor ANOVA identifies the main effect of each independent variable on the dependent variable as well as any interaction effect between the two of them on the dependent variable.

ANOVA can be used only when comparing two means. True False

True: ANOVA can be used only when comparing two means.

ANOVA with a statistically significance result without post hoc tests tell us only that there is a statistically significant difference somewhere among the multiple groups being compared -- not which particular comparisons of group means are statistically significant. True False

True: ANOVA with a statistically significance result without post hoc tests tell us only that there is a statistically significant difference somewhere among the multiple groups being compared -- not which particular comparisons of group means are statistically significant.

If a father who is abusive consistently denies being abusive, his self-report is reliable but not valid.(Ch.2-3) True False

True: If a father who is abusive consistently denies being abusive, his self-report is reliable but not valid.

Keeping current with and critically appraising practice-related studies and basing one's practice on evidence-based knowledge makes one a more ethical practitioner. (Ch.1) True False

True: Keeping current with and critically appraising practice-related studies and basing one's practice on evidence-based knowledge makes one a more ethical practitioner.

Meta-analyses systematically review existing studies and aggregate their statistical results. (Ch.2-3) True False

True: Meta-analyses systematically review existing studies and aggregate their statistical results.

Understanding statistics makes one a more compassionate practitioner. (Ch.1) True False

True: Understanding statistics makes one a more compassionate practitioner.

The most important reason why practitioners should learn about statistics is that they want to help people. (Ch.1) True False

True: the most important reason why practitioners should learn about statistics is that they want to help people.

A study is conducted to test the hypothesis that cognitive behavioral therapy is more effective than eclectic therapy in alleviating the severity trauma symptoms among female victims of rape. Which of the following is the independent variable in this study? (Ch.2-3) A. Cognitive behavioral therapy B. Severity of trauma symptoms C. Gender D. Type of therapy

Type of therapy

It is appropriate to use the one-sample t-Test when: A. We want to compare the means of pairs of individuals who have been matched because they are similar to each other. B. We want to compare the means of two independent groups. C. We want to compare a sample statistic to a population parameter. D. All of the above.

We want to compare a sample statistic to a population parameter.

It is appropriate to use the paired-samples t-Test when: A. We want to compare the means of pairs of individuals who have been matched because they are similar to each other. B. We want to compare the means of two independent groups. C. We want to compare a sample statistic to a population statistic. D. All of the above.

We want to compare the means of pairs of individuals who have been matched because they are similar to each other.

It is appropriate to use the independent-samples t-Test when: A. We want to compare the means of pairs of individuals who have been matched because they are similar to each other. B. We want to compare the means of two independent groups. C. We want to compare a sample statistic to a population statistic. D. All of the above.

We want to compare the means of two independent groups.

A statistically significant finding: A. Is substantively significant. B. Would certainly be substantively significant if the effect size is strong. C. Would not be substantively significant if the effect size is weak. D. None of the above

Would not be substantively significant if the effect size is weak.

If the null hypothesis is true: A. The hypothesized relationship really exists. B. There is no relationship between the hypothesized variables. C. The relationship found in our study data between the hypothesized variables can be attributed to sampling error. D. b and c above, only, are true.

b and c above, only, are true.