Deck 9: More About Using Statistics

Question 1

If a study involves an examination of the relationship between two variables measured on an interval or ratio scale, the appropriate statistical test is ______.

A) a Pearson r test
B) an independent samples t test
C) a paired/related samples t test
D) an ANOVA

Answer 1

a Pearson r test

Question 2

If a study involves comparing two means from a between-subjects design, the appropriate statistical test is ______.

A) a one-sample t test
B) an independent samples t test
C) a paired/related samples t test
D) an ANOVA

Answer 2

an independent samples t test

Question 3

The hypothesis that an effect or relationship exists (or exists in a specific direction) in the population is the ______.

A) alternative hypothesis
B) statistical hypothesis
C) null hypothesis
D) critical region

Answer 3

alternative hypothesis

Question 4

Variability of the sample indicates the amount of ______ presents because samples with high variability are less likely to be good representations of the population.

A) effect
B) power
C) sampling error
D) accuracy

Question 5

A quasi-experiment was conducted to compare men's and women's attitudes about extramarital affairs. Men and women who are married were recruited to complete a survey about their attitudes. The researchers then compared scores on the survey for men and women. The appropriate statistical test to analyze the data in this study is ______.

A) a one-sample t test
B) an independent samples t test
C) a paired/related samples t test
D) an ANOVA

Question 6

Sample mean differences can be caused by ______.

A) the effect
B) sampling error
C) the effect and sampling error
D) neither effect nor sampling errors

Question 7

When entering data into SPSS for a within-subjects study, one should always enter ______.

A) data for each condition in a different column
B) all data in one column
C) half the data in one column and the other half in a second column
D) one-third of the data in one column and two-thirds in a second column

Question 8

If a study involves comparing two means from a within-subjects design, the appropriate statistical test is ______.

A) a one-sample t test
B) an independent samples t test
C) a paired/related samples t test
D) an ANOVA

Question 9

If a study involves comparing means from a factorial design, the appropriate statistical test is ______.

A) a one-sample t test
B) an independent samples t test
C) a paired/related samples t test
D) an ANOVA

Question 10

The ability of a significance test to detect an effect or relationship when one exists is referred to as ______.

A) the effect
B) power
C) sampling error
D) inaccuracy

Question 11

A significant difference between groups or conditions allows researchers to conclude that an effect exists in the population because they are able to reject the ______ in a significant test.

A) alternative hypothesis
B) statistical hypothesis
C) null hypothesis
D) critical region

Question 12

The most extreme portion of a distribution of statistical values for the null hypothesis determined by the alpha level is called ______.

A) the outlier
B) the extremes
C) the statistical cutoff
D) the critical region

Question 13

A researcher was interested in the effect of anxiety on intelligence measurement. A group of 100 individuals were placed in an anxiety-provoking situation before being given an IQ test. The scores for this group were then compared to the IQ population mean of 100. The appropriate statistical test to analyze the data in this study is ______.

A) a one-sample t test
B) an independent samples t test
C) a paired/related samples t test
D) an ANOVA

Question 14

A researcher who wants to test the relationship between nominal or ordinal variables should use a(n) ______.

A) Pearson r test
B) independent samples t test
C) paired/related samples t test
D) chi-square test

Question 15

A developmental psychologist conducted an experiment to examine the effect of type of text used on math performance across age groups. Fifth grade and college students studied age-appropriate math concepts using either a traditional hard copy book text or an e-text available on the web. Performance on a math test of the concepts studied was then measured for all students. The appropriate statistical test to analyze the data in this study is ______.

A) a one-sample t test
B) an independent samples t test
C) a paired/related samples t test
D) an ANOVA

Question 16

If a researcher wishes to predict the score on one measured variable from the score on another measured variable, the appropriate statistical test is ______.

A) a Pearson r test
B) an independent samples t test
C) a paired/related samples t test
D) a linear regression

Question 17

A researcher conducted a correlational study to examine the relationship between high school GPA and extroversion. A group of high school students completed a measure of extroversion. The GPAs for these students were then obtained from their records. The appropriate statistical test to analyze the data in this study is ______.

A) a Pearson r test
B) an independent samples t test
C) a paired/related samples t test
D) an ANOVA

Question 18

The hypothesis that an effect or relationship does not exist (or exists in the opposite direction of the alternative hypothesis) in the population is the ______.

A) alternative hypothesis
B) statistical hypothesis
C) null hypothesis
D) critical region

Question 19

An experiment was conducted to compare participant responses to two different social situations. All participants viewed a scene with two children playing cooperatively and a scene with two children arguing while playing. Participants responded to a questionnaire measuring anxiety after viewing each scene to determine if the type of scene viewed had an effect on anxiety scores. The appropriate statistical test to analyze the data in this study is ______.

A) a one-sample t test
B) an independent samples t test
C) a paired samples t test
D) an ANOVA

Question 20

Samples with high variability will typically have a ______ margin of error in the population mean estimate.

A) larger
B) minute
C) smaller
D) none of these

Question 21

The number of scores that can vary in the calculation of a statistic is called ______.

A) the degrees of freedom
B) homogeneity of variance
C) multivalent variable
D) the null hypothesis

Question 22

The ______ is the assumption of between-subjects t tests and ANOVAs that the variance in the scores in the population is equal across groups.

A) degrees of freedom
B) power
C) alpha level
D) homogeneity of variances

Question 23

"One-way ANOVA" test analyzes ______ subject variable(s).

A) no
B) two
C) one
D) four

Question 24

The independent samples t test is used when ______ samples of different individuals are compared.

A) two
B) three
C) four
D) five

Question 25

There are ______ types of t tests used to compare means.

A) two
B) three
C) four
D) five

Question 26

The first question to address about the study design in identifying the correct statistical test is to ______.

A) determine if comparing means or testing relationships
B) determine the response rate
C) determine the sample size
D) ask the study principal investigator

Question 27

If the p value for the statistic is less than or equal to the alpha level, the null hypothesis is ______.

A) accepted
B) rejected
C) flawed
D) small

Question 28

Analysis of variance (ANOVA) is used to test an effect when more than ______ groups or conditions are being considered.

A) two
B) one
C) four
D) five

Question 29

A Bonferroni and Tukey tests are SPSS options for ______ test of mean differences.

A) main effects
B) interaction effects
C) post hoc
D) paired-samples

Question 30

A variable that includes three or more levels is called ______.

A) the degrees of freedom
B) post hoc test
C) the alpha level
D) multivalent variable

Question 31

Violations of the sphericity assumption can decrease the chance of a Type I error.

Question 32

When each participant experiences all levels of the independent variable, this is called ______ variable.

A) between-subjects
B) independent subjects
C) within-subjects
D) dependent

Question 33

Counterbalancing is used to control ______.

A) bias
B) sample size
C) assignment
D) levels of a condition

Question 34

Additional significance tests conducted to determine which means are significantly different for a main effect are called ______.

A) the degrees of freedom
B) post hoc tests
C) the alpha level
D) multivalent variable

Question 35

The ______ effect tests the effect of one independent variable at each level of another independent variable in an ANOVA.

A) main
B) primary
C) interaction
D) independent

Question 36

The critical region is the most extreme portion of a distribution of statistical values for the null hypothesis, determined by the alpha level, typically of ______.

A) 5%
B) 10%
C) 15%
D) 20%

Question 37

The ______ value is less than or equal to alpha in an inferential test, and the null hypothesis can be rejected.

A) j
B) p
C) d
D) f

Question 38

If the p value is greater than the alpha level, the researcher cannot ______ the null hypothesis.

A) accept
B) reject
C) understand
D) include

Question 39

When each participant experiences only one level of the independent variable, this is ______.

A) between subjects
B) independent subjects
C) within subjects
D) dependent

Question 40

The probability level used by researchers to indicate the cutoff probability level (highest value) that will allow them to reject the null hypothesis is called ______.

A) the degrees of freedom
B) power
C) the alpha level
D) the null hypothesis

Question 41

If the output for a statistical test contains a p value that is less than or equal to alpha, the test is significant and the null hypothesis can be rejected.

Question 42

Samples with low variability often contain extreme scores that could affect the sample mean, giving a sample mean that is not very similar to the population mean.

Question 43

If the p value is greater than the alpha level, the researcher cannot reject the null hypothesis and must conclude that there is no evidence of an effect.

Question 44

SPSS will calculate inferential statistics, making it unnecessary that a researcher understands how the statistical tests work.

Question 45

What is a Type I error? Please provide an example.

Question 46

A Type I error is made in a significance test when the researcher rejects the null hypothesis when it is actually true.

Question 47

For related samples tests, scores for different conditions go in separate columns; no group codes are needed.

Question 48

Discuss the sphericity test. What needs to be done if the sphericity test is significant?

Question 49

If the p value for the statistic is less than or equal to the alpha level, the null hypothesis is accepted, and the researcher concludes that there is an effect.

Question 50

Discuss the difference between levels and conditions for a factorial design.

Question 51

Briefly describe how to choose an appropriate statistical test?

Question 52

Mauchly's test is an assumption that pairs of scores in the population have similar variability.

Question 53

Discuss analysis of variance including main effects, interaction effects, and post hoc tests.

Question 54

In experiments and quasi-experiments, hypotheses about effects are often tested by comparing groups (e.g., men and women) or conditions.

Question 55

Explain what it means for a statistical test to be significant.

Question 56

Statistical tests for effects are based on a ratio of the size of the difference in the sample means and sampling error to allow us to determine what part of the mean difference is due to the effect and which part is due to sampling error.

Question 57

Discuss the Pearson r statistic. What type of relationships does it measure?

Question 58

If the sphericity test is significant in the SPSS repeated measures output, the F statistic needs to be adjusted in order to retain accuracy of the test.

Question 59

Samples with high variability contain scores that are similar to one another and are more likely to represent the population mean.

Question 60

Sample mean differences can be caused by the effect, by sampling error, or both.