Business Research Ch 17
A two-way ANOVA differs from a one-way ANOVA in that _____. A. Post hoc comparisons are completed as a part of the initial test B. It requires an assumption of normality C. It examines possible interaction effects among two independent factors D. It examines possible interaction effects among two or more dependent variables E. It allows an examination of ordinal data
C. It examines possible interaction effects among two independent factors
What type of hypothesis states that a sample statistic is either greater than or less than the population parameter? A. Null B. One-tailed C. Two-tailed D. Three-tailed E. None of the above
C. Two-tailed
Statisticians recommend that the power of a test equal _____, that is, the probability that one will correctly reject a false null hypothesis. A. 5% B. 10% C. 50% D. 80% E. 95%
D. 80%
Which of the following outcomes is roughly the equivalent of committing a type I error? A. Finding a guilty person guilty B. Finding a guilty person not guilty C. Finding an innocent person not guilty D. Finding an innocent person guilty E. None of the above
D. Finding an innocent person guilty
The _____ is the probability of rejecting the null hypothesis when it is in fact false, and should be rejected. A. type I error B. level of significance C. type II error D. power of a test E. Z score
D. power of a test
What are the assumptions for using parametric tests for hypothesis testing?
Parametric tests are significance tests for data that is interval or ratio-scaled. The assumptions that should be met for using parametric tests include that the observations should be independent, and drawn from normally distributed populations. The populations should have equal variances.
Which of the following tests is most appropriate for examining differences in the average number of hours spent viewing television among four different age groups? A. Z test B. t-test C. ANOVA D. X2 E. McNemar test
C. ANOVA
Which of the following illustrates the correct expression of the null hypothesis for the alternate hypothesis that more than 40% of Internet users shop online? A. H0: π ≤ .40 B. HA: π > .40 C. H0: π = .40 D. HA: π ≠ .40 E. H0: µ = .40
A. H0: π ≤ .40
What type of hypothesis states that the sample statistic is not the same as the population statistic but is either greater than or less than, but not both? A. Null B. One-tailed C. Two-tailed D. Three-tailed E. None of the above
B. One-tailed
How can a researcher determine whether data meet the assumption of normality necessary for using parametric tests? A. Assess the level of significance B. Determine the probability of making a type II error C. Determine the probability of making a type I error D. Examine a normal probability plot E. Examine whether the distribution is bimodal or multimodal
D. Examine a normal probability plot
The _____ is a parametric test to determine the statistical significance between the sample distribution mean and a population parameter. A. F statistic B. t-test C. Z distribution D. Z test E. t distribution
D. Z test
Which of the following hypotheses is a two-tailed test? A. Hamburger consumption differs among men and women B. Men consume more hamburgers than women C. Women are more concerned with the health consequences associated with eating hamburgers than are men D. There is no difference in hamburger consumption among men and women E. All of the above are two-tailed tests
A. Hamburger consumption differs among men and women
Which of the following hypotheses is a one-tailed test? A. Hybrid cars get better gas mileage than traditional cars B. There is a difference in the gas mileage of cars and trucks C. There is no difference in gas mileage among two-door and four-door vehicles D. There is a relationship between the number of miles to one's job and the gas mileage associated with his or her chosen car E. All of the above are one-tailed tests
A. Hybrid cars get better gas mileage than traditional cars
Consider the following hypothesis: "There is no relationship between income and amount of money spent on food." 26. If the hypothesis presented is tested with a .05 level of significance and the resulting p value is .01, which of the following is the correct decision regarding the null hypothesis? A. Reject the null B. Cannot reject the null C. The decision cannot be determined with the information provided D. Reject the alternate E. None of the above
A. Reject the null
Which of the following best explains how the F ratio examines differences among groups? A. The variability attributable to a treatment is compared to the variability arising from random error B. The probability of making a type I error is compared to the probability of making a type II error C. The critical F is compared to the critical t D. The standard deviation for each group is subtracted from the mean of all groups E. None of the above
A. The variability attributable to a treatment is compared to the variability arising from random error
_____ tests are hypothesis testing procedures that assume that the variables of interest are measured on at least an interval scale. A. Parameter B. Parametric C. Nonparametric D. Significance E. Metric
B. Parametric
Which of the following involves a test of two-independent samples? A. Test of differences in the percent of men and women who are or are not members of Greek organizations on campus B. Test of the average incomes of magazine subscribers of Southern Living verses Better Homes and Gardens C. Test of whether the mean salary of professors at Metro University is higher than the national average for university professors D. Test of whether a change occurred in the likelihood of heart disease among people who switched to a diet high in fish E. Test of differences in ad recall among three experimental groups (each of which saw a different advertisement) and a control group
B. Test of the average incomes of magazine subscribers of Southern Living verses Better Homes and Gardens
If the hypothesis presented is tested using a .05 alpha level and the resulting p value is .01, which of the following interpretations of the results is most appropriate? A. There is no relationship between income and food expenditures B. There is a relationship between income and food expenditures C. As income increases, food expenditures increase D. As income decreases, the percentage of income spent on food increases E. None of the above
B. There is a relationship between income and food expenditures
When conducting an ANOVA, if the F ratio is close to 1, which of the following interpretations is true? A. The null hypothesis is rejected B. There is no difference between the means of the groups examined C. The population means are unequal D. The between-groups variance is twice the within-groups variance E. All of the above are true
B. There is no difference between the means of the groups examined
As one increases the significance level accepted for hypothesis testing, the probability of committing a type II error _____. A. increases B. decreases C. stays the same D. is rejected E. is accepted
B. decreases
If a data difference is NOT caused only by random sampling fluctuations, it is said to have _____. A. resistance B. statistical significance C. substantive significance D. reasonable doubt E. practical significance
B. statistical significance
The region of acceptance and the region of rejection are determined by the _____. A. resistance level of the statistic B. statistical significance level C. substantive significance level D. reasonable doubt E. practical significance level
B. statistical significance level
The null hypothesis is typically rejected when _____. A. the calculated value is smaller than the critical value B. the critical value is smaller than the calculated value C. the level of significance chosen is .05 D. a chi-square statistic is computed E. the Z score approaches 1
B. the critical value is smaller than the calculated value
In an examination of differences among the mean hamburger consumption of people in the United Kingdom, United States, France, and Korea, how would the null hypothesis be stated? A. H0: πUK > πUS > πFR > πKR B. HA: πUK + πUS > πFR + πKR C. H0: μUK = μUS = μFR = μKR D. HA: π ≠ 0 E. H0: μ = 0
C. H0: μUK = μUS = μFR = μKR
Which of the following hypotheses is an alternative hypothesis? A. There is no relationship between grade point average and drinking behavior among college students B. Seniors are no more likely than freshmen to binge drink C. Men are more likely to binge drink than women D. Athletes and non-athletes are equally likely to binge drink E. There is no difference in alcohol consumption among beer drinkers and wine drinkers
C. Men are more likely to binge drink than women
_____ tests are hypothesis testing procedures that assume that the variables are measured on a nominal or ordinal scale. A. Parameter B. Parametric C. Nonparametric D. Resistant E. Type I
C. Nonparametric
Which statement is NOT true concerning the t distribution? A. Compared to the normal distribution, the t distribution has more area in the tails and less in the center. B. As the number of degrees of freedom increases, the t distribution approaches the normal distribution. C. The t distributions are skewed to the left. D. The population variance is unknown and is estimated by the sample variance s2. E. As the sample size increases beyond 120, the t and Z distributions are indistinguishable.
C. The t distributions are skewed to the left.
A researcher should consider answers to all of the following questions except _____ when selecting a particular test of significance. A. how many samples are involved in the test? B. are the samples related? C. what type of data is involved? D. what is the level of significance? E. all of the above should be addressed
D. what is the level of significance?
Which of the following illustrates the correct expression of the alternate hypothesis that customers of McDonald's consume more than the national average of 36 hamburgers each year? A. H0: π ≤ 36 B. HA: π > 36 C. H0: µ = 36 D. HA: µ ≠ 36 E. HA: µ > 36
E. HA: µ > 36
Hypothesis testing of the effectiveness of two experimental manipulations against a control group finds that there is a significant difference in the mean score by group and the null hypothesis is rejected. Which test below can be used to determine where a difference exists? A. ANOVA B. X2 C. F ratio D. Z test E. Scheffe's S
E. Scheffe's S
List the six-stage sequence for testing statistical significance.
The six stages in hypothesis testing are 1) state the null hypothesis, 2) choose the statistical test, 3) select the desired level of significance, 4) compute the calculated difference value, 5) obtain the critical value, and 6) interpret the test.
What is the difference between a Type I error and a Type II error? How are the two errors related?
A Type I error occurs when the sample results lead to the rejection of the null hypothesis when it is in fact true. The probability of Type I error is denoted as α. Type II error occurs when, based on the sample results, the null hypothesis is not rejected when it is in fact false. The probability of Type II error is denoted by β. Unlike α, which is specified by the researcher, the magnitude of β depends on the actual value of the population parameter (proportion). The complement (1 - β) of the probability of a Type II error is called the power of a statistical test. The power of a testis the probability of rejecting the null hypothesis when it is false and should be rejected. Although β is unknown, it is related to α. An extremely low value of α (e.g., = 0.001) will result in intolerably high β errors. So it is necessary to balance the two types of errors. As a compromise, α is often set at 0.05; sometimes it is 0.01; other values of α are rare. The level of α, along with the sample size, will determine the level of β for a particular research design. The risk of both α and β can be controlled by increasing the sample size.
Define the null and alternative hypotheses. Discuss the relationship between the two hypotheses.
A null hypothesis is a statement of the status quo, one of no difference or no effect. If the null hypothesis is not rejected, no changes will be made. An alternative hypothesis is one in which some difference or effect is expected. Accepting the alternative hypothesis will lead to changes in the actions of the business decision maker. The alternative hypothesis is the opposite of the null hypothesis. The null hypothesis is always the hypothesis that is tested. The alternative hypothesis represents the conclusion for which evidence is sought.
The most common level of significance used in hypothesis testing is _____. A. .05 B. .10 C. .25 D. .90 E. .95
A. .05
When sample sizes exceed _____, the t and Z distributions are virtually identical. A. 120 B. 300 C. 500 D. 1000 E. the t and Z distributions will never be identical
A. 120
Which test is an extension of the McNemar test useful for tests involving more than two samples? A. Cochran Q B. ANOVA C. n-way ANOVA D. Kruskal-Wallis E. Mann-Whitney U
A. Cochran Q
Which of the following hypotheses is a null hypothesis? A. There is no difference in the monthly grocery bills of families with one child and families with two children B. Grocery bills vary according to the number of meals eaten outside the home C. Families with two children have significantly higher grocery bills than families with just one child D. There is a relationship between grocery bills and the number of people in a household E. The mean age in a household is predictive of the amount of money sent on food each month
A. There is no difference in the monthly grocery bills of families with one child and families with two children
Which type of error is also known as alpha? A. Type I error B. Type II error C. Beta error D. Standard error E. Demand error
A. Type I error
_____ occurs when the sample results lead to the rejection of a null hypothesis that is in fact true. A. Type I error B. Two-tailed error C. Type II error D. One-tailed error E. Parametric significance
A. Type I error
The hypothesis that men and women use the Internet approximately the same number of hours per week is a _____ hypothesis. A. null B. one-tailed test C. two-tailed test D. test of proportions E. test of means
A. null
Under which of the following conditions must the null hypothesis be rejected? A. p value < α B. p value > α C. p value = α D. p value cannot be determined E. p value is unrelated to hypothesis testing
A. p value < α
_____ statistics considers subjective probability estimates while _____ statistics considers only objective estimates. A. Classical; Bayesian B. Inductive; deductive C. Bayesian; classical D. Descriptive; exploratory E. Exploratory; descriptive
C. Bayesian; classical
Repeated measures taken from the same participant are called _____. A. examinations B. related samples C. time series data D. trials E. n-way tests
D. trials
Which of the following is true of a one-sample chi-square test? A. The null hypothesis is that the actual frequencies in each category is different than those hypothesized B. The greater the difference between the actual and hypothesized frequencies in a category, the more likely the difference can be attributed to chance C. The value of the X2 statistic expresses the extent of the difference between the actual and hypothesized frequencies D. The larger the divergence, the smaller the X2 value E. A X2 statistic is significant if it is less than .05
C. The value of the X2 statistic expresses the extent of the difference between the actual and hypothesized frequencies
Jeremy is using an ANOVA to examine the alternative hypothesis that brand loyalty is higher among frequent fliers of Jet Blue than the reported brand loyalty of frequent fliers on United, US Airways, and Delta. If the p value is less than .05 and the F ratio is greater than 1, which of the following interpretations is correct? A. Jet Blue has higher brand loyalty among its frequent fliers than do the other three airlines examined B. There is no difference in brand loyalty among customers of the four airlines C. There is a difference in brand loyalty among customers of the four airlines D. Jet Blue has lower brand loyalty among its frequent fliers than do the other three airlines E. No interpretation can be made with the information available
C. There is a difference in brand loyalty among customers of the four airlines
In which of the following situations should an a priori contrast be used? A. A t-test is used to conclude that men consume more hamburgers than women B. A chi-square test is used to conclude that there is a difference in type of living quarters by class status C. Using a one-way ANOVA, significant differences in ad recall are found between three experimental groups and one control group D. A Z test indicates that the national average of the number of soft drinks consumed in the US exceeds that of France E. All of the above should use an a priori contrast
C. Using a one-way ANOVA, significant differences in ad recall are found between three experimental groups and one control group
The level of significance chosen for hypothesis testing is based on _____. A. the desired level of confidence one wishes to have in the results B. the desired degree of precision C. how much risk of a type I error one is willing to accept D. the statistical test used E. whether the sample is a probability sample
C. how much risk of a type I error one is willing to accept
The hypothesis that the number of hours worked is related to student grade point average is a _____ hypothesis. A. null B. one-tailed test C. two-tailed test D. test of proportions E. test of means
C. two-tailed test
Also known as beta error, _____ occurs when the sample results lead to the nonrejection of a null hypothesis that is in fact false. A. type I error B. two-tailed error C. type II error D. one-tailed error
C. type II error
Which of the following statements is NOT correct about the alternative hypothesis? A. It may be directional or nondirectional B. The alternative hypothesis represents the conclusion for which evidence is sought C. The alternative hypothesis is the opposite of the null hypothesis D. It is always the hypothesis tested E. None of the statements are correct
D. It is always the hypothesis tested
Which of the following is NOT true of the Kruskal-Wallis test? A. It is a one-way analysis of variance by ranks B. It assumes random selection C. It assumes a continuous distribution D. It is used with two-related samples E. All of the above are true
D. It is used with two-related samples
Which of the following involves a test of two-related samples? A. test of differences in the percent of men and women who are or are not members of Greek organizations on campus B. Test of the average incomes of magazine subscribers of Southern Living verses Better Homes and Gardens C. Test of whether the mean salary of professors at Metro University is higher than the national average for university professors D. Test of whether a change occurred in the likelihood of heart disease among people who switched to a diet high in fish E. Test of differences in ad recall among three experimental groups (each of which saw a different advertisement) and a control group
D. Test of whether a change occurred in the likelihood of heart disease among people who switched to a diet high in fish
ANOVA can be used as a parametric test of _____. A. one sample B. two-related samples C. two-unrelated samples D. k-independent samples E. all of the above
D. k-independent samples
The probability of observing a sample value as extreme as, or more extreme than, the value actually observed, given that the null hypothesis is true is called the _____. A. level of significance B. critical value C. t statistic D. p value E. alpha
D. p value
Which of the following involves a test of k-independent-samples? A. Test of differences in the percent of men and women who are or are not members of Greek organizations on campus B. Test of the average incomes of magazine subscribers of Southern Living verses Better Homes and Gardens C. Test of whether the mean salary of professors at Metro University is higher than the national average for university professors D. Test of whether a change occurred in the likelihood of heart disease among people who switched to a diet high in fish E. Test of differences in ad recall among three experimental groups (each of which saw a different advertisement) and a control group
E. Test of differences in ad recall among three experimental groups (each of which saw a different advertisement) and a control group
If a data difference is NOT caused only by random sampling fluctuations, and its size is important to the organizational decision maker, it is said to have _____. A. resistance B. statistical significance C. substantive significance D. reasonable doubt E. practical significance
E. practical significance
