Chapter 15
Data Analysis: Basic Questions
in a recent survey. The appropriate measure(s) of central tendency for this variable are
a. the mode.
b. the median.
c. the mode and the median.
d. the mean.
e. the mode, the median, and the mean.
established using rating scales completed by consumers?
“New improved Killo disinfectant now has a 50% fresher odor, is 15% less
irritating, is 25% easier to use, and in a selected sample was stated as being more
effective by 50% of the subjects.”
a. 50% of the subjects felt it to be more effective
b. 50% fresher odor
c. 25% easier to use
d. 15% less irritating
e. they are all correct if the claims are based on consumer perceptions
(Use the following information for the next two questions.)
Consider the following advertising claims:
Claim 1: “Ultrasoft chairs last 50% longer than our competitor’s best chairs.”
Claim 2: “A random sample of homemakers found Ultrasoft chairs 65% more comfortable
than our leading competitor’s chairs.”
a. Claim 1
b. Claim 2
c. both Claim 1 and Claim 2
d. neither Claim 1 nor Claim 2
e. both claims are legitimate but not valid
a. Claim 2 can be made legitimately.
b. Claim 2 cannot be made legitimately because of the nominal nature of the rating
scale that likely was employed.
c. Claim 2 cannot be made legitimately because the sample provided
nonindependent judgments of the two chairs.
d. Both b and c are true with regard to Claim 2.
e. None of the above are true with regard to Claim 2.
A manufacturer of lawnmowers wanted to know the most important product attributes
to consumers. The company’s research team developed a comprehensive list of
lawnmower attributes. Respondents were asked to rate each attribute as either
essential (3), nice to have but not essential (2), or unnecessary (1). Using the above
information answer the following two questions.
a. nominal
b. ordinal
c. interval
d. ratio
e. none of the above
a. 60% of all respondents rated an electric starter as essential.
b. The mean rating for having an electric starter was significantly higher than the
rating given for having a catcher at =0.05.
c. For respondents over 50, an electric starter was the most important feature on a
lawnmower.
d. None of the statements are legitimate given the scale.
e. All of the statements would be legitimate.
a. In most studies the choice of statistical technique by which to analyze the
collected data is crucial for proper interpretation of what was found.
b. The conclusion of a study typically does not depend on the statistical method used
to analyze the data.
c. With interval scaling it is correct to say that car A had a scale value rating 6 times
as great as that of car B.
d. An analyst is interested in determining how the undergraduate grade point
averages of students in the Graduate School of Business and the Law School
compare. He should use a statistical test for related samples.
e. All of the above statements are false.
a. the power of the test.
b. the type of data.
c. the research design.
d. the assumptions underlying the test statistic.
e. it depends on all of the above.
analyzing the data.
a. distribution free
b. parametric
c. metric
d. multiple-sample
e. single-sample
X2 02
03
the samples are
a. large.
b. small.
c. dependent.
d. analyzed in pairs.
e. independent.
detergent product. The brand team can not decide whether to use a newspaper
coupon (X1), a sample drop (X2), or an in-store coupon (X3) to increase sales. The
research manager suggests an in-market test to (1) determine if any of the
promotions had an impact, and (2) which had the greater impact. Of the designs
shown below, which would provide the research manager with the information
necessary to make this determination?
a. X1 01
X2 02
X3 03
04
b. X1 01
X2 02
X3 03
c. 01 X1 02
03 X2 04
03 06
d. 01 X1 02
03 X2 04
05 X3 06
07 08
e. None of the designs are appropriate to meet the needs of the brand manager.
a. The samples are independent in an experiment diagrammed:
X 01
02
b. In an experiment diagrammed 01 X 02 the observations must be analyzed in
pairs as the observations are not independent.
c. The t-test for the differences in means should be used to analyze an
experiment diagrammed as: X1 02
X2 02
03
d. Suppose we wish to contrast the “exposed” and “unexposed” groups with
respect to their differences in attitude toward a product and also with respect
to the sales of the product to each group; the design would be diagrammed:
X 01
02
and the most appropriate procedure would be to test for the differences
between the two groups considering both variables simultaneously.
e. All of the above statements are true.
a. The most important question that needs to be answered in preparing to run
the maze of statistical methods is to decide whether the problem is of a
univariate or multivariate nature.
b. A statistical problem is univariate if there are several measurements on each
of the observations but each variable is to be analyzed in isolation.
c. Assuming the problem implies univariate analysis, a most important question
the analyst need ask is what level of measurement underlies the data.
d. The parametric statistical procedures are most appropriate if the data are ratio
or interval scaled.
e. Nominal data are most appropriately analyzed using arametric statistical
procedures.
a. the observations should be analyzed in pairs.
b. the samples are independent.
c. the t-test for the difference in two means is the appropriate analysis
procedure.
d. the problem is essentially multivariate in nature.
e. that none of the above are implied by the design.
razors before and after using a new kind of electric razor. The proper statistical test
for examining the data is
a. the t-test of the difference between means.
b. the paired difference test.
c. analysis of variance.
d. regression analysis.
e. none of the above.
(Use the following information for the next two questions.)
The manager of a car dealership was concerned that female customers found sales
representatives to be intimidating. The manager asked a local market research firm
to determine whether or not significant gender based differences existed in attitudes
toward automobile sales personnel.
The research supplier used random digit dialing to contact 200 men and women
over the age of 21 in the dealer’s market area. Respondents were asked to rate
automobile salespeople in the local area on helpfulness, willingness to deal,
answering questions fully, courtesy, and patience using a 7-point Likert scale with
1 being poor to 7 being excellent. All respondents were also asked if new car
salespeople were intimidating (yes or no). Only one person per household was
asked to respond to the survey and the variances between the two groups on all
questions were assumed to be equal.
conclusions based on the scales being used?
a. There is a significant difference between men and women in the ratings given
to salespeople on willingness to deal and patience.
b. Twice as many women as men felt intimidated by new car sales
representatives.
c. The mean score for willingness to deal was 50% higher among male
respondents than among female respondents.
d. All of the above are valid inferences.
e. None of the above are valid inferences.
assumption, which of the tests below should be used?
a. the Chi-square test
b. the Kolmogorov-Smirnov test
c. the F test
d. the Chebov test
e. none of the above
a. dependent.
b. metric.
c. nominally scaled.
d. ordinally scaled.
e. none of the above.
means when
a. the variance in the two populations can be assumed equal.
b. the characteristic of interest is normally distributed in each population.
c. a pooled estimator for the overall variance is warranted.
d. the data is ordinal or nominally scaled.
e. the samples are independent.
number of characteristics are considered simultaneously?
a. a multivariate statistical procedure
b. a histogram
c. a matrix
d. a cumulative distribution function
e. a frequency polygon
a. A multivariate problem of analysis obtains whenever the analyst has two or
more measures per sample object and he wishes to analyze the variables
together.
b. Both scale of measurement and role of each variable interact to produce a
complex classification scheme of multivariate procedures.
c. In dependence analysis, one (or more) of the variates is selected for special
treatment by the conditions of the problem and the emphasis is on
investigating how it depends on the other variates.
d. A criterion variable is an independent variable while an antecedent variable is
a dependent variable.
e. In interdependence analysis, all of the variables have equal footing in the
sense none is considered the criterion to be predicted by the others.
rather the researcher is interested in the relationship among all the variables
considered at once, the most appropriate technique is
a. factor analysis.
b. multiple regression analysis.
c. linear discriminant analysis.
d. multiple regression with dummy variables.
e. multiple discriminant analysis.
themselves he is concerned with the analysis of
a. dependence.
b. interdependence.
c. independence.
d. predictor variables.
e. consequent variables.
number of characteristics are simultaneously considered the most appropriate
statistical technique is
a. univariate analysis.
b. multiple regression analysis.
c. multivariate test of group differences.
d. t-test for difference in two means.
e. traditional analysis-of-variance procedures.
(Use the following information for the next three questions.)
Consider the following scenarios:
SCENARIO A: The research director for a large chain of department stores is
interested in examining the sales of a certain product in a sample of stores located
on the west coast with sales of the product in a sample of stores located along the
east coast in order to determine any differences in sales patterns.
SCENARIO B: The product manager for a large ice cream company believes that
sales of his product in supermarkets greatly depends upon the amount of space
given to the product in the ice cream section and the amount of in-store promotion
given his product. To determine if this is the case, the manager collected data from
20 supermarkets.
a. Scenario A
b. Scenario B
c. both Scenario A and Scenario B
d. neither Scenario A nor Scenario B
e. more information is needed
Scenario A?
a. t-test
b. analysis of variance
c. z-test
d. all of the above would be appropriate
e. none of the above would be appropriate.
B?
a. factor analysis
b. discriminant analysis
c. multiple regression analysis
d. Spearman’s Rank Correlation
e. all of the above are appropriate