Exam 2 TB Flashcards
Descriptive statistics are a type of univariate statistics.
a. True
b. False
True
The type of measurement scale used in the research study determines the possible statistical tests that can be used appropriately with the resulting data.
a. True
b. False
True
All statistics that are appropriate to use for higher-order scales are also appropriate to use with lower-order scales.
a. True
b. False
False
RATIONALE: All statistics appropriate for lower-order scales are suitable for higher-order scales.
A planogram is a graphical way of showing the frequency distribution in which the height of a bar corresponds to the frequency of a category.
a. True
b. False
False
RATIONALE: A histogram is a graphical way of showing the frequency distribution in which the height of a
bar corresponds to the frequency of a category.
Tabulation refers to the orderly arrangement of data in a summary format.
a. True
b. False
True
Cross-tabulation allows the inspection and comparison of differences among groups based on nominal or ordinal categories.
a. True
b. False
True
A contingency table is a data matrix that displays the frequency of some combination of possible responses to multiple variables.
a. True
b. False
True
The row and column totals in a contingency table are called subtotals because they are less than the total.
a. True
b. False
False
RATIONALE: These are called marginals because they appear in the table’s margins.
Researchers are usually most interested in the marginals of a contingency table.
a. True
b. False
False
RATIONALE: Researchers are usually more interested in the inner cells of a contingency table.
A 3 x 4 table represents a contingency table with twelve variables.
a. True
b. False
False
RATIONALE: This represents a two-way contingency table displaying two variables – one with three levels
and the other with four levels.
The distribution of the dependent variable determines which marginal total will serve as a base for computing
percentages.
a. True
b. False
False
RATIONALE: The nature of the problem the researcher wishes to answer will determine which marginal total will serve as a base for computing percentages.
A common form of elaboration analysis is to do cross-tabulation of data within subgroups of the sample under study.
a. True
b. False
True
Suppose a third variable inserted into an analysis changes the results of when two other variables were studied previously. This third variable is called a moderator variable.
a. True
b. False
True
The process of changing data from their original form to a format that more closely fits the objectives of the research study is called data transformation.
a. True
b. False
True
Combining the data from adjacent categories of a Likert-scale item is a common form of data transformation.
a. True
b. False
True
An index split means that respondents below the observed median go into one category and respondents above the median go into another.
a. True
b. False
False
RATIONALE: A median split means that respondents below the observed median go into one category and
respondents above the median go into another.
When a data set is unimodal, a median split of the data is inappropriate.
a. True
b. False
True
The purpose of a table in a research report is to summarize and communicate the meaning of the data to the reader.
a. True
b. False
True
An extreme value that lies far beyond range of most of the data in a distribution (either as a very high score or as a very low score) is called an outlier.
a. True
b. False
True
A significance level is a critical probability associated with a statistical hypothesis test that indicates how likely it is that an inference supporting a difference between an observed value and some statistical expectation is true.
a. True
b. False
True
The term p-value stands for power-value.
a. True
b. False
False
RATIONALE: The term stands for probability-value.
The researcher who uses a sample rather than the entire population runs the risk of committing two types of errors: primary errors and secondary errors.
a. True
b. False
False
RATIONALE: The two types of errors are Type I and Type II errors
A Type I error occurs when the researcher fails to reject the null hypothesis when the alternative hypothesis is true.
a. True
b. False
False
RATIONALE: A Type I error occurs when the researcher rejects the null hypothesis when it is true.
A Type II error occurs when the researcher rejects the null hypothesis when, in fact, it is true.
a. True
b. False
False
RATIONALE: This is a Type I error. A Type II error is caused by failing to reject the null hypothesis when
the alternative hypothesis is true.
The t-test is appropriate for small sample sizes with unknown standard deviations.
a. True
b. False
True
The transformation of raw data into a form that makes the data easier to understand and to interpret is called ____.
a. descriptive analysis
b. outlier analysis
c. computer mapping
d. box and whisker plotting
A
The researcher examining descriptive statistics for any particular variable is using which type of statistics?
a. multivariate
b. interval
c. nominal
d. univariate
D
Which graphical application shows a frequency distribution in which the height of a bar corresponds to the frequency of a category? a. perceptual map b. histogram c. contingency table d. frequency chart
B
The orderly arrangement of data in a summary format showing the number of responses to each response category is called \_\_\_\_. a. tabulation b. frequency c. analysis d. interpretation
A
Counting the number of responses to questions in a survey by hand is called ____.
a. indexing
b. tallying
c. collating
d. moderating
B
An arrangement of data that shows the number of times each category occurs is called a(n) ____ table.
a. cross-tabulation
b. frequency
c. percentage
d. pre-coding
B
Counting the different ways respondents answered a question and arranging them in a simple summary form yields a(n) \_\_\_\_. a. elaboration analysis b. spurious analysis c. marginal tabulation d. index analysis
C
Suppose 60 males are asked if they recognize the brand name, “Focus,” and 35 of them correctly identify the product
as a model of Ford’s product line. The proportion of the sample who recognize this brand name is approximately ____.
a. .35
b. .58
c. .64
d. .79
B
Which of the following is the appropriate technique for addressing research questions involving relationships among
multiple variables that are measured with a less-than interval scale?
a. cross-tabulation
b. ANOVA
c. regression
d. cluster analysis
A
A researcher interested in a data matrix that displays the frequency of some combination of possible responses to
multiple variables should construct a ____.
a. perceptual map
b. contingency table
c. regression equation
d. marginal table
B
Carlos is examining the row and column totals in a contingency table. What are these called?
a. marginals
b. subtotals
c. totals
d. running totals
A
If a researcher wants to summarize the responses of subjects by gender and awareness of a particular brand (“Yes” or
“No”), he or she should use a ____ contingency table.
a. 1 x 2
b. 2 x 2
c. 2 x 3
d. normal
B
The number of respondents or observations (in a row or column) used as a basis for computing percentages in a contingency table is referred to as the ____.
a. reference point
b. moderator
c. statistical base
d. analytical point
C
The nature of the problem the researcher wishes to answer will determine which \_\_\_\_ will serve as a base for computing percentages. a. independent variable b. marginal total c. dependent variable d. column mean
B
Examining responses to the question “Have you ever purchased a ticket online for an American Airlines flight?” by
looking at subgroups based on gender and zip code is an example of ____.
a. a box and whisker plot analysis
b. an index number
c. elaboration analysis
d. interquartile analysis
C
When a third variable is included in an analysis and that third variable changes the relationship between the
independent variable and the dependent variable in an important way, the third variable is called a(n) ____.
a. spurious variable
b. moderator variable
c. contingency variable
d. outlier variable
B
It is hypothesized that an individual’s style of processing information (i.e., verbal or visual) will influence the impact
of advertising on attitudes toward the brand being advertised. Style of processing, then, is considered which type of
variable?
a. dependent variable
b. external variable
c. internal variable
d. moderating variable
D
Another name for data transformation is ____.
a. index analysis
b. data conversion
c. quadrant analysis
d. data exchange
B
When a respondent's answers to ten Likert-scale items are added up to form a total subtest score for these questions, \_\_\_\_ is being used. a. data indexing b. data transformation c. contingency analysis d. data indexing
B
When a researcher combines the “Strongly Disagree” and “Disagree” responses on a Likert scale item to a single “Strongly Disagree/Disagree” percentage, the researcher is using ____.
a. data indexing
b. collapsing the data
c. the outlier effect
d. a box and whisker plot
B
Data with a(n) ____ distribution are appropriate for division based on the median split.
a. normal
b. unimodal
c. bimodal
d. uniform
C
Scores or observations recalibrated to indicate how they relate to a base number are referred to as ____.
a. index numbers
b. rank orders
c. elaborated numbers
d. real numbers
A
The use of index numbers requires the ____ level of measurement.
a. nominal
b. interval
c. ratio
d. ranked
C
A researcher is reviewing average household income data and sees that one household reported an annual income of
over $1 million. This value lies outside the normal range of the data and is called a(n) ____.
a. abnormality
b. marginality
c. outlier
d. quartile
C
Which type of statistical analysis tests hypotheses involving only one variable?
a. primary statistical analysis
b. bivariate statistical analysis
c. univariate statistical analysis
d. monovariate statistical analysis
C
The error caused by rejecting the null hypothesis when it is, in fact, true is called a ____.
a. Type II error
b. confidence level error
c. confidence interval error
d. Type I error
D
Which type of error occurs when the researcher concludes a relationship exists, when in fact one does not exist?
a. Type I
b. Type II
c. Type A
d. Type B
A
When a researcher sets an acceptable significance level a priori, the researcher is determining how much tolerance will be allowed for a \_\_\_\_ error. a. Type I b. Type II c. Type A d. Type B
A
Failing to identify a hypothesized difference using a sample result when a difference really does exist in the population is a \_\_\_\_ error. a. primary b. secondary c. Type I d. Type II
D
When sample size (n) is larger than ____, the t-distribution and Z-distribution are almost identical.
a. 10
b. 20
c. 25
d. 30
D
The orderly arrangement of data into a summary form is known as ____________________.
tabulation
The arrangement of data into a row-and-column format that gives the number of responses for each category of the
variable is known as a(n) ____________________ table.
frequency
When tabulation is done by hand to create a frequency table, the data are said to be ____________________.
tallied
A graph in which the height of a bar indicates the frequency with which that category occurred is called a(n)
____________________.
histogram
The appropriate technique for addressing a research question involving relationships among multiple less-than interval
variables is ____________________.
cross-tabulation
cross tabulation
A data matrix that displays the frequency of some combination of possible responses to multiple variables called a(n)
____________________ table.
contingency
A two-way contingency table in which each variable has two possible levels is a(n) ____________________ table.
2 x 2
An analysis of the basic cross-tabulation for each level of a variable not previously considered, such as subgroups of the sample, is referred to as____________________ analysis.
elaboration
When a third variable changes the relationship between the independent variable and a dependent variable in
important ways, the third variable is called a(n) ____________________ variable.
moderator
The process of changing data from its original form to a format that more closely matches the research objectives of the study is called data ____________________.
transformation
Scores or observations recalibrated to indicate how they relate to a base number are called ____________________
numbers.
index
A value that lies far beyond the range of the rest of the data set is called a(n) ____________________.
outlier
Analyses that test hypotheses and models involving multiple (three or more) variables or sets of variables are referred to as ____________________ statistical analyses.
multivariate
Another name for an observed or computed significance level is the ____________________.
p-value
The appropriate test to use for hypotheses involving an observed mean compared to specified value is the univariate
____________________.
t-test
What are descriptive statistics and why are they used in marketing research?
Descriptive analysis is the elementary transformation of data in a way that describes the
basic characteristics such as central tendency, distribution, and variability. Averages,
medians, modes, variance, range, and standard deviation typify widely applied descriptive
statistics that can summarize responses from large numbers of respondents.
What is a contingency table and how is it useful in marketing research?
A contingency table is a data matrix that displays the frequency of some combination of
possible responses to multiple variables. Two-way contingency tables, meaning they involve
two less-than interval variables, are used most often. The row and column totals often are
called marginals because they appear in the table’s margins. Researchers usually are more
interested in the inner cells of a contingency table because they display conditional
frequencies (combinations). Using these values, we can draw more specific conclusions.
Explain what an index number is and how it is computed. What level of measurement is required to compute index numbers?
Index numbers represent simple data transformations that allow researchers to track a
variable’s value over time and compare a variable with other variables. Recalibration allows
scores or observations to be related to a certain base period or base number. To calculate an
index number, a base number is first selected. Index numbers are computed by dividing the
score for each category by the base number and multiplying by 100. If the data are timerelated, a base year is chosen, and the index numbers are computed by dividing each year’s activity by the base-year activity and multiplying by 100. Index numbers require ratio
measurement scales.
Explain the appropriate statistical analysis for the following hypothesis: H1: The average household income in zip code 71227 is greater than $50,000.
This is a univariate hypothesis dealing with one variable: income. Univariate hypotheses are
typified by tests comparing some observed sample mean against a benchmark value. The test
addresses the question, is the sample mean truly different from the benchmark? The level of
scale measurement is ratio scaled, and if the sample size is large, parametric statistical
procedures are appropriate. In this case, a univariate t-test is appropriate for testing this
hypothesis because in involves an observed mean income against the value of $50,000.
Compare and contrast Type I errors and Type II errors and explain which one is of more concern to researchers.
Hypothesis testing using sample observations is based on probability theory. Because we
cannot make any statement about a sample with complete certainty, there is always the chance
that an error will be made. The researcher using sampling runs the risk of committing two
types of errors. A Type I error occurs when a condition that is true in the population is
rejected based on statistical observations. When a researcher sets an acceptable significance
level a priori (a), he or she is determining how much tolerance he or she has for a Type I
error. When testing for relationships, a Type I error occurs when the researcher concludes a
relationship exists when in fact one does not exist. A Type II error is the probability of
failing to reject a false null hypothesis. Alternatively, one can think of this as failing to
identify a hypothesized difference using a sample result when one really does exist in the
population. This incorrect decision is called beta (b), Type I errors generally are considered
more serious than Type II errors. Thus, more emphasis is placed on determining the
significance level, a, than in determining b