Burns05 Tif 15
Burns05 Tif 15
Burns05 Tif 15
Chapter 15
BASIC DATA ANALYSIS: DESCRIPTIVE STATISTICS
GENERAL CONCEPT MULTIPLE CHOICE QUESTIONS
1.
If we had data that shows the percentage of persons in the population who expect to live until one of
the following categories: 6170, 7180, 8190, 91100, and over 100, the pie chart would be:
a. an effective visual aid for displaying age range percentages
b. less preferable than a bar chart because a pie chart does not show relative sizes of response
categories
c. less preferable because percentages should not be used to display data having to do with age, a
metric variable
d. less preferable than a scatterplot diagram because the age groups represent categories
e. less preferable than using a logarithmic scale because age is not a linear variable
The statistical software package that is used with your textbook is:
a. WorldStats
b. MICROStats
c. SPSS
d. SCSS
e. SASS
224
4.
In the statistical package that comes with your book, which of the following gives you access to the
"underlying code book"?
a. VIEW, CODEBOOK
b. FILE, EDIT, CODES
c. UTILITIES, FILE INFO
d. UTILITIES, VARIABLES
e. Either C or D are correct
You can use SPSS to obtain the codes used for a dataset. You do this by opening the data file and
going to:
a. CODE; DEFINITIONS; OUTPUT
b. UTILITIES-FILE INFO or UTILITIES-VARIABLES
c. UTILITIES; DEFINITIONS; CODES
d. DEFINITIONS; UTILITIES; VARIABLES; CODES; IDENTIFICATION LABELS
e. None of the above; SPSS is not your statistical package; it is SCSS.
Which of the following contains a list of all the variables, their names, and codes associated with
each possible response to each question?
a. data code book
b. data variables identification book
c. survey ID book
d. anonymous respondent data book
e. None of the above; there is no such list available.
225
8.
What is the process of describing a data matrix by computing a small number of measures that
characterize the dataset?
a. data description
b. small population correction factors
c. data demagnification
d. data characterization
e. data summarization
Which one of the following is NOT one of the four functions of data summarization discussed in
your text?
a. summarization
b. conceptualization
c. underlying patterns
d. generalizes sample findings to the population
e. regresses data to facts
Which type of statistical analysis is used to describe the sample data matrix in such a way as to
portray the "typical" respondent and to reveal the general pattern of responses?
a. averages and trends
b. descriptive analysis
c. inferential analysis
d. associative analysis
e. regresses data to facts
226
12.
Which type of statistical analysis is used to generalize the results of the sample to the target
population that it represents?
a. averages and trends
b. descriptive analysis
c. population determination analysis
d. associative analysis
e. inferential analysis
Which type of statistical analysis would we use to determine if College of Business college
graduates' starting salary was different from their counterparts in liberal arts?
a. differences analysis
b. descriptive analysis
c. inferential analysis
d. associative analysis
e. population determination analysis
Assume a college professor wanted to know if the number of hours studied by her students was
related to students' test scores. She would use:
a. descriptive analysis
b. interpolation
c. associative analysis
d. standard deviation analysis
e. population determination analysis
Regression analysis or times series analysis are often used in which type of statistical analysis?
a. differences analysis
b. predictive analysis
c. variance analysis
d. associative analysis
e. population determination analysis
227
16.
If a marketing manager were to need a statistical analysis to make a forecast or prediction, he or she
would most likely use:
a. differences analysis
b. predictive analysis
c. variance analysis
d. associative analysis
e. population determination analysis
When you view the Hobbit's Choice Restaurant survey data on the data editor screen in SPSS
showing columns and rows of data, you are viewing:
a. a data matrix
b. associative data (row data are associated with column data)
c. differences data (row data are different from column data)
d. population determination data
e. None of the above; there is no data editor screen in SPSS.
Which term refers to any statistical measure used that somehow reflects a typical or frequent
response?
a. averages and trends
b. frequency distribution
c. central variation
d. central tendency
e. typical matrix
For a variable coded "0" or "1," there are 102 "0s" and 101 "1s." What is the central tendency?
a. 101.5
b. 102
c. 0
d. 1
e. None of the above
If two values are tied for the most frequent values in a dataset, the distribution is said to be:
a. deuced
b. modal
c. bimodal
d. semimodal
e. trimodal
21.
Which of the following describes this data set: 12, 0, 0, 1, 1, 1, 6, 10, 11?
a. bimodal
b. trimodal
c. deuced
d. quadmodal
e. None of the above
229
26.
For purposes of comparison, we can convert the frequency distribution by dividing the frequency of
each value by the total number of observations, which results in the:
a. comparative distribution
b. variable distribution
c. count distribution
d. percentage distribution
e. standard distribution
One of the advantages of the standard deviation is that it is a measure of variation that is also:
a. translatable in terms of the normal or bell-shaped curve distribution
b. calculated as part of the frequency distribution
c. included in the range
d. applicable when calculating the mode and median
e. easily calculated when preparing a percentage frequency distribution
In the formula for calculating the standard deviation, the differences between each observation and
the mean is squared. If we did not square these differences, the standard deviation would:
a. be too small to be of any usefulness
b. always be near zero
c. not be normally distributed
d. not be interpreted by z scores
e. none of the above; the formula does not require that the differences be squared
31.
If we examine a frequency distribution and find it to be very "stretched out" (not compressed), we
can say:
a. There is a low standard deviation.
b. There is an average standard deviation.
c. There is a high standard deviation.
d. There is low variance.
e. None of the above: frequencies do not communicate anything about variability.
The FactFinder Research firm conducted a survey for a national food manufacturer, and one of
the issues addressed by the research was to determine how many pounds of fish were consumed per
capita annually. In the survey they found one person who consumed only one pound of fish
per year while 10 people reported 200 pounds per year. The range was:
a. 200
b. 1 to 2,000
c. 201
d. 199
e. 190
231
35.
When the scale type is nominal the appropriate measure of central tendency is:
a. mode
b. median
c. mean
d. nominal mean
e. All of the above
When the scale type is ordinal the appropriate measure of central tendency is:
a. mode
b. median
c. mean
d. ordinal mean
e. All of the above
When the scale type is interval or ratio, the appropriate measure of central tendency is:
a. mode
b. median
c. mean
d. interval (or ratio) mode
e. All of the above
If you have a question that has an interval or ratio scale, which of the following should be used to
report the variability?
a. frequency distribution
b. cumulative percentage distribution
c. percentage distribution and range
d. standard deviation and range
e. accumulative percentage standard deviation
Which of the following command sequences in SPSS would allow you to generate a frequency
distribution?
a. SPSS; FREQ; RUN
b. ANALYZE; DESCRIPTIVE STATISTICS; FREQUENCIES
c. ANALYZE; GENERATE; FREQ DIS
d. STATISTICS; ANALYZE; SUMMARIZE; DESCRIPTIVES
e. STATISTICS; FREQUENCY DISTRIBUTION
232
40.
When SPSS produces a frequency distribution, how does it report missing values that come from
respondents who do not answer the question being analyzed?
a. "Missing"
b. "Respondent error"
c. "No data entered"
d. Null entry
e. None of the above; SPSS cannot know that a respondent did not answer a question.
41.
You have a survey question that asks consumers to rank order their preferences of three brands of
toothpaste. You want to know the central tendency of their response. Which command sequence in
SPSS would you run?
a. SPSS; RUN: RANKAVG
b. ANALYZE; SUMMARIZE; FREQUENCIES; MEAN
c. ANALYZE; DESCRIPTIVE STATISTICS; FREQUENCIES; STATISTICS; select Median
d. ANALYZE; DESCRIPTIVE STATISTICS; DESCRIPTIVES; select Mode
e. ANALYZE; DESCRIPTIVE STATISTICS; FREQUENCIES; STATISTICS; select
Mode
Answer: (c) Difficulty: (Difficult) Page: 444
42.
Assume you have ratio data that are answers to a question concerning an appropriate price for a
service. You have 10,000 respondents you have interviewed and you want to generate a mean for
this question. Which of the following command sequences in SPSS would allow you to generate a
mean?
a. SPSS; FREQ; RUN
b. ANALYZE; SUMMARIZE; FREQUENCIES; MEAN
c. ANALYZE; GENERATE; FREQ DIS
d. MEAN; ANALYZE; DESCRIPTIVES
e. ANALYZE; DESCRIPTIVE STATISTICS; DESCRIPTIVES
If you had six categories of an answer to the question "What physical condition worries you most?"
a bar chart would be an excellent way of displaying the responses because it would easily display
the relative sizes of the different worries.
233
44.
Data entry refers to the creation of a computer file that holds the raw data taken from all the
questionnaires deemed suitable for analysis.
There are a number of options for data entry including keyboarding of each datum and scanning
questionnaires to software programs, such as WebSurveyor that automatically creates data files as
data is recorded during the interview process.
Data entry requires the researcher to first undertake an operation called data coding.
The book that contains a list of all the variable names and the codes that represent every response to
each question is called the "data matrix register."
Through the process of data summarization, the researcher describes the data matrix by computing a
small number of measures that characterize the dataset.
The function of "summarization" is achieved when we report that the average rating for a Volvo S80
model style was 8.9 on a 10-point scale.
When we describe the "typical" respondent using measures such as the mean, median, mode,
standard deviation, and range, we are employing inferential analysis.
234
52.
Inferential analysis is used anytime we wish to take known information about the population and
make inferences about what we expect to find in our sample data.
Analysis that investigates differences between groups using statistical concepts such as t tests and
analysis of variance is referred to as "differences" analysis.
A research study determined that a company's expenditure in training was associated or related to
sales force performance. This is an example of associative analysis.
Regression analysis or times series analysis are used for predictive analysis in marketing research.
The phrase central tendency refers information that describes the most typical response to a
question. It could be a mode, median, or mean, for example.
Given a string of numbers, the number that appears most often is the mean.
Given an ordered set of numbers, the value lying in the middle of the set is known as the mode.
235
61.
The mean provides more information than the mode or the median because it takes every member
of a set of numbers into account.
Measures of variability are concerned with depicting the "typical" difference between values in a
set of values.
Frequency distributions, standard deviation, and the range are all measures of variability.
A tabulation of the number of times that each different value appears in a particular set of values is
called a frequency distribution.
The range tells you how often the minimum and maximum values occur.
Plus or minus 1.96 standard deviations accounts for 68 percent of the area under the normal curve.
Plus or minus 1 standard deviation accounts for 68 percent of the area under the normal curve.
Plus or minus 2.58 standard deviations accounts for 99 percent of the area under the normal curve.
236
70.
If we take the square root of the summated, squared differences between each observation and the
mean divided by the number of observations less one, we have a frequency distribution.
In calculating the standard deviation, if we didn't square the differences between the observations
and the mean, then the standard deviation itself would be a negative number.
The appropriate measure of central tendency for an ordinal scaled variable is the mean.
The appropriate measure of central tendency for an interval or ratio scaled variable is the mean.
The appropriate measure of variability for a nominal scaled variable is the standard deviation.
The FREQUENCIES command in SPSS is particularly useful for examining descriptive statistics
for variables that are nominally or ordinally scaled.
In the SPSS FREQUENCIES command, you may ask for either the mean, median, or mode via the
STATISTICS options.
237
79.
In SPSS frequency distributions, missing cases are not counted under the column "Valid Percent."
In SPSS, DESCRIPTIVES would be most useful if we wanted the measure of central tendency and
variability for a ratio scaled variable.
In SPSS, DESCRIPTIVES would be useful if we wanted the standard deviation for a nominally
scaled variable.
APPLICATION QUESTIONS
82.
Jesse Pollard is the marketing director for SNERDLY TV Cable. He is considering offering a DVR
service (digital video recording) to his customers and he is not certain what price they are willing to
pay. He had a survey conducted and, after respondents were given a detailed description of the
proposed DVR service, they were asked what price they were willing to pay for the service. The
mean price was $30 a month. Based upon this mean, Jesse should:
a. immediately offer the service for $30 a month
b. examine the standard deviation
c. examine the range
d. examine the frequency and percentage distribution
e. Pollard should actually examine all items covered in b through d before making the decision.
83.
Robert Amos is the marketing manager for TeleOptics Inc. TeleOptics offers a system that greatly
enhances the viewing experience of home theaters by altering audio and video signals and creating
ambient lighting. Because TeleOptics is a new product, Robert is considering offering a single
package or a "Basic" package with several options at additional prices. He examines survey data
that was conducted during the concept stage of product development. One research question asked
owners of home theaters what they would be willing to pay for this enhancement system. Robert
looked at the mean and standard deviations. Which one of the following sets of means and standard
deviations would indicate that Robert should offer the "Basic" package and several options at
additional cost?
a. $75; 1.98
b. $100; .88
c. $95; 30.2
d. $88; .05
e.
$101; 2.1
238
84.
The FactFinder Research firm conducted a survey for a national food manufacturer, and one of
the issues addressed by the research was to determine how many pounds of fish were consumed
per capita annually. In the survey they found one person who consumed only one pound of fish
per year while 10 people reported 200 pounds per year. The range was:
a. 200
b. 1 to 2,000
c. 201
d. 199
e. 190
Laura Strubel is reviewing some data from a marketing research project that shows the age of
persons who frequently purchase her company's product, Strubel's Gourmet Seafood frozen dinners.
Laura is considering buying radio time for a new ad campaign, and knowing the age of the target
market would be very helpful to her in selecting which programs to place the ads. Laura sees that
the mean age of frequent buyers is 45 with a standard deviation of 12. She correctly interprets this
to mean that about 70 percent (68 percent to be exact) of her target market is aged from:
a. 18 to 45
b. 45 to 68
c. 33 to 57
d. 20 to 32
e. 45 to 57
George Hubbard has nearly completed designing a survey for a political candidate. Not only is the
candidate interested in knowing how constituents in her state feel about certain issues, but she is
interested in knowing if attitudes toward these issues differ by demographic subgroups. One of the
demographic questions George has added to the survey is religious preference. He asked this
question in a way that respondents would indicate their preference by checking a blank alongside
the name of several possible religious affiliations such as "Catholic," "Methodist," "Muslim," and so
on. George knows that he should anticipate how he is going to analyze the data before he completes
the survey questions. As he looks at the religious preference question, he knows that because it's
measurement level is ________, he should use a ________ to report the central tendency and a
________ to report variability.
a.
ratio; median; range
b.
nominal; median; frequency distribution
c.
ordinal; median; standard deviation
d.
nominal; mode; frequency; and/or percentage distribution
e.
interval; mean; standard deviation; and/or range
Answer: (d) Difficulty: (Difficult) Page: 437
239