MKT 4533 Final
Mia is preparing a research report. When including the data analysis and findings of the study in the body of the report, she should _____.
explain the information in a straightforward fashion
T/F: Area sampling is an example of a non-probability sampling method.
false
T/F: Common items contained in the appendix of a research report include the name, position, employing organization, address, telephone number of the person submitting the report, and the date the report is submitted.
false
T/F: Compared to sampling, it is less time-consuming and less expensive to conduct a census.
false
T/F: Data is validated using the curbstoning process.
false
T/F: If the means of two groups are the same, then the underlying distributions of the two groups must also be the same.
false
T/F: If the number of data observations is odd, the median is generally considered to be the average of the first and last values.
false
T/F: In any sampling plan, the first task of a researcher is to choose a method of data collection.
false
T/F: In marketing research, means should be displayed with no decimals past the decimal point.
false
T/F: In order to determine the mode of a set of responses, one has to find the number with the lowest frequency.
false
T/F: In the context of the factors that play an important role in determining sample sizes with probability designs, the higher the level of confidence desired, the smaller the sample size needed.
false
T/F: In the process of editing the responses to open-ended questions, researchers typically fill out the incomplete answers based on their best judgment.
false
T/F: Regression analysis assumes a linear relationship is a bad description of the relationship between two variables.
false
T/F: Reporting limitations often diminishes the credibility of a marketing research report.
false
T/F: Researchers should strive to communicate findings and key points using graphics and should avoid the use of text to explain the findings in graphs and tables in their reports.
false
T/F: Sampling errors usually are related to the accuracy of data, whereas non-sampling errors relate to the representativeness of a sample to a defined target population.
false
T/F: Scanning technology cannot be used to enter data.
false
T/F: The least squares procedure determines the best-fitting line by maximizing the vertical distances of all the data points from the line.
false
T/F: The objective of the coding process is to expand the number of individual responses to a larger set of specific, yet related categories of answers that can be assigned numerical codes.
false
T/F: The skip interval in systematic random sampling is computed by multiplying the number of potential sampling units on a list by the desired sample size.
false
T/F: The smaller the size of the coefficient of determination, the stronger the linear relationship between the two variables being examined.
false
T/F: The use of a simple regression model assumes that the error terms associated with making predictions are not independently distributed.
false
T/F: Univariate statistics use several variables at a time to generalize about a population from a sample.
false
T/F: When reporting percentages in marketing research, it is common practice to show only one digit past the decimal.
false
T/F: When reporting results, writers should state that the results are obvious or self-evident.
false
T/F: Writing a summary of the findings is the final step in both qualitative and quantitative reports.
false
Why do we reverse certain items?
filter out invalid respondents, reduce bias, easier to understand for some items
What are the common mistakes in sample design or sampling procedures?
frame error, population specification error, selection error
The first step in developing codes for the anticipated responses to open-ended questions is _____.
generating a list of potential responses
How is the research population identified?
geographic area, demographic characteristics, product or service usage characteristics, awareness measures
What are the characteristics of self-selected sampling?
have to know why people responded to the survey, usually end points of the distribution, may have use in application (like feedback)
The pattern of covariation around the regression line that is not constant around the regression line and varies in some way when the values change from small to medium and large is known as _____.
heteroskedasticity
_____ can bias the sample in systematic/sequential sampling.
hidden patterns in the population list
margin of random error
how far from the sample statistic the researchers may believe the population parameter might be (how much above or below the statistic found)
What does the chi-square test tell us?
how far the observed frequencies are from the expected frequencies
What does regression test?
how independent variables influence dependent variables
z-value
how many standard deviations above or below the mean
How do we know if there is a relationship between two variables of interest?
if a systematic relationship exists between two or more variables (present)
When does a Type 2 error occur?
if we accept the null hypothesis and it is false
When does a Type 1 error occur?
if we reject the null hypothesis and it is true
population specification error
inaccurate definition of the research population
frame error
incomplete or inaccurate list of the research population
Which of the following is permissible in the process of data validation?
To ascertain the completeness of interviews, a researcher can recontact a sample of respondents and ask about questions from different parts of the questionnaire.
sampling frame
a list of population elements from which units can be selected or a specified procedure that is used to generate a list
population variance
a measure of the dispersion of the population, and its square root of the level of confidence desired in the estimate
Pearson correlation coefficient
a statistical measure of the strength of a linear relationship between two metric variables
A fundamental basis of regression analysis is the assumption of _____.
a straight-line relationship between the independent and dependent variables
A _____ relationship is one between two variables whereby the strength and/or direction of their relationship changes over the range of both variables.
curvilinear
_____ is a statistical method that is an extension of multiple regression and helps researchers determine whether there are meaningful relationships between the variables shown in the structural model.
partial least squares
Peter wants to clearly portray the relative proportion of response to a question in his research report. In this scenario, Peter is most likely to use a(n) _____.
pie chart
What are examples of probability sampling?
simple random, systematic/sequential, stratified, cluster/area
What are the advantages of systematic/sequential sampling as compared to simple random sampling?
simpler, less time consuming and less expensive
Simple random sampling is the _____ form of probability sampling.
simplest
Which method of sampling relies on the assumption that rare groups of people tend to form their own unique social circles?
snowball sampling
How is systematic error reduced?
solid research, sample design and skilled interviewers
self-selected sampling
something that you as the individual selects for yourself
random error
spread of distribution, happens randomly
Which of the following measures is an indicator of how similar or dissimilar the numbers are in a set of responses?
standard deviation
hypothesis
statement about a population based on a measure of the population
alternative hypothesis
the hypothesis researchers are testing
Researchers use analysis of variance to determine the _____.
statistical difference between three or more means
What form of sampling would you use when you know the distribution and can segment to similar within, different between?
stratified sampling
While studying the relationship between advertising and sales growth, a researcher determines that the relationship is sometimes weak and at other times moderate. This variation from one situation to another is the variation in the _____ of the relationship between advertising and sales growth.
strength of association
What are the disadvantages of judgment sampling?
success is dependent on subjective decisions made by researchers and representativeness cannot be measured (generalized results beyond sampled respondents in questionable)
Which of the following sections in a report highlights each topical area, the subdivisions within each area, and corresponding page numbers?
table of contents
What does ANOVA test?
test group means
covariation
the amount of change in one variable that is consistently related to the change in another variable of interest (degree of association between two variables)
The mean is best defined as the _____.
the arithmetic average of the sample
Variance is _____.
the average squared deviations about a mean of a distribution of values
mean
the average value within the distribution
What do we calculate a test statistic based on?
the data and confidence level
Which of the following is included in the title page of a report?
the date the report is submitted
In regression analysis, the technique used to determine the best-fitting line by minimizing the vertical distances of all the points from the line is called _____.
the least squares procedure
What type of respondents should be excluded from the research population?
those who work for the competitors
T/F: A coded value can be rejected if it is too large or too small for a particular scaled item on a questionnaire.
true
T/F: A one-way frequency table shows the number of respondents who answered each possible response to a question given the available alternatives.
true
T/F: A population is an identifiable group of elements of interest to a researcher and pertinent to the information problem.
true
T/F: A problem area for marketing researchers in multiple regression is when the independent variables are highly correlated with each other.
true
T/F: A scatter plot wherein the dots form an ellipse indicates a positive relationship between variables.
true
T/F: Codes must be assigned to facilitate quantitative data analysis only after responses are reviewed and themes and common words and patterns are identified.
true
T/F: Covariation refers to the degree of association between two variables.
true
T/F: Customer lists from credit card companies are a common source of sampling frames.
true
T/F: For interval or ratio data, the mean is appropriate, except when there are extreme values within the interval or ratio data, which are referred to as outliers.
true
T/F: Generally, actual population parameters are unknown since the cost to perform a true census of almost any population is prohibitive.
true
T/F: In cluster sampling, each cluster is assumed to be representative of the heterogeneity of a target population.
true
T/F: In multiple regression, the value of a beta coefficient can never be greater than 1.
true
T/F: In the context of the process of coding the responses to survey questions, developing consolidated categories is a subjective decision that should be made only by an experienced research analyst with input from the project's sponsor.
true
T/F: In the context of the systematic sampling method, hidden patterns represent populations that researchers may be interested in studying, but often are hard to reach.
true
T/F: Information in the appendix of a research report is cited in the report to guide a reader to further technical or statistical detail.
true
T/F: Measures of central tendency locate the center of a distribution.
true
T/F: Multiple regression analysis is an extension of bivariate regression.
true
T/F: Non-sampling errors reduce the overall quality of the data regardless of the data collection method.
true
T/F: One of the simplest ways to present regression findings in a research report is to create a diagram in Word or in PowerPoint that displays the predictor and the outcome variables with arrows showing the relationships between the variables.
true
T/F: Recommendations are generated by critical thinking.
true
T/F: Researchers can use the Chi-square test to determine whether responses observed in a survey follow the expected pattern.
true
T/F: The Scheffé follow-up test identifies differences between all pairs of means at high and low confidence interval ranges.
true
T/F: The central limit theorem (CLT) describes the theoretical characteristics of a sample population.
true
T/F: The purpose of inferential statistics is to make a determination about a population on the basis of a sample from that population.
true
T/F: The strength of association between two variables is determined by the size of the correlation coefficient.
true
T/F: To measure whether a relationship exists between two variables, we rely on the concept of statistical significance.
true
T/F: When the correlations between independent variables in multiple regression are high enough to cause a problem, one approach to deal with it is to create summated scales consisting of the independent variables that are highly correlated.
true
convenience sampling
using people who are easily accessible
Why can't formulas be used for non-probability sampling?
usually a subjective judgment by the researcher
What are the characteristics of the Pearson correlation coefficient?
varies between -1.00 and 1.00, 0 and null hypothesis are no correlation
A researcher plots a scatter diagram of two variables. The dots on the plot are scattered roughly in a circle. This indicates that the relationship (covariation) between the two variables is _____.
very close to zero
What is an advantage of snowball sampling?
very useful with hard-to-reach and low incidence populations
Why conduct a hypothesis test?
want to decide if our statement is true or not
When is cluster sampling useful?
when population size is large and geographically dispersed
How is sample vs population measured?
µ ≠ X µ = X + error
If p-value is _____, reject the null hypothesis and accept the alternative hypothesis.
≤ 0.05
If the test statistic value is _____, reject the null hypothesis and accept the alternative hypothesis.
≥ critical value
When a market researcher has reported data, statistics, and information that are not consistent with a study's objectives, which of the following problem areas has the researcher fallen victim to?
lack of relevance
Cluster sampling is the _____ representative form of probability sampling.
least
What are the steps in sampling?
1. define population 2. choose sampling elements/frame 3. select sampling procedure/method 4. compute sample size 5. collect data
What are the steps of cluster/area sampling?
1. divide the population into mutually exclusive clusters 2. random sample a number of clusters- one level (sample entire cluster) or two level (randomly select members within selected cluster)
What are the steps of stratified sampling?
1. divide the population into mutually exclusive groups 2. random selection from each group
What is the measure of central tendency, measure of dispersion and statistic for interval or ratio data?
1. mean, median, mode 2. standard deviation, percent 3. t-test, ANOVA (parametric)
What is the measure of central tendency, measure of dispersion and statistic for ordinal data?
1. median, mode 2. percent 3. chi-square (nonparametric)
What is the measure of central tendency, measure of dispersion and statistic for nominal data?
1. mode 2. none 3. chi-square (nonparametric)
What three factors play a role in sample sizes with probability designs?
1. population variance (standard deviation) 2. level of confidence desired in the element (z-value) 3. degree of precision desired (random error)
What are the two types of systematic errors?
1. sample design error 2. measurement error
What are the six steps of hypothesis testing?
1. state the hypothesis 2. choose the appropriate statistical test 3. choose the confidence/significance level 4. calculate the test statistic value 5. compare the absolute value of test statistic value to the critical value at the significance level and state the conclusion
What three assumptions do we make while calculating the Pearson correlation coefficient?
1. two variables have been measured with interval/ratio measures 2. linear relationship 3. normally distributed population
If the between-group variance is 3 and the within-group variance is 2, then the F-ratio is _____.
1.5
In a systematic sampling study, if the sampling frame has 2,000 names and the desired sample size is 50, then the skip interval should be _____.
40
Calculate the mode of the following raw responses: 2, 3, 3, 4, 5, 5, 6, 6, 6, 7, and 8.
6
List the advantages and disadvantages of simple random sampling.
Advantages: easily understood, results can be generalized to a target population, unbiased estimates of a population's characteristics, valid representation of a target population Disadvantages: difficult to obtain an accurate listing of the target population elements, works best for small populations (not large)
Which of the following is an example of curbstoning?
An interviewer filling out surveys without interviewing respondents
Which of the following is true of cluster sampling?
Area sampling is a popular form of cluster sampling.
Which of the following is true of data editing?
As part of the editing process, the researcher ensures that all respondents were asked the proper questions.
Which of the following statements about the Chi-square test is true?
Chi-square analysis compares the observed frequencies of responses with the expected frequencies.
In the context of the components of a marketing research report, how are conclusions different from recommendations?
Conclusions concisely explain research findings and the meaning that can be attached to the findings, whereas recommendations address appropriate future actions.
How do we determine internal consistency?
Cronbach's Alpha
Which of the following is true of the mean?
It can be distorted if extreme values are included in the distribution.
Which of the following is true of convenience sampling?
It is a non-probability sampling method.
Which of the following is true about n-way analysis of variance (n-way ANOVA)?
It is a type of ANOVA that can analyze several independent variables at the same time.
Which of the following statements about the Scheffé test is correct?
It is equivalent to simultaneous two-tailed hypothesis tests.
Which of the following is true of the mode?
It is especially useful as a measure for data that have been somehow grouped into categories.
Which of the following is true of the median?
It is especially useful as a measure of central tendency for ordinal data.
Which of the following statements is true of the range?
It is the distance between the smallest and largest values in a set of responses, and it identifies the endpoints of a distribution of values.
Which of the following is true of the introduction in a research report?
It lists specific research objectives and questions the study was designed to answer.
Which of the following is true of the executive summary in a research report?
It presents the major points of the report and should actually be written last.
Which of the following is true of a beta coefficient?
It shows the change in the dependent variable for each unit change in the independent variable.
Which of the following instructions should be kept in mind when reporting the means of thematically related variables?
Means and standard deviations should generally display one digit past the decimal.
Which of the following is true of skip questions?
Skip questions are not a problem with online surveys since the computer controls the sequence of answering questions.
Which of the following statements is true of the factors that play an important role in determining sample sizes with probability designs?
The more precise the required sample results, the larger the sample size.
Which of the following statements is true of correlation analysis?
The null hypothesis for the Pearson correlation coefficient states that the correlation coefficient is zero.
Which of the following is true of coding the responses to survey questions?
The second phase of the process of developing codes is the consolidation of responses.
What is the z-value formula?
Z = (x-µ) / σ
Which of the following tests flags the means that are statistically different from each other?
a follow-up test
degree of precision desired
acceptable amount of error in the sample estimate
In the context of coding the responses to survey questions, researchers can never analyze the actual answers of respondents in more detail if the _____.
answers were initially coded into broad categories
What is the most popular way to cluster sample?
area
What form of sampling would you use when members are similarly distributed across geographic areas?
area sampling
What is a limitation of cluster sampling?
assumes every cluster is as diverse and heterogenous as the entire population (members are similarly distributed across clusters) and this is not often true
While preparing a research report, a researcher should _____.
avoid the unnecessary use of sophisticated multivariate statistical techniques
_____ is defined as the quality of a research report that is based on clear and logical thinking, precise expression, and accurate presentation.
believability
How are sample sizes determined for non-probability sampling?
budget and previous studies' results, scope of study, incidence rates, cooperation/completion rate, planned contrasts
How are decisions shaped?
by trade-offs of time, money and information quality
The best way to handle omitted responses is to _____.
check how the data analysis software treats missing data and then determine a course of action
What are the types of analysis?
chi-square test, t-test, ANOVA, correlation analysis, regression
difference hypothesis
claims that there is a difference between two groups
relational hypothesis
claims that there is a relationship between two variables
Which of the following is a probability sampling method?
cluster sampling
What type of research often uses non-probability sampling?
commercial
The objective of the methods-and-procedures section in a research report is to _____.
communicate how the research was conducted
What is the purpose of screening questions?
confirm that respondents are within the research population
reliable
consistent results over time (ability to test/re-test)
What are the advantages of judgment sampling?
contains subgroups in the proportions desired by researchers and reduces selection bias by field workers
What are examples of non-probability sampling?
convenience, snowball, self-selected, judgment, quota
Zara participated in a telephone survey. A day later, she received a call. She was asked if the interviewer sounded negative during the survey. Which of the following areas covered by data validation is illustrated in this scenario?
courtesy
In a certain town, when the number of automobiles owned went up, the number of automobile repair and service centers also went up. This illustrates the concept of _____.
covariation
Which of the following is the first step in the data preparation process?
data validation
scatter diagram
describes the covariation between two variables using horizontal and vertical axes
The first step in error detection is to _____.
determine whether the software used for data entry performs "error edit routines" that identify the wrong type of data
Perceptual mapping is a process that is used to _____.
develop maps that show the perceptions of respondents in a study
If a relationship is present, it is important to know the _____.
direction (positive or negative)
stratified sampling
divide the population based on criteria that can affect the behaviors being measured by the research
What is needed for simple random sampling?
each population member is given a number then random number generator is used to select units
The process where raw data are checked for mistakes made by either the interviewer or the respondent is known as _____.
editing
probability sampling
every member in a population has a known, non-zero chance of being selected
What three intervals are accepted internal consistencies using Cronbach's Alpha?
excellent- alpha ≥ 0.9 good- 0.8 ≤ alpha ≤ 0.9 acceptable- 0.7 ≤ alpha ≤ 0.8
Janice is waiting for a research report to prepare for a meeting. She receives the report just 10 minutes before the meeting. She wants to know about the research objectives, research method, key findings, and suggested future actions. Given the short time frame, Janice has time to read only one section of the report. In this scenario, which of the following sections of the report is she most likely to read?
executive summary
Why is quota sampling useful and where is it used?
increase representativeness of a non-probability sample and used in mall intercepts/phone polls
How is sampling error reduced?
increase sampling size
census
information obtained from every element in the defined target population
In the context of the format of a research report, a researcher is most likely to include relevant background information, definition of terms, and the study's scope and emphasis in the _____.
introduction
A college professor wants to know if university students in the Unites States will find the new textbook that he has authored to be interesting and useful. He chooses all marketing majors at the school he teaches as his sample. He believes that this group of students will be representative of the university student population in the United States. In this scenario, the professor is most likely using _____.
judgment sampling
What are the two types of relationships between variables?
linear and curvilinear
What is an advantage of stratified sampling?
maintains genetic makeup of the population in the sample, more statistically accurate than a simple random sample
_____ is the most common measure of central tendency.
mean
What are examples of descriptive statistics?
measurements of central tendency and measurements of dispersion
The _____ is the middle value of a distribution when the distribution is ordered in either an ascending or a descending sequence.
median
Which of the following measures requires that the responses be first arranged in a hierarchical pattern?
median
non-probability sampling
members of a population do not have a known probability of being chosen in the sample
systematic/sequential sampling
members of the population are numbered and selected based on a skip interval skip interval = population size / sample size
simple random sampling
members of the population have an equal probability to be included in the sample selection probability = sample size / population size
If a researcher is interested in measuring the effect of multiple independent variables on a dependent variable, he or she should use _____.
multiple regression analysis
What is the formula for estimating a sample size?
n= (Z_(B,C)^2 )(σ^2⁄e^2 )
What is the formula for estimating a sample size for small populations?
n=n∗ N⁄((N+n -1) )
snowball sampling
new participants are based on referrals from the initial respondents
strength of association
no relationship, weak, moderate or strong
What type of error is a measurement error?
non-sampling error
What are examples of frequencies?
one-way frequency table and cross-tabulations
In the context of data preparation for quantitative analysis, the data entry procedure is not necessary when _____.
online data collection is used
The statistical procedure that results in equation parameters (a and b) that produce predictions with the lowest sum of squared differences between actual and predicted is called _____.
ordinary least squares
What are the advantages between probability sampling and non-probability sampling?
probability- obtains information from a representative cross-section of the population of interest, random error can be computed, survey results can be projected to the whole population non-probability- costs less than probability samples, faster to execute and if collected in a thorough manner, reasonably representative for applied marketing research
strength of association with Pearson correlation coefficient
quantitative description of the size of the correlation coefficient (between 0.81-1.00 is strong, between 0.00-0.20 is weak)
reverse coded question
questions that have opposite word phrasing, resulting in the opposite score on a scale, need to be recoded to get the non-reversed score
Sarah, a researcher, does not have the resources or time to use a probability sampling method. However, she wants to make sure that all ethnicities are fairly represented in her sample. In this scenario, Sarah is most likely to use _____.
quota sampling
What form of sampling would you use when you do not know distribution?
random or sequential sampling
The coefficient of determination _____.
ranges from .00 to 1.0
In a research report, the action statements that will help solve the problem at hand through the creation of a competitive advantage is most likely to be included in the _____.
recommendations
What does the correlation analysis test?
relationships between variables
Jamie Nelson works for a telephone company. She is interested in determining the satisfaction of customers with the service provided by the company (for landline customers only). She decides to collect data from the customers listed in the company's existing customer directory. In this scenario, the customer directory serves as a(n) _____.
sampling frame
sampling vs census
sampling is less time consuming and less costly than a census, important indirect role in designing questionnaires
selection error
sampling procedures are incomplete, improper, or not fully followed
Spectrum Inc., an automobile manufacturer, is interested in measuring the customer satisfaction of car owners. It decides to collect data from new purchasers of Spectrum cars. In this scenario, the new purchasers of Spectrum cars represent a(n) _____.
sampling unit
sample
selection of a small number of elements (sample) from a larger defined target group of elements (population)
What does the t-test test?
simple mean and two means
median
the middle value of the distribution when ordered in either ascending or descending sequence
null hypothesis
the opposite of the alternative hypothesis
confidence level
the probability that the confidence interval will include the population parameter
significance level
the researcher's maximum acceptable rate to make a Type 1 error
The difference between stratified random sampling and cluster sampling is that in cluster sampling _____.
the sampling units are divided into mutually exclusive and collectively exhaustive subpopulations
judgment sampling
the selection is based on the researcher's judgment as to how well the sample represents the research population
quota sampling
the selection of prospective participants according to pre-specified quotas for either and maintains the same ratios of major demographic characteristics in the research population
Sampling units refer to _____.
the target population elements available for selection during a sampling process
mode
the value that appears in the distribution most often