Marketing Research Exam 3
A researcher wants to use systematic random sampling to draw a sample of 300 from a target population of 1,500. In this scenario, the skip interval will be
5
Nonsampling Error
A bias that occurs in a research study regardless of whether a sample or census is used is called
a difficulty associated with detecting sampling errors in a research study.
A census is rarely conducted in survey research.
Which of the following is an example of convenience sampling
A consumer psychology professor interviews his students to measure the success of a new advertising campaign.
Angelo, a researcher, asks the following question in his rating scale that measures employee satisfaction: How satisfied or dissatisfied are you with your current employer's promotion criteria and pension plans? 1. Very Happy 2. Happy 3. Unhappy 4. Very Unhappy Which of the following misleading scaling formats is exemplified in this scenario
A double-barreled question
Which of the following includes two or more different attributes or issues in the same question, but the scale points allow respondents to comment on only a single issue
A double-barreled question
Identify an advantage of convenience sampling
A large number of respondents can be interviewed in a relatively short time.
Sampling Frame
A list of all eligible sampling units that are developed by a researcher
Census
A research study that includes data about every member of a defined target population
Which of the following is an example of area sampling
A researcher segregates participants into subgroups based on where they live and then interviews participants from each subgroup
Free-choice scale
A scale that has a center neutral response
Forced-choice scale
A scale that lacks a neutral descriptor to divide positive and negative answers
N
Calculated sample size determined by the formula used to calculate the sample size for a large population
e
Choice Acceptable tolerance level of error (stated in percentage points)
The population variance
Choice It is a measure of the dispersion of the population, and its square root, referred to as the population standard deviation
The degree of precision desired in estimating the population characteristic
Choice It refers to the acceptable amount of error in a sample estimate.
The confidence level desired in an estimate
Choice It refers to the certainty that the true value of the data being estimated falls within the precision range that has been selected.
A probability sampling method in which the sampling units are divided into mutually exclusive and collectively exhaustive subpopulations is called
Cluster Sampling
A hypothetical variable made up of a set of component responses or behaviors that are thought to be related is called
Construct
The integrative process in which researchers determine what particular data should be collected for solving the defined research problem is called
Construct development
Which of the following tasks can be performed by a researcher who understands the basics of the central limit theorem
Drawing representative samples from any target population Obtaining sample statistics from a random sample that work as accurate estimates of the target population's parameters
Proportionately stratified sampling
Each stratum's sample size is dependent on that stratum's size relative to the defined target population.
Disproportionately stratified sampling
Each stratum's sample size is independent of that stratum's proportion of the total defined target population
Identify the true statements about the equivalent form reliability technique.
Equivalent form reliability is evaluated by measuring the correlations between scores on the two equivalent scale measurements. It is difficult and probably impossible to create two completely equivalent scales
Q
Estimate of expected population proportion having a desired characteristic based on prior information or intuition
Changing respondent behaviors disallow multisource sampling
False
Quantitative data is not easily organized and categorized within fixed fields.
False
True or false: Nonprobability sampling results are often used by researchers to make statistical inferences about the true population parameters.
False
True or false: The basic logic underlying optimal allocation is that the greater the heterogeneity of a stratum, the fewer the units that would be selected to accurately estimate the true population parameter for that subgroup.
False
Identify the features of nonsampling error.
It can occur at any stage of the research process. It occurs due to incorrect question/scale measurements.
Identify the true statements about a nominal scale
It does not allow researchers to rank a set of responses. It only allows researchers to classify responses into mutually exclusive subsets that do not have distances between them.
Face validity
It involves a systematic but subjective evaluation of a scale's validity.
Which of the following is a disadvantage of systematic random sampling
It involves the possibility of hidden patterns in the list of prospective participants' names that create bias.
Content validity
It is a measure of the degree to which all the relevant dimensions of a construct are represented.
Multiple-item scale
It is a scale format that simultaneously collects data on several attributes of an object or construct.
identify the definition of a loaded question.
It is a situation where the question suggests a socially desirable answer or involves an emotionally charged issue.
Face validity
It is determined using researchers' expert judgment.
Identify a disadvantage of simple random sampling
It is difficult to obtain a precise and complete listing of the target population elements.
Identify a true statement about cluster sampling
It is easy to implement and is cost-effective.
Identify a disadvantage of a census
It is more time-consuming and expensive than sampling.
Which of the following is an advantage of simple random sampling
It produces unbiased estimates of the characteristics of the target population.
Content validity
It requires more rigorous statistical assessment than the other measure of scale validity.
An ordinal scale format that asks respondents to indicate the degree to which they agree or disagree with a series of mental belief or behavioral belief statements about a given object is called
Likert Scale
The process of developing methods to systematically characterize or quantify information about constructs, concepts, or objects is called
Measurement
describe how the data are distributed around a central value.
Measures of dispersion
______ is sometimes used in stratified random sampling when no single source can generate a large or low incidence sample
Multisource sampling
A scale that allows a respondent to express relative magnitude between the answers to a question and arranges responses in a hierarchical pattern, but does not allow researchers to determine absolute difference between responses, is called
Ordinal scale
n
Population size
A nonprobability sampling method in which participants are selected according to prespecified quotas regarding demographics, attitudes, behaviors, or some other criteria is called
Quota Sampling
State-of-being information
Researchers can use external sources to verify the data.
In the context of stratified random sampling, which of the following is true of dividing a target population into homogeneous strata
Researchers have the opportunity to study each stratum and compare strata.
State-of-behavior information
Researchers have various methods available for capturing this type of information.
State-of-mind information
Responses or information representing a person's cognitive thinking, mental attributes, or emotional feelings about an object that are not directly observable or available through external sources
State-of-intention information
Responses or information that represent an individual's or organization's expressed likelihood of undertaking specified future behavioral actions/reactions
State-of-behavior information
Responses or information that represents an individual's, object's, or organization's observable current actions/reactions or recorded past actions/reactions
Identify the formula to calculate the sample size when researchers work with small populations
Sample size = (Specified degree of confidence × Variability/Desired precision)2 × N/(N + n - 1)
Any type of bias that is attributable to mistakes in either drawing a sample or determining the sample size is called
Sampling error
Which of the following is true of detecting sampling errors in a research study
Sampling error determination can be done only after a sample is drawn and data collection is completed
Which of the following is true of detecting sampling errors in a research study
Sampling error determination can be done only after a sample is drawn and data collection is completed.
Which of the following assesses whether a scale measures what it is supposed to measure?
Scale validity
What selection factors need to be considered when selecting the sampling design
Scope of research Research objectives Resources Time frame Statistical analysis needs
Arrange the steps involved in drawing a stratified random sample in the order of their occurrence.
Segregating a target population into homogeneous subgroups or strata deriving random samples from each stratum Merging the samples from each stratum into a single sample of the target population
or referral sampling is a nonprobability sampling method in which a set of respondents is chosen by a researcher, and they help the researcher identify additional people to be included in the study
Snowball sampling
Identify the popular techniques for evaluating internal consistency reliability
Split-half test Coefficient alpha
______ involves the separation of the target population into different groups and the selection of samples from each group.
Stratified random sampling
State-of-mind information
The accuracy and quality of this type of information are limited to the degree of honesty of the individual providing the responses to the questions.
Defined Target Population
The complete set of elements identified for investigation based on the objectives of a research project
Which of the following is true of convenience sampling
The data are not generalizable to the members of the defined target population.
P
The estimate of expected population proportion not holding the characteristic of interest
Identify the true statements about the factors that play an important role in determining sample sizes with probability designs
The higher the level of confidence desired, the larger the sample size required. The greater the variability in the data being estimated, the larger the sample size required.
Which of the following is true of cluster sampling
The homogeneous nature of clusters leads to less precise sample estimates.
Which of the following are factors that play a significant role in determining sample sizes with probability designs
The level of confidence desired in the sample estimate The degree of precision desired in estimating the population characteristic The population variance
What is at the core of construct development?
The need to determine what is to be measured exactly
--- p
The percentage value derived from a simple random sample
Identify the true statements about designing questionnaires
The principles of designing questionnaires remain essentially the same regardless of advances in communication systems. Good questionnaires, or well-designed questionnaires, allow researchers to gather information that is not only reliable but also valid.
Which of the following is a feature of judgment sampling
The representativeness of the sample cannot be measured.
Identify the tasks that can be performed by a researcher who understands the basics of the central limit theorem
The researcher can more accurately assess the validity and reliability of scale measurements and constructs. The researcher can draw one random sample, instead of many samples, and thus reduce data collection costs.
Which of the following are advantages of quota sampling
The sample generated consists of specific subgroups in the proportions desired by researchers. It ensures the identification and inclusion of appropriate subgroups in a survey.
Which of the following is a specific rule followed when members from a population are selected in probability sampling?
The sample population must be a proper representation of the defined target population.
--- x
The sampling distribution of the mean
when selecting members from a population for the inclusion in probability sampling.
The selection of the sampling units should be unbiased.
n
The size of the sample
ZB,CL
The standardized z-value associated with the level of confidence
Sampling Units
The target population elements available for selection during the sampling process are
Karen, a researcher, administers a test on a particular 15-member family once every fifteen days for two months. She chooses this technique of measurement to make sure the results are reliable. Identify the method used by Karen
The test-retest reliability technique
Which of the following techniques involves reiterating the scale measurement with either one sample of respondents at two different times or two different samples of respondents from one specific target population under as nearly the same conditions as possible
The test-retest reliability technique
μ
The true target population mean
Identify true statements about research panel samples
They are quota samples drawn based on behavioral patterns, demographic quotas, and similar information. They are nonprobability samples but are considered representative of the target population.
Complex questions
They are situations in which the question is worded in a way the respondents are not sure how they are supposed to respond.
Ambiguous questions
They involve a situation in which possible responses can be interpreted a number of different ways.
Identify the features of unbalanced scales that differentiate them from balanced scales.
They often introduce bias in the research project. They have a larger number of response choices on one side, either positive or negative.
Construct selection
To accurately identify and define what is to be measured
Scale measurement
To determine how to accurately measure each construct
Identify a purpose of quota sampling.
To ensure the representation of prespecified subgroups of the population
The absolute difference between rankings cannot be determined using ordinal scales.
True
State-of-being information
Verifiable responses or information representing the physical and/or demographic or socioeconomic characteristics of individuals, objects, or organizations
When is snowball sampling typically used
When it is very difficult to compile a complete list of sampling units When the defined target population is unique and small
Given X = Defined target population list size, and Y = Desired sample size, identify the formula for skip interval that is used in systematic random sampling
X/Y
Sampling is used when...
a census is impossible or unreasonable to use.
In systematic random sampling, sampling units are selected
according to their position using a skip interval
Validity is a measure of
accuracy
A true statement about sampling frames is that
accurate, representative, and current sampling frames are difficult and expensive to obtain
A form of cluster sampling in which the clusters are formed by geographic designations is called
area sampling
A special type of rating scale designed to capture the likelihood that people will demonstrate some type of predictable behavior intent toward purchasing an object or service in a future time frame is called a
behavioral intention scale
Sharon, a researcher, is using a rating scale to collect data for her study on the likelihood of consumers visiting particular restaurants. The rating scale assesses the likelihood of consumers visiting EatnShop, VictoryDine, GentleFoods, and Hog and Blog. The scale points are as follows: Would definitely eat here; Would probably eat here; Would probably not eat here; Would definitely not eat here. In this scenario, Sharon is using a
behavioral intention scale
In the context of measurement scales, which of the following best exemplifies a construct?
brand loyalty
Natalie, a researcher, wants values that indicate the relative magnitude of importance each feature of a mobile phone has to a respondent. She asks respondents to assign values to six features, whose total must add up to 100. In this scenario, Natalie is using
constant sum scale
Scales that require a respondent to allocate a given number of points, usually 100, among each separate attribute or feature relative to all the other listed ones are called
constant sum scale
A nonprobability sampling method in which samples are drawn at the convenience of the researcher is called
convenience sampling
How do you define a target population precisely
defining a target population is done through terms of elements, sampling units, and time frames.
Arrange the steps in developing a good sampling plan in the order of their occurrence
defining the target population selecting the appropriate data collection method identifying the sampling frames needed selecting the appropriate sampling method determining the necessary sample size and overall contact rates creating an operational plan for selecting sampling units and executing the operational plan execute the operational plan
The primary difficulty researchers encounter when using stratified sampling is
determining the basis for stratifying the target population
The scale's ability to differentiate between categorical scale responses, or points, is called its
discriminatory power
Lang, a researcher, asks his subjects, "To what extent do you agree that there are never insufficient funds to complete a project?" In this scenario, Lang is using a
double-negative question
The more scale points researchers use, the lesser the discriminatory power of the scale and the lesser the variability in the collected data.
false
A scale measure that uses a scale point format that presents the respondent with some type of illustrative continuum as the set of possible raw responses to a given question is called a
graphic rating scale
A difference between balanced and unbalanced scales is that balanced scales
have an equal number of positive and negative response options
The degree to which individual questions of a construct are correlated is called
internal consistency
A scale that demonstrates absolute differences between each scale point, but does not allow researchers to make absolute comparisons between responses, is called
interval scale
To measure consumer responses, CellMan Inc., a mobile phone company, asks its users to rate its products' features on a scale of 1 to 5, where 1 is "Strongly disliked this feature" and 5 is "Absolutely loved this feature." CellMan Inc. is using Blank______ to measure consumer responses.
interval scale
Systematic random sampling is frequently used because
it is a relatively easy way to draw a sample while ensuring randomness
Single-item scale
it is a scale format that collects data about only one attribute of an object or construct
Comparative rating scale
it is a scale format that requires a judgment contrasting one object, person, or concept against another on the scale.
Noncomparative rating scale
it is a scale format that requires a judgment without reference to another object, person, or concept.
Frequency distribution
it is a summary of the number of times each possible response to a scale was recorded by the total group of respondents.
Convergent validity
it is assessed with multi-item scales and represents a condition in which the multiple items assessing one construct share a high proportion of variance.
Mean
it is the arithmetic average of all the information responses.
Discriminant validity
it is the extent to which one construct differs from other constructs and represents a unique construct.
Mean
it is the most appropriate measure for interval and ratio scales
Estimated standard deviation
it is the most appropriate measure for interval and ratio scales.
Frequency distribution
it is the most appropriate measure for nominal scales.
Mode
it is the most appropriate measure for nominal scales.
Median
it is the most appropriate measure for ordinal scales
range
it is the most appropriate measure for ordinal scales.
Mode
it is the most frequently occurring value given among all of the responses.
Median
it is the sample statistic that splits the information so that half the data are above the statistic value and half are below.
Standard deviation
it is the statistical value that specifies the extent of variation in the responses.
Range
it shows the distance between the largest and smallest response
A nonprobability sampling method in which participants are selected according to a researcher's belief that they will meet the requirements of a study are called
judgment sampling
The selection of sampling units in nonprobability sampling is based on the
knowledge or intuitive judgment of a researcher
A question that introduces bias and often influences the way a respondent answers a question is called a
leading question
Marlene, a researcher, asks the following question to consumers: Most technology reviewers believe that CellCall is the best product on the market. Do you agree? 1. Agree 2. Neutral 3. Disagree In this scenario, this question is a
leading question
Li, a researcher, is trying to collect data regarding adolescent behavior in schools using a questionnaire. The scale points in the measurement instrument are as follows: 5, Strongly Disagree; 4, Disagree; 3, Neither Agree Nor Disagree; 2, Agree; 1, Strongly Agree. In this scenario, Li is using a
likert scale
measures of central tendency
locate the center of a distribution of responses and are basic summary statistics.
Reliability is a
measure of a measurement's consistency
In comparison to single-item scales, multiple-item scales are generally
more reliable and valid
Identify the formula used to estimate the sample size for a simple random sample when the situation involves estimating a population mean
n = (Z2B,CL)�2�,CL (σ2e2)
is the most basic and least powerful scale design in which the questions require respondents to provide only some type of descriptor as the raw response.
nominal scale
Sampling designs in which the probability of selection of each sampling unit is not known are called
nonprobability sampling
method, consideration is given to the relative size of the stratum as well as the variability within the stratum to determine the necessary sample size of each stratum.
optimal allocation sampling
All scale measurements can be classified as one of four basic scales levels:
ordinal, nominal, interval, ratio
In Blank______, each sampling unit in the defined target population has a known possibility of being selected for the sample
probability sampling
Structure Data is also defined as
quantitative data.
Research panel samples are most often considered
quota sampling
Scales that allow respondents to compare their own responses by indicating their first, second, third, and fourth preferences, and so forth are called
rank order scale
A scale that allows a researcher to identify the absolute differences between each scale point and also to make comparisons between the responses is called
ratio scale
Which of the following scales is designed to allow a "true natural zero" or "true state of nothing" response as a valid response to a question
ratio scale
Sampling
refers to the selection of a small number of elements from a larger defined target group of elements and expecting that the information gathered from the small group will allow judgments to be made about the larger group.
Forced-choice scales
researchers believe that mental attitudes almost always have a degree of a positive or negative orientation.
Free-choice scales
respondents are provided with an easy way to express their feelings.
Any type of bias that is attributable to mistakes in either drawing a sample or determining the sample size is called
sampling error
The blueprint or framework needed to ensure that the data collected are representative of the defined target population is called
sampling plan
Scale measurement assigns designated degrees of intensity to responses in a given questioning or observation method. The degrees of intensity are commonly known as
scale points
The extent to which a scale can reproduce the same or similar measurement results in repeated trials is called
scale reliability
Unlike stratified random sampling, the sampling units in cluster sampling are
segregated into mutually exclusive and collectively exhaustive subpopulations
A unique bipolar ordinal scale format that captures a person's attitudes or feelings about a given object is called a Blank
semantic differential scale
A marketing researcher wants to draw a sample of 30 participants out of the 100 potential participants who are present. The researcher writes each participant's name on a separate, identical piece of paper and places all the names in a bowl. She then proceeds to pick names arbitrarily until she picks 30 participants. The scenario given above is an example of
simple random sampling
A probability sampling procedure in which every sampling unit has a known and equal chance of being selected is called Blank
simple random sampling
Central Limit Theorem
states that the sampling distribution derived from a simple random sample will be approximately normally distributed
a defined target population is ordered in some way, usually in the form of a taxpayer roll, customer list, or membership roster, and selected systematically
systematic random sampling
Researchers develop two similar yet different scale measurements for a given construct and administer both forms to either the same sample of respondents or two samples of respondents from the same defined target population in
the equivalent form technique for measuring scale reliability
An inherent limitation of quota sampling is that
the success of a study is dependent on subjective decisions made by researchers
Random sampling error occurs because
there can be chance variations in the selection of sampling units
Random sampling error occurs because Blank
there can be chance variations in the selection of sampling units
Identify a true statement about rank-order scale
they can only produce ordinal data
Scale responses must be mutually exclusive and nonoverlapping.
true
does not have values associated with it, and cannot be processed and analyzed using conventional statistical tools and methods
unstructured data
does not have values associated with it, and cannot be processed and analyzed using conventional statistical tools and methods.
unstructured data
How do you extract value
unstructured data needs to be converted into structured data.
