Marketing 412 test 2
inductive (qual) - used to generate new theory
deductive (quan) - test existing theories
comparative rating scales
A scale format that requires a judgment comparing one object, person, or concept against another on the scale Ex. Rank-order scales, Constant-sum scales
noncomparative rating scales
A scale format that requires a judgment without reference to another object, person, or concept Ex. Graphic rating scale The pain rating scale at the doctors office
quotas
A tracking system that collects data from respondents and helps ensure that subgroups are represented in the sample as specified
cluster sampling
A probability sampling method in which the sampling units are divided into mutually exclusive and collectively exhaustive subpopulations called clusters* *Each cluster is assumed to be representative of the heterogeneity of the population
Considerations in Questionnaire Design
1) Confirm the research objectives before starting to design the questionnaire. 2) Determine data requirements to compute each research objective. 3) The introduction section should include a general description of the study. 4) Instructions should be clearly expressed. 5) Questions and scale measurements should follow a logical order, that is, one that appears logical to the respondent rather than to the researcher or practitioner. 6) Begin an interview or questionnaire with simple questions that are easy to answer, and then gradually lead up to the more difficult questions. Use general-to-specific questions and topic sequence. 7) Ask personal questions at the end of the survey. 8) Place questions that involve personal opinions, attitudes, and beliefs towards the end of the interview or survey, but before demographics. 9) Avoid asking questions using a different measurement format in the same section of the questionnaire. 10) End the survey with a thank-you statement.
There are two approaches that are used to obtain data to assess validity:
1) If sufficient resources are available, a pilot study with 100 to 200 respondents believed to be representative of the defined target population 2) When fewer resources are available, researchers asses only content validity using a panel of experts
simple random sampling
A probability sampling procedure in which every sampling unit has a known and equal chance of being selected Advantages × Technique is easily understood × Results can be generalized to the defined target population with a prespecified margin of error × Provide unbiased estimates of the population's characteristics Disadvantages × Difficulty of obtaining a complete and accurate listing of the target population elements
probablility sample sizes
1) The population variance, which is a measure of the dispersion of the population, and its square root, referred to as the population standard deviation. The greater the variability in the data being estimated, the larger the sample size needed. 2) The level of confidence desired in the evidence. Confidence is the certainty that the true value of what we are estimating falls within the precision range we have selected. 3) The degree of precision desired in estimating the population characteristic. Precision is the acceptable amount of error in the sample estimate.
call records
A recording document that gathers basic summary information about an interviewer's performance efficiency (e.g. number of contact attempts, number of completed interviews, length of time of interview)
Step 4: Determine Layout & Evaluate Questionnaire In a good questionnaire design, questions flow from general to more specific information, and end with demographic data. 1) Introductory section: Gives the respondent an overview of the research
3) Demographic questions section: The last section of the questionnaire that focuses on the demographic questions (age, sex, income level, educational attainment, location, Questionnaires should be designed to eliminate, or at least minimize, response order bias.
common methods variance (CMV)
A biased variance that results from the measurement method used in a questionnaire
pretest
A descriptive research activity representing a small-scale investigation of 5 - 40 subjects that are representative of the main study's defined target population but focus on a specific sub-component of the main study. × Results are intended only to assist researchers in designing or executing a particular subcomponent of a larger study (or experiment) × While researchers do conduct pretests in the development of a pilot study, pretests are more associated with exploratory and causal experimental research designs
code sheet
A document that lists the different themes or categories for a particular study
area sampling
A form of cluster sampling in which the clusters are formed by geographic designations
supervisor instruction form
A form that serves as a blueprint for training people on how to execute the interviewing process in a standardized fashion; it outlines the process by which to conduct a study that uses personal and telephone interviews
questinnaire
A formal framework consisting of a set of questions and scales designed to generate primary raw data
judgment sampling (aka purposive sampling)
A nonprobability sampling method in which participants are selected according to an experienced individual's belief that they will meet the requirements of the study Ex. P&G may select a sample of key accounts to obtain information about consumption patterns and changes in demand for selected products, for example, Crest toothpaste or Cheer laundry detergent Sales representatives may be interviewed rather than customers to determine whether customers' wants and needs are changing or to assess the firm's product or service performance Advantages × If the judgment of the researcher is correct, the sample generated by judgment sampling will be better than one generated by convenience sampling × Disadvantages × Representativeness of the sample cannot be measured × Generalizability is limited
quota sampling
A nonprobability sampling method in which participants are selected according to prespecified quotas regarding demographics, attitudes, behaviors, or some other criteria Advantages × The sample contains specific subgroups in the proportions desired by researchers × Reduces selection bias by field workers Disadvantages × Success of the study is dependent on subjective decisions made by researchers × Representativeness of the sample cannot be measured × Generalizability beyond the sampled respondents is questionable
convenience samplign
A nonprobability sampling method in which samples are drawn at the convenience of the researcher Ex. Mall-intercept Undergraduate student sample Advantages × Enables a large amount of respondents to be interviewed in a relatively short time Disadvantages × Data is not generalizable to the defined target population × Representativeness of the sample cannot be measured because sampling error estimates cannot be calculated
snowball sampling (referral sampling)
A nonprobability sampling method, also called referral sampling, in which a set of respondents is chosen, and they help the researcher identify additional people to be included in the study Advantages × Good for identifying respondents who are members of small, hard-to-reach, uniquely defined target populations × Particularly useful in qualitative research Disadvantages × Allows bias to enter the study - there may be significant differences between people who are known in a certain social circle and those who are not × Generalizability is limited
ordinal scales
A scale that allows a respondent to express relative magnitude between the answers to a question x More powerful than nominal scales x Enables respondents to express relative magnitude (therefore the answers can be rank-ordered in a hierarchical pattern) x Cannot be used to determine the absolute difference between rankings x Statistics available: mode, median, frequency distributions, ranges
ratio scale
A scale that allows the researcher not only to identify the absolute differences between each scale point but also to make comparisons between the responses x Highest level scale x Designed to enable a "true natural zero" responses to be a valid response to a question x Asks respondents to provide a specific numerical value to their response x Statistics available: mode, median, mean, standard deviation, comparisons between levels
interval scale
A scale that demonstrates absolute differences between each scale point x Intervals between the scale numbers tell us how far apart the measured objects are on a particular attribute x Allows us to compare across options x Statistics available: mode, median, mean, standard deviation
forced choice scale
A scale that does not have a neutral descriptor to divide the positive and negative answers Ex. Purchase Intention (Not Buy - Buy) __ Definitely will buy __ Probably will not buy __ Probably will buy __ Definitely will buy
nonforced (free-choice) scale
A scale that includes a center neutral response Ex. Purchase Intention (Not Buy - Buy)
cover letter
A separate written communication to a prospective respondent designed to enhance that person's willingness to complete and return the survey in a timely manner
double negative question
A situation where the question/setup contains two negative thoughts in the same question
loaded question
A situation where the question/setup suggests a socially desirable answer or involves an emotionally charged issue
pilot study
A small-scale version of the intended main research study, including all the components that make up the main study, including data collection and analysis from 50 - 100 respondents that have representation of the main study's defined target population
pilot study
A small-scale version of the intended main research study, including all the components that make up the main study, including data collection and analysis from 50 - 100 respondents that have representation of the main study's defined target population. × Serves as a guide for conducting a larger study × Employed to examine specific subcomponents to see if the selected procedures work as expected or if refinements are needed × While pilot studies can be included in any form of research, they are most often associated with empirical descriptive or predictive quantitative research studies
behavioral intention scale
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 × The objective of this type of scale is to assess the likelihood that people will behave in some way regarding a product or service × To make scale points more specific, researchers can use descriptors that indicate the percentage change that they will buy a product (or engage in a behavior of interest
proportionately
A stratified sampling method in which each stratum is dependent on its size relative to the population 2/3 of the target population is 18-24 1/3 is 25-30
disproportionately
A stratified sampling method in which the size of each stratum is independent of its relative size in the population Large segment of manufacturers with fewer than 10 employees and a very small segment with more than 500; but economic importance of the firms with 500 or more dictates taking a larger sample size from this stratum than the proportionality method would indicate
semantic differential scale
A unique bipolar ordinal scale format that captures a person's attitudes or feelings about a given object × Bipolar adjectives (ex. good/bad, like/dislike, competitive/noncompetitive, helpful/unhelpful, high quality/low quality, dependable/undependable) × Only the endpoints of the scale are labeled × In most cases, semantic differential scales use either 5 or 7 scale points
Advantages/disadvantages
Advantages × Assurance of representativeness in the sample × Opportunity to study each stratum and make comparisons between strata × Ability to make estimates for the target population with the expectation of greater precision and less error Disadvantages × Difficulty in determining the basis for stratifying × Inclusion of irrelevant strata can waste time and money
advantages/disadvantages
Advantages × Cost-effective and easy to implement (often the only representative sampling frame available to researchers is one based on clusters) Disadvantages × Clusters are often homogeneous (the more homogeneous the cluster, the less precise the sample estimates) × Appropriateness of the designated cluster factor used to identify sampling units within clusters
negatively worded statements
Although scale development guidelines traditionally suggest that negatively worded statements should be included to verify that respondents are paying attention, it has been found that negatively worded statements create problems for respondents in data collection.
construct development
An integrative process in which researchers determine what specific data should be collected for solving the defined research problem
measurement
An integrative process of determining the intensity (or amount) of information about constructs, concepts, or objects The measurement process 1) Construct selection/development 2) Scale measurement
likert scale
An ordinal scale format that asks respondents to indicate the extent to which they agree or disagree with a series of mental belief or behavioral belief statements about a given object × Usually the scale format is balanced × The scale originally had five scale descriptors, but today it is often expanded to seven scale descriptors so that it can be treated as an interval scale × Best used for survey designs that use self-administered surveys, personal interviews, or online surveys
bad questions
Any questions that prevent or distort the fundamental communication between the researcher and the respondents
constant-sum scale
Below is a list of seven banking features. Allocate 100 points among the features. Your allocation should represent the importance of each feature has to you in selecting your bank. The more points you assign to a feature, the more importance that feature has in your selection process. If the feature is "not at all important" in your process, you should not assign it any points. When you have finished, double-check to make sure your total adds to 100.
structured questions
Closed-ended questions that require the respondent to choose from a predetermined set of responses or scale points
Step 7: Implement the Survey
Collecting the data using the agreed-upon survey questionnaire. Ex. Self-administered questionnaires must be distributed to respondents using methods to increase response rates With Internet surveys, the format, sequence, skip patterns, and instructions must be thoroughly checked after the questionnaire is uploaded to the web
concrete vs. abstract
Consumer: Concrete properties: age, sex, marital status, income, brand last purchased, dollar amount of purchase, types of products purchased, color of eyes and hair Abstract properties: attitudes toward a product, brand loyalty, high-involvement purchases, emotions (love, fear anxiety), intelligence, personality organization: Concrete properties: name of company, number of employees, number of locations, total assets, Fortune 500 rating, computer capacity, types and numbers of products and service offerings Abstract properties: competence of employees, quality control, channel power, competitive advantages, company image, consumer-oriented practices
measures of dispersion
Describe how the data are dispersed around a central value. These statistics enable the researcher to report the variability of responses on a particular scale. × Frequency distribution × Range
scale points
Designated degrees of intensity assigned to the responses in a given questioning or observation method Ex. definitely important, moderately important, slightly important, not at all important All scale measurements can be classified as one of four basic scale levels: 1) Nominal 2) Ordinal 3) Interval 4) Ratio
nonprobability sample sizes
Determining the sample size for nonprobability samples is usually a subjective, intuitive judgment made by the researcher based on either past studies, industry standards, or the amount of resources available. Regardless of the method, the sampling results cannot be used to make statistical inferences about the true population parameters. Steps in developing a sampling plan Step 1: Define the Target Population Step 2: Select the Data Collection Method Step 3: Identify the Sampling Frame(s) Needed Step 4: Select the Appropriate Sampling Method Step 5: Determine Necessary Sampling Sizes and Overall Contact Rates Step 6: Create an Operating Plan for Selecting Sampling Units Step 7: Execute the Operational Plan
You are estimating the average annual income for the large population of those who subscribe to a particular magazine. You want to be 95% confident that your estimate is within ± $500 from the true value. A previous sample found the sample standard deviation to be $6,000.
Finding Z: First use the normal distribution table to get the z-value using 95% confidence. Divide .95 by 2, and work backwards in the normal distribution table to find the z-value corresponding to that probability. .95/2 = .4750. The z-value corresponding to that probability is 1.96. Finding σ: Even though we don't know the population standard deviation (σ), we do have an estimate from a previous sample ---- the sample standard deviation (s), which is $6,000 Finding e: You want the sample mean to be within ± $500 from the population mean, so e = $500. Therefore, n = (1.96)^2 × ((6,000)^2 /(500)^2) = 553.19 In order to be 95% confident that the sample mean income is within ± $500 from the population mean income, your representative sample taken from the large population needs to include approximately 553 subscribers.
unbalanced scale
Has a larger number of response options on one side, either positive or negative Ex. Based on your experiences with your new vehicle since owning and driving it, to what extent are you presently satisfied or dissatisfied with the overall performance of the vehicle? Please check only one response.
balanced scale
Has an equal number of positive (favorable) and negative (unfavorable) response alternatives Ex. Based on your experiences with your new vehicle since owning and driving it, to what extent are you presently satisfied or dissatisfied with the overall performance of the vehicle? Please check only one response. Completely sat --> completely dissa
sensitive questions
Include income, sexual beliefs or behaviors, medical conditions, financial difficulties, alcohol consumption, and so forth that respondents are likely to respond to incorrectly
double-barred questions
Includes two or more different attributes or issues in the same question
leading question
Introduces bias and often influences the way a respondent answers a question
ambiguous questions
Involves a situation in which possible responses can be interpreted a number of different ways
measures of central tendency
Locate the center of a distribution of responses and are basic summary statistics. Mean, median, and mode measure central tendency using different criteria.
Determining The Sample Size For Estimating A Population proportion We are estimating the percentage of taxpayers who are in favor of a particular tax-related piece of legislation. We want to be 98% sure that our estimate is within ± 3% from the true population value. What should be the number of taxpayers included in our representative sample?
N (population size) = 10,000,000 and we have no prior knowledge as to what the actual population percentage might be First find the z-value for 98% confidence. Divide .98 by 2, and work backwards in the normal distribution table to find the closest z-value for that probability (.98/2 = .4900 - the z-value for that probability is 2.33). When you have no prior knowledge as to what the actual population percentage might be, use P = .5 and thus (1-P) = (1 - .5). This guarantees that you don't artificially take too small a sample, because any other value between 0 and 1 chosen for P will make the sample size smaller. e = .03, because we want our estimate (Ps) to be within ± .03 (3%) from the true population value (P) Therefore, n = ((2.33)^2× (.5) × (1-.5))/ (.03)^2 = 1,508 The number of taxpayers needed to be sampled is 1,508.
response order bias
Occurs when the order of the questions, or of the closed-ended responses to a particular question, influences the answer given
unstructured questions
Open-ended questions formatted to allow respondents to reply in their own words
categorization
Placing portions of transcripts into similar groups based on their content
Step 6: Pretest, Revise, & Finalize Questionnaire
Pretest: A descriptive research activity representing a small-scale investigation of 5-40 subjects that are representative of the main study's defined target population but focus on a specific sub-component of the main study.
Step 1: data reduction
The categorization and coding of data that is part of the theory development process in qualitative data analysis
nonprobablity sampling
Sampling designs in which the probability of selection of each sampling unit is not known The selection of sampling units is based on the judgment of the researcher and may or may not be representative of the target population Convenience sampling Judgment sampling Quota sampling Snowball sampling
mutually exclusive
Scale responses should not overlap - using response choices that overlap with other response choices creates confusion in the respondent's choice
stratified random sampling
Separation of the target population into different groups, called strata, and the selection of samples from each stratum 1. Dividing the target population into homogenous subgroups or strata. 2. Drawing random samples from each stratum. 3. Combining the samples from each stratum into a single sample of the target population.
systematic random sampling
Similar to simple random sampling but the defined target population is ordered in some way, usually in the form of a customer list, taxpayer roll, or member roster, and selected systematically Skip interval = Defined target population list size/ Desired sample size Advantages × Availability of lists and the shorter time required to draw a sample versus simple random sampling makes it an attractive, economical method Disadvantages × Possibility of hidden patterns in the list of names that can create bias × The number of sampling units in the population must be known
complex questions
Situations in which the question is worded in a way the respondent is not sure how they are supposed to respond
interviewer instructions
Used to train interviewers how to select prospective respondents, screen them for eligibility, and conduct the actual interview
Questionnaire design
Step 1: Confirm Research Objectives Step 2: Select Appropriate Data Collection Method Step 3: Develop Questions and Scaling Step 4: Determine Layout and Evaluate Questionnaire Step 5: Obtain Initial Client Approval Step 6: Pretest, Revise, and Finalize Questionnaire Step 7: Implement the Survey
Step 3: Develop Questions & Scaling Questionnaire design is systematic and includes a series of logical activities. Researchers select the appropriate scales and design the questionnaire format to meet the data requirements.
Step 3: Develop Questions & Scaling Questionnaire design is systematic and includes a series of logical activities. Researchers select the appropriate scales and design the questionnaire format to meet the data requirements.
skip questions
Used if the next question (or set of questions) should be responded to only by respondents who meet a previous condition
scale measurement
The process of assigning descriptors* to represent the range of possible responses to a question about a particular object or construct *Scale descriptors are a combination of labels such as "Strongly Agree" or "Strongly Disagree" and numbers, such as 1 to 7
discriminatory power
The scale's ability to discriminate between the categorical scale responses (points) Researchers must decide how many scale points are necessary to represent the relative magnitudes of a response scale. The more scale points, the greater the discriminatory power of the scale.
nominal scale
The type of scale in which the questions require respondents to provide only some type of description as the new response x Most basic and least powerful design x Responses do not contain a level of intensity (therefore, ranking of the set of responses is not possible) x Nominal scales allow the researcher only to categorize the responses into mutually exclusive subsets that do not have distances between them x Statistics available: simple counts, mode Example 1: Please indicate your marital status. __ Married __ Single __ Separated __ Divorced __ Widowed Example 2: Do you like or dislike chocolate ice cream? __ Like __ Dislike Example 3: Which of the following supermarkets have you shopped at in the past 30 days? Please check all that apply. __ Albertson's __ Winn-Dixie __ Publix __ Safeway __ Wal-Mart
rank-order scale
Thinking about the different types of music, please rank your top three preferences of types of music you enjoy listening to by writing in your first choice, second choice, and third choice on the lines provided below. First preference: Second preference: Third preference:
sampling from a small pop
When working with small populations, the use of the earlier formulas may lead to unnecessarily large sample size. The calculated sample size should be multiplied by the following correction factor: N/(N + n - 1)
codes
Words (labels) or numbers that are used to track categories in a qualitative study
scale validity
assesses whether a scale measures what it is supposed to measure x Measure of accuracy in measurement x Validation involves determining the suitability of the questions (statements) chosen to represent the construct
Step 2: Select Appropriate Data Collection Method To select the data collection method, the researcher first must determine the data requirements to achieve each of the objectives as well as the type of respondent demographic information required. The data requirements and the flow for the American Bank study:
banking services, lifestyle dimensions, banking relationships and demographic characteristics
content validity
is a measure of the extent to which a construct represents all relevant dimensions
face validity
is based on a researcher's intuitive evaluation of whether the statements look like they measure what they are supposed to measure
convergent validity
is evaluated with multi-item scales and represents a situation in which the multiple items measuring the same construct share a high proportion of variance
discriminant validity
is the extent to which a single construct differs from other constructs and represents a unique construct
population proportion
n = (z^2) x ((P x Q)/e^2) ZB,CL= The standardized z-value associated with the level of confidence P = Estimate of the population proportion having a desired characteristic based on intuition or prior information Q = [1-P] or the estimate of expected population proportion not holding the characteristic of interest e = Acceptable tolerance level of error (stated in percentage points)
population mean
n = (z^2) x (σ^2 / e^2) ZB,CL= The standardized z-value associated with the level of confidence σμ = Estimate of the population standard deviation (σ) based on some type of prior information e = Acceptable tolerance level of error
scale reliability
refers to the extent to which a scale can reproduce the same or similar measurement results in repeated trials x Measure of consistency in measurement x Random error produces inconsistency in scale measurements that leads to lower scale reliability x Researchers can improve scale reliability by carefully designing scaled questions x Techniques that help researchers assess the reliability of scales: x Test-retest x Equivalent form x Internal consistency reliability: split-half tests and coefficient (Cronbach's) alpha α
what is a construct?
× An abstract idea of concept formed in a person's mind × An unobservable concept this measured indirectly be a group of related variables × A hypothetical variable made up of a set of component responses or behaviors that are thought of as related × A combination of a number of similar characteristics Ex. Customer Interaction (7-point scale, where 1 = Strongly Disagree and 7 = Strongly Agree) This customer was easy to talk with. This customer genuinely enjoyed my helping her/him. This customer likes to talk to people. This customer was interested in socializing. This customer was friendly. This customer tried to establish a personal relationship. This customer seemed interested in me, not only as a salesperson, but also as a person.
descriptive ques
× Descriptive research designs use questionnaires to collect data that can be turned into knowledge about a person, object, or issue
predictive
× Predictive survey questionnaires require the researcher to collect a wider range of data than can be used in predicting changes in attitudes and behaviors as well as testing hypotheses
Nature of Qualitative data analysis
× Some researchers criticize qualitative research as "soft," lacking rigor, and being inferior - but as we have seen, measurement and statistical analysis do not ensure that research is useful or accurate. × When the purpose of a research project is to better understand psychoanalytical or cultural phenomena, quantitative research may not offer a great deal of insight or depth. For these topics, qualitative research and analysis is often superior to quantitative research in providing useful knowledge for decision makers.
