Exam 2 Flashcards

Marketing 310 with Kasieta at University of Wisconsin - Madison

About this deck

By: Makenzie Blazich
Created: 2011-03-28
Size: 100 flashcards
Views: 46

About StudyBlue

STUDYBLUE makes things that make you better at school. Things like online flashcards with photos and audio. Things like personalized quizzes and friendly reminders about when (and what) to study next. Think of it as a digital backpack™: access to all of your study materials online and on your phone. STUDYBLUE exists to make studying efficient and effective for every student, for free. Join us.

“Simply amazing. The flash cards are smooth, there are many different types of studying tools, and there is a great search engine. I praise you on the awesomeness.”
Dennis

Sign up (free) to study this.

Three factors to determine if research design is descriptive

(1) nature of the initial decision problem/opportunity, (2) the set of research questions, (3) the research objectives

Nature of initial decision problem/opportunity in a descriptive design must be one of these two things

Describe specific characteristics of existing mkt situations or evaluate current marketing strategies

Types of questions descriptive research asks

Who what where when why

Research objectives of descriptive research

Identify meaningful relationships or verify validity of relationships

Two basic approaches to collecting primary data

Observation and asking questions

Variable

Observatble, measurable element or attribute of an object

Construct

Unobservable, abstract concept that is measured indirectly by a group of related variables (i.e. service quality, value, customer satisfaction)

Relationships

Associations between variables and constructs

Null hypothesis states that?

There is no relationship between the variables or that it is random

Alternative hypothesis states that?

There is a relationship between the two variables that is signifcant

Sampling error

The statistically measured difference between actual sampled results and the estimated true population results

Nonsampling error

A type of bias that occurs in a research study regardless of whether sample or census is used (respondent errors, measurement/questionnaire design errors, faulty or incorrect problem definition, and project administration errors)

Two types of respondent errors

Nonresponse errors and response errors

Nonresponse error

Systematic bias that occurs when the final sample differs from planned sample (i.e. not home, wrong address, refusal)

Two types of response error

Deliberate falsification & unconscious misrepresentation

Faulty recall

Inability of a person to accurately remember specifics about behavior under investigation

Averaging

Assuming the norm behavior or belief to be reality

Construct development error

Type of nonsampling (systematic) error that is created when researcher is not careful in fully identifying the concepts and constructs to be included in the study

Survey instrument error

Type of error that occurs when the survey instrument induces some type of systematic (nonsampling) bias in response

Interpretive bias

Wrong inference about the real world or defined target population is made by researcher or decision-maker due to some type of extraneous factor

Unconscious misrepresentation occurs when?

Interviewers induce a pattern of responses that does not represent the target population

Sampling frame error

Occurs when an incomplete or inaccurate sampling frame is used (classic example is using a phone book for phone surveys; lots of people aren't listed)

CATI stands for?

Computer-assisted telephone interview

CATS stands for?

Completely automated telephone survey

Four advantages of person-administered surveys

Adaptability, rapport, feedback, quality of responses

Four disadvantages of person-administered surveys

Speed of data acquisition, possible recording error, interviewer-respondent interaction error, high expense

Plus-one dialing

Method of generating telephone numbers to be called by choosing numbers randomly selected from a telephone directory and adding one digit (i.e. 555-4321 becomes 555-4322)

Systematic random digit dialing

Technique of randomly dialing telephone numbers, but only numbers that meet specific criteria (with a "skip" number)

Random digit dialing

Truly random selection of phone numbers

Propensity scoring

Weighting underrepresented respondents more heavily in results; used to adjust results to look more like those a representative sample would have produced

Task difficulty

How hard respondents need to work to supply a response

Topic sensitivity

The degree to which a survey question leads the respondent to give a socially acceptable response (e.g. income, racial issues, politics, personal hygiene, etc.)

Incidence rate

Percentage of the general population that is the subject of the market research

Probability sampling

Each sampling unit has a known probability of being included in the sample

Nonprobability sampling

Sampling process where the probability of selecting each sampling unit is unknown (so therefore sampling error is unknown)

Four types of probability sampling methods

Simple random sampling, systematic random sampling, stratified random sampling, cluster sampling

Four types of nonprobability sampling methods

Convenience sampling, judgment sampling, quota sampling, snowball sampling

Simple random sampling

Ensures every sampling unit in the target population has a known and equal chance of being selected (probability = size of sample / size of population)

Systematic random sampling

Sampling technique that requires defined target population to be ordered in some way; uses a skip interval (interval = defined target population size / desired sample size)

Stratified random sampling

Target population is divided into groups (strata) and samples are selected from each. Two types are proportionate and disproportionate

Cluster sampling

Probability sampling technique in which sampling units are divided into mutually exclusive and collectively exhaustive subpopulations, called clusters (e.g. customers at a store on some given day, people at a matinee for a movie)

Area sampling

Clusters are formed by geographic designations

Convenience sampling

Nonprobability sampling method in which samples are drawn at convenience of researcher

Judgment sampling

Nonprobability sampling method in which participants are selected according to an experienced individual's belief they will meet study requirements (i.e. sales director surveys salespeople instead of customers)

Quota sampling

Nonprobability sampling method in which participants are selected accoridng to prespecified quotas regarding demographics, attitudes, behavior, or something else (i.e. "we want x people under 25 to be surveyed")

Snowball sampling

Nonprobability sampling method in hich respondents are chose and they help the researcher identify additional people to be included in the study

Seven critical factors in selecting appropriate sampling design

Research objectives, degree of accuracy, resources, time frame, knowledge of target population, scope of research, statistical analysis

Sampling plan

Blueprint or framework needed to ensure that the data collected are representative of the defined target population

Steps in developing a sampling plan (7)

Define target population, select data collection method, identify sampling frame(s) needed, select appropriate sampling method, determine necessary sample sizes and overall contact rates, create an operating plan for selecting sampling units, execute plan

Domain of observables

Set of identifiable and measurable components associated with an abstract construct

Concrete features vs. abstract constructs

Plane: concrete = number of engines, seating capacity; abstract = quality of in-flight service ? brand loyalty: concrete = number of times brand is purchased; abstract = overall attitude toward brand)

Content validity

Subjective yet systematic assessment of how well a construct's measurable components represent that constuct

Convergent validity

When the researcher's measures of a construct are highly correlated with known existing measures of the same construct

Discriminant validity

Existence of a negative correlation between measurement of one construct and those measures of another construct

Nomological validity

Assessment of how well one constuct theoretically fits within a network of other established constucts that are related but different

Direct cognitive structural analysis

Data analysis technique that assesses how well identifiable attributes of a construct reflect that construct and their importance to it

Operationalization

When reserachers explain a construct's meaning in measurement terms by specifying activities or operations necessary to measure it

State-of-being data

Verifiable facts. The physical and/or demographic or socioeconomic characteristics of people, objects, and organizations

State-of-mind data

Mental thoughts or emotional feelings of people

State-of-behavior data

Past and current behaviors. Person or organization's current observable or recorded actions or reactions

State-of-intention data

Planned future behaviors

Four scaling properties

Assignment, order, distance, origin

Assignment property

Use of unique descriptors to identify an object in a set (i.e. use of jersey numbers to label sports teams)

Order property

Establishes "relative magnitudes" among descriptors that can be ranked (i.e. 1st place is better than 4th place)

Distance property

Enables researcher or respondent to identify, understand, and accurately express absolute (or assumed) differences between objects (i.e. differences in income ranges or age categories)

Origin property

Scale descriptor that is designated a unique starting point or as being a "true natural zero" or "true state of nothing" (i.e. number of times a person shops at a store, age, weight)

Nominal scales

Only need to give some type of descriptor as response (i.e. married, single, divorced, etc.)

Ordinal scales

Have assignment and ranking properties (i.e. "please rank the following in terms of how important they are to you?")

Interval scales

Measures absolute differences between each scale point (i.e. "please rank each of the following brands on a 1-7 scale")

Ratio scales

Like interval scales except can make comparisons between responses (i.e. "in a typical year, how many miles do you drive in your car and in your truck?")

Intelligibility criterion

Degree to which the questions on a scale are understood by the respondents

Discriminatory power

Scale's ability to significantly differentiate between the responses

Internal consistency

Degree to which vairous dimensions of a multidimensional construct correlate with the scale (?)

Forced-choice scale

No neutral response category

Free-choice scale

Includes a neutral response category

Three components of attitudes

Cognitive, affective, and behavioral (conative)

Cognitive component of attitude

Represents beliefs, perceptions, and knowledge about a specified object (i.e. we believe the UW is a prestigious place to get a degree)

Affective component of attitude

Person's emotional feelings toward given object (i.e. we love the UW)

Behavioral (conative) component of attitude

Represents a person's intended or actual behavioral response to a given object (i.e. we recommend the UW to high school students)

Likert scale

Asks to what extent people agree or disagree with a series of statements about an object

Semantic differential scale

Bipolar scale format that captures attitudes about an object (i.e. rating Tiger Woods - haha)

Halo effect bias

Generalization from perception of one outstanding factor, attribute, or trait to an overly favorable evaluation on the whole object or construct

Behavior intention scale

Type of rating scale designed to caputre the likelihood that people will demonstrate some type of predictable behavior intent toward purchasing an object or service in a future time frame

Noncomparative rating scales

Scale format that requires a judgment without reference to another object, person, or concept

Comparative rating scale

A scale format that requires a judgment comparing one object, person, or concept against another

Graphic rating scales

Use a scaling descriptor format that prsents respondents with a graphic continuum (the smiley faces)

Paired-comparison scales

Pick which of paired attributes is most important

Constant sum scales

When respondents allocate certain number of "points" (100, usually) to what's most important

Formative composite scale

Uses several individual scale items to measure different parts of the whole object or construct

Reflective composite scale

A scale format that uses multiple scale items to member one component of an object or construct

Flowerpot approach

Questionnaire design that integrates measurements into a logical, smooth-flowing order

Questionnaire design precision

Extent to which questionnaire can produce similar results over repeated usages

Ten guidelines for developing cover letters

(1) personalization (2) identificaiton of org (3) clear statement of importance and purpose (4) anonymity and confidentiality (5) general time frame of study (6) reinforcement of importance of participation (7) acknowledgment of reasons for nonparticipation in study (8) time requirements and compensation (9) completion date and where/how to return survey (10) advance thank-you

Lottery incentive approach

Incentive money forms signifcantly larger dollar amount and everyone who completes and returns the survey has a chance of receiving the incentive

Screening forms

Determine eligibility

Data validation

Determining whether survey's interviews were conducted correctly and are free of bias

Curbstoning

Cheating in data collection process

Five areas of data validation

Fraud, screening, procedure, completeness, courtesy

Coding

Grouping and assigning value to various responses from survey

Cross-tabulation

Simultaneously treating two or more variables in the study (i.e. people who are over age 55 and also attended x APT shows in the last x years)

About this deck

By: Makenzie Blazich
Created: 2011-03-28
Size: 100 flashcards
Views: 46

About StudyBlue

“Simply amazing. The flash cards are smooth, there are many different types of studying tools, and there is a great search engine. I praise you on the awesomeness.”
Dennis