• Shuffle
    Toggle On
    Toggle Off
  • Alphabetize
    Toggle On
    Toggle Off
  • Front First
    Toggle On
    Toggle Off
  • Both Sides
    Toggle On
    Toggle Off
  • Read
    Toggle On
    Toggle Off
Reading...
Front

Card Range To Study

through

image

Play button

image

Play button

image

Progress

1/175

Click to flip

Use LEFT and RIGHT arrow keys to navigate between flashcards;

Use UP and DOWN arrow keys to flip the card;

H to show hint;

A reads text to speech;

175 Cards in this Set

  • Front
  • Back
objective phenomena
those that are directly observable
subjective phenomena
those that can be known only be respondents, themselves
response
=attitude+other constructs+method bias+random error
random error
results due to temporary aspects of the person or measurement situation and which affects the measurement in irregular ways (mood, state of leath, fatigue, situation in which measure is taken, ambiguity of question wording
cognitive steps in answering questions
1) understand question
2) search memory for information
3) integrate information into summary judgement
4) map judgment onto response alternatives
difference between weak and strong satisficing (aiming to achieve only an adequate level of decision making)
weak satisficing: people go through steps really quickly
strong satisficing: people skip steps 2 & 3 all together (in cognitive steps mentioned earlier)
causes of satisficing
-respondent motivation
-respondent ability
-task difficulty
results of satisficing
-select first reasonable response
-agree with assertions
-"don't know"
dichotomous nominal level questions
-simplest type of nominal measure
-classify into 2 exhaustive, mutually exclusive groups
-most common form: yes/no questions
-forcing people to answer one way or another
-easy for respondent to answer, simple to edit cod and analyze (good for skip patterns)
multiple choice questions (nominal)
-present 3 or more exclusive and exhaustive categories of response
-there should be an appropriate response for everyone respondent and no overlap!
-use when need is to categorize into smaller, more focused categories than are permitted by dichotomous questions
advantages of MC questions
flexible format, appropriate wide range of situations, easy to code; edit; tabulate; balance
checklists (nominal)
-combines series of related dichotomous questions into single question; less time consuming and less tedious
-"which of the following words apply?"
-must explicitly define selection criteria
-order choices to reduce bias
response order effects
• Recommendations: multiple versions or randomizing the order
• Caution: reasonable response options (influence the number of times people believe they partake in a behavior or what it's associated with!)
• If you want a straightforward number - ask people for a number don't give them options
rating scale (type of interval level questions)
"how believable or unbelievable was the commercial you just saw?"
considerations: number of scale options, scale balance, frame of reference
-recommendation: uni-polar scale
frame of reference
-non-comparative scales ask for rating without an explicit frame of reference "Think about the commercial you just saw. How believable or unbelievable would you say the commercial was?"
-comparative scales provide a frame of reference "Think about the commercial you just saw. How believable or unbelievable would you say the commercial was compared to other beer advertising"
constant sum questions
the more points you give to something, the more important it is. You can give as many or as few points you wish to each reason
o Considerations: manageable number of options, reasonable number of points, easily divisible number of points
why are people more likely to agree with assertions?
-norms of conduct (be polite and agreeable)
-status differential: defer to higher status
-satisficing: hypothesis confirmation bias
what is the most crucial step to avoid problems with questions?
Pre-testing to understand cognitive processes and determine potential problems...give people your questionnaire and have people think aloud as they respond to it...easy to see miss understandings/confusion
questionnaire components
-intro
-selection/screenings
-substantive (main body)
-background info
-post-interview questions
-transitions!
Rules of Conversation
1.Maxim of Quality
a.Try to make your contribution one that is true. Specifically, do not say what you believe to be false, and do not say that for which you lack adequate evidence
2.The Maxim of Quantity
a.Make your contribution as informative as is required for the current purposes of the exchange, and do not make your contribution more informative than is required
3.The Maxim of Relevance
a.Make your contribution relevant
4.The Maxim of Manner
a.Be perspicuous, and specifically avoid obscurity, avoid ambiguity, be brief, and be orderly
poorly written transitions
-potential to bias response
-too long; too detailed. increases difficulty level of the questionnaire
-too demanding; damages rapport
well-written transitions
-lends conversational tone; helps to maintain rapport
-alerts respondent to intro of new topic
-alerts respondent to more detailed questions within a topic
-provides a reason for collection of sensitive or personal information
Objective Phenomena
those that are directly (how many hours of sleep you get) observable
Subjective Phenomena
those that can be known only by respondents, themselves
Types of measures
Attitudes, Beliefs, Emotions, and Behavioral Intentions
Attitudes
Likes and Dislikes
Beliefs
Liking an object to an attribute
Emotions
happiness, frustration, pride (joy of new clothing)
Behavioral Intentions
Plans to behave in certain ways
Random Error
Due to temporary aspects of the person or measurement situation and what affects the measurement in irregular ways
Sources of Random Error
Mood, state of health, fatigue, situation in which the measure is taken, ambiguity of question
Cognitive Steps to Answering Questions
Understand- the question
Search- Memory for information
Integrate- Information into summary judgement
Map- Judgment onto response alternatives
Satisficing
a heuristic that satisfies the minimum requirements, when ability or task is difficult, respondent motivation low, just agree with assertions
Types of questions
Nominal
Ordinal
Interval
Ratio
Nominal
whenever the goal is the classification of the measured characteristic or attribute; assigns each level of a characteristic or attribute to a distinct category (advertising, marketing, click-throughs, email) must be mutually exclusive, collectively exhaustive, and have internal category equivalence
Ordinal
arranges characteristics or attributes according to their magnitude in an ordered relationship along some explicit dimension; numbers have mathematical meaning; relative standing; represent place in an ordered array
Interval
everything that ordinal has and distance and magnitude between any two adjacent numeric points on the scale is assumed to be equivalent ; relative ranking and distance; deeper and draw more inferences
Ratio
all the power of the last 3 but also make comparisons among quantities, equal distances between points and meaningful zero point, constant sum scale
Exclusive events
Answer can only fit in one category
Exhaustive events
Must be category with every imaginable answer
Response Order Effects
occurs when the distribution of responses to a closed-ended survey question is influenced by the order in which the response options are offered to respondents.
Primary effect
occur when response options are more likely to be chosen when presented at the beginning of a list of response options than when presented at the end.
Recency effect
occur when response options are more likely to be chosen when presented at the end of a list of response options than when presented at the beginning of the list.
Frequency estimates
how often an answer is chosen
agree-type responses
Example question would be like "to what extent do you agree with this statement..."
item-specific responses
Example question would be like "how important is this issue to you..."
Common types of problems when making questionnaire
double-barreled
double negatives
mismatch between response options and questions
non-exclusive
leading, loaded
conversational norms
Solving problems when making questionnaires
Simple language
Words with only 1 meaning
Ask about one thing at a time
Specific details
Appropriate time frames
Provide cues to aid memory
Pre-testing to understand cognitive processes and determining potential problems
Minimize cognitive burden
Avoid cues for satisficing (agree-disagree)
Questionnaire design disguised
makes purpose explicit
Questionnaire components
Intro, Screener, Main Body, Background Information/Post-interview questions
Questionnaire design undisguised
provides general overview but not everything
Intro
· explicit or implicit reference
· rationale and goals
· explicit request for participation
· task isn't burdensome
· need for truthful answers
· confidentiality
· real, legit research
Screener
Question at the beginning to admit all individuals who possess all the target characteristics and eliminates those that do not
Main Body
· simple, non-threatening, interesting, easy to answer questions first
· group questions on same topic together
· within a topic move from general to specific
· difficult and sensitive at end
· don't bias end questions from beginning
· address important topics first
Rules of Conversation
Maxim of quality, quantity, relevance, manner
Maxim of quality
try to make your contribution one that is true. Don't say things that you don't have evidence for
Maxim of quantity
make contribution as informative as is required for the current purposes of the exchange, and do not make your contribution more informative than is required.
Maxim of relevance
Make your contributions relevant and on topic
Maxim of manner
be perspicuous, and specifically avoid obscurity, avoid ambiguity, be brief, and be orderly
Experimental research
determine causality (effect of changes in one area on other areas)
Descriptive research
Describe specific point in time
Independent variable
"Cause"
Dependent variable
"Effect"
Internal Validity
A Broader View, Allows or eliminates alternative explanations of the results
External Validity
Affects the extent to which the results can legitimately be generalized
Surveys
respondents are asked to recall and report on behaviors
Experiments
observe behaviors, observe beyond description to describe causlity
Quasi Experimental Design
Attempt to uncover a causal relationship (do so poorly) because fail to eliminate threats to internal validity
1. One group post test only
One shot case study, "let's at least do something" design, Single group of individuals and exposes them to the treatment/experimental manipulation then measures the DV's (as part of posttest)
2. One group pretest to posttest
"Before and after without Control", Pre-measure is taken before manipulation of the IV, Often used when testing: product pricing, packaging and advertising response, Assessed by comparing levels in dependant measure (post treatment) to levels in the pretreatment measure
3. Two group protest with control
Attempt to address the problems with the prior designs, Cause and effect conclusions may not be correct
Explicit Measures
assess stored evaluative feelings and information about an object
Implicit Measures
assess evaluative tendencies, but do NOT require intentional recollection of stored evaluative info
Types of explicit measures
Graphic ratings, itemized ratings, likert scales, semantic differential
Types of implicit measures
Subliminal messaging, disguised self reports, projective techniques, priming, implicit association test,
Steps in experimentation
• Identify what you need to learn
• Take relevant actions
• Observe effects and consequences
• Determine causality
Categories of responding
Feelings - goodwill, positive affect toward object
Thoughts - favorable beliefs about objects
Behavior - recommending to others, purchasing, word of mouth
Functions of attitudes
Instrumental, Knowledge, Value expressive, Ego-defensive
Functions of attitudes - Knowledge
Remember that our attitudes don't just change
Functions of attitudes - Value-expressive
Attitudes help tell people who you are
Functions of attitudes - Ego-defensive
Ideas can protect us from unflattering truths, or resent, or fear
differences between descriptive and experimental research
experimental moves beyond description to determine causality is the effect of changes in one area on one or more other areas
limitations of survey research
Surveys become less reliable for explaining behaviors when:
-questions require recall
-individuals ask for introspection in areas of behavior not normally thought about
-individuals must use memory to attribute cause/effect
-complex, multiple or interrelated influences on behavior
major components of the classical experiment
-independent and dependent variables
-pre-testing/post-testing
-experimental and control groups
Dependent variable
refers to the status of the "effect" (how the pizza crust turned out) RESULT
independent variable
referes to the presumed "cause" (how much water you add into the pizza crust)
pre-test
the measurements of DV among participants
post-testing
the measurement of a DV among participants after they have been exposed to an IV
experimental group
group of subjects whom an experimental stimulus is administered (measure dependent variable->administer experimental stimulus->remeasure dependent variable
control group
a group of subjects to whom no experimental stimulus is administered and who should resemble the experimental group in all other respects (measure dependent variable -> remeasure dependent variable)
Steps in Experimentation
-identify what you need to learn
-take relevant action
-observe effects and consequences
-determine causality
what defines a true experiment
-controlled arrangement and manipulation of the conditions
-random assignment of treatments to the sampling units (helps us generalize the broader populations)
why is it important to randomize?
protect against unsuspected sources of bias and attempt equalize groups
requirements for causality
-events must take place in proper order
-events must show an explicit relationship
-alternative explanations must be reduced or eliminated
-relationships must show strength of association
what are the 3 imperatives for Establishing Casual Relationships?
-co-variation
-temporal precedence
-internal validity
internal validity
refers to our ability to attribute the observed effect to the independent variables, not other variables
threats to internal validity
history, maturation, testing, instrumentation, selection, morality (see more in depth below)
History threat to internal validity
events or influences beyond those intentionally manipulated by the researcher, which have potential to effect the experimental outcome
maturation threat to internal validity
people are always changing, which may affect the dynamics of the experiment
testing threat to internal validity
a pre-test can influence the way people respond ton the post-test or influence the way they respond to the treatment
instrumentation threat to internal validity
the measures that you can use to affect the results (not due to the treatment but to the instruments you are using)
selection threat to internal validity
whether or not you can randomly assign participants to treatment groups
morality threat to internal validity
when people drop out of an experiment
external validity
refers to the extent to which the results of an experiment can be generalized, or extended, to other situations, populations, times
pre-measurement error
whenever an interview given before start of experiment has direct effect on respondent's attitudes, actions or behaviors during experiment
interaction error
whenever an interview given before start of experiment affects respondent's sensitivity or responsiveness to independent variable
researcher bias error
occurs when actions of the experimenter bias has an effect on the outcome of the experiment; can be intentional or unintentional
double blind experiment
Neither the subjects or the experimenters know which is the experimental and which is the control group
quasi-experimental design
untrue experiments (one shot case study, one-group pre-test post-test design, static-group comparison) morality and selection are always threats to quasi-experimental design
types of true experimental designs
-post-test only with control
-pre-test to post-test with control
-Solomon 4-group design
factorial experiment
effects of more than one IV on a DV
-possible main effect for each IV
-allows for manipulation of two or more independent variables at the same time
interaction effect
the effect of one IV on the DV depends on the level of the other IV
Focus Group Pros
interactive
stimulating
spontaneous
lower cost
Focus Group Cons
single respondent may dominate
potential for bias
group pressures
group data not individual
Focus Group Uses
product idea generation
product positioning
creative exploration
Online Focus Groups
Synchronous
Asynchronous
Hybrid
Synchronous
all participants online at the same time
closest to traditional focus group
Asynchronous
participants dont need to be online at the same time
Hybrid
starts asynchronous and ends synchronous
Goal of Qualitative Analysis
reduce large amount of data into a set of well defined patterns and themes
Before Research
review problem and informational needs
Examine Data
become more familiar with data
be open minded
understand reasons underlying attitudes
review with a critical ear and eye
Theme Identification, Analysis and Revision Process
Theme development
Code Data
Examining Relevant Data
Theme Revision
Relating Individual Themes to Form Metathemes
Evaluating analysis
Metathemses
interrelationships of the individual themes
Human observation
researcher observes behaviors
Human Observations situations
observation is more insightful than descriptions
attitudes are hard to verbalize
survey measures may not predict behaviors
behaviors are the best source of insight
Observing Consumer Generated Media
coverage
depth
content
sentiment
Modes of Human Observation
situation
observer obtrusiveness
observer participation
data recording
Situation
natural vs. artificial
Observer Obtrusiveness
open vs. disguised
Observer Participation
active vs. passive
Data Recording
structured vs. unstructured
Automated Observation
data collected by a machine
Biometric Research
measure an individuals voluntary/involuntary responses
Neuromarketing
consumers response to marketing stimuli
FMRI
specific brain areas
EEG
measures and record brains electrical activity
Methods of Collecting Survey Info
personal interviews
telephone interviews
mail surveys
online surveys
hybrid surveys
Response Rate
Valid sample that participate in the research by completing the survey
Non-response Rate
subtracting the response rate from 100%
Measurement
the way unobservable concepts are linked to observable events
The Measurement Process
Identify and define the concept of interest
Specify an observable event
Evaluate and revise observable event
Concept definition
central or core idea
Observable Events
Nominal
Ordinal
Interval
Ration
Nominal
classification of measured characteristics
Ordinal
arranges attributes
Interval
distance between two adjacent points
Ratio
make comparisons among quantities
Reliability
extent a measure provides the same results
Validity
what researcher thinks its measuring
Operational definition
explanation that gives meaning to a concept by specifying activities necessary to measure it
Open-ended Questions
answer in your own words
measure attitudes, beliefs, perceptions
eliminate potential bias
avoid assumptions
Closed-ended Questions
responses available to choose from
Nominal Level Questions
Dichotomous
Multiple Choice
Checklist
Dichotomous
classify individuals into mutually exclusive groups
Undisguised
makes the purpose of research clear
Disguised
provides general overview but not explicit information
Questionnaire Components
Introduction
Selection/Screening
Main Body
Classification
Screening
distinguishes target from non-target
Rules of Conversation
quality
quantity
relevance
manner
Goal of Experimentation
determine causality
Causality
effect of changes in one area on one or more areas
Independent Variable
variable that the experiment manipulates
Dependent Variable
what the researcher is interested in explaining
Characteristics of Experiments
identify what you need to learn
take action
observe the effects
determine causality
Experimental Group
receives some treatment
Control Group
doesn't receive treatment
Internal Validity
extent that one can eliminate alternative explanations for the observed experimental results
External Validity
extent results can be generalized or extended to other situation, populations, times
Threats to internal validity
problems associated with...
an initial
data collection
the sample
study context
researcher behavior
Quasi-Experimental Designs
One shot case study
One group pre-test and post-test design
Static-group comparison
True Experiment
controlled arrangement and manipulation of the conditions
Three imperatives for establishing causal relationships
co-variation
temporal precedence
internal validity
Co-variation
Events must show an explicit relationship
Temporal Precedence
Cause must precede the effect
Events must take place in proper order