Upgrade to remove ads
Marketing Research Exam 2
exam 2/midterm for Marketing research
Terms in this set (54)
Definition of Measurement
the process of assigning numbers or labels to things in accordance with specific rules to represent quantities or qualities of attribute.
Things are not measured, the attributes of things are measured
We don't measure a person, but we may measure the person's, social class, education, height, weight, attitudes etc.
Rule guide, method, or command that tells a researcher what to do
What are the steps in the measurement process?
1. Identify the concept of interest
2. Develop a construct
3. Define the concept constitutively
4. Define the concept operationally
5. Develop a measurement scale
6. Evaluate the reliability and validity of the measurement
7. Utilizes the scale
8. Research Findings
scales that partition data into mutually exclusive and collectively exhaustive categories
Lowest level of measurement, uniquely classifies, numbers are simply labels for categories ie frequencies, %, mode
scales that maintain the labeling characteristics of nominal scales and have the ability to order data
numbers have no absolute meaning, equality of intervals not assumes
scales that have the characteristics of ordinal scales, plus equal intervals between points to show relative amounts; they may include an arbitrary zero point
Farenheit, SPI, Rating scales are often assumed to have interval propertires, stats
scales that have the characteristics of interval scales, plus a meaningful zero point so that magnitudes can be compared arithmetically
Uniquely classifies, preserves order, equal intervals, meaningful zero point, IE age, income, purchaes, usage, occasions
degree to which measures are free from random error and, therefore, provide consistent data
the degree to which what the researcher was trying to measure was actually measured
Degree to which a measurement seems to measure what it is supposed to measure
representativeness, or sampling adequacy, of the content of the measurement instrument
Criterion Related validity
degree to which a measurement instrument can predict a variable that is designated a criterion
degree to which a future level of a criterion variable can be forecast by a current measurement scale
Degree to which another variable, measured at the same point in time as the variable of interest, can be predicted by the measurement instrument
Degree to which a measurement instrument represents and logically connects, via the underlying theory, the observed phenomenon to the construct
degree of correlation among different measurement instruments that purport to measure the same construct
measure of the lack of association among constructs that are supposed to be different
Constant Sum Scales
measurement scales that ask the respondent to divide a given number of points, typically 100, among two or more attributes, based on their importance to him or her
Semantic Differential scales
measurement scales that examine the strengths and weaknesses of a concept by having the respondent rank it between dichotomous pairs of words or phrases that could be used to describe it; the means of the responses are then plotted as a profile, or image
Graphic Rating Scale
Measurement scales that include a graphic continuum, anchored by two extremes
Measurement scales in which the respondent specifies a level of agreement or disagreement with statements expressing either a favorable or an unfavorable attitude toward the concept under study
criteria for a good questionare
Does it provide decision-making information?
Does it consider the respondent?
Does it meet editing and coding requirements?
Some attributes are easy to measure
not always so with psychological variables like attitude satisfaction, intention
Split half tech
A method of assessing the reliability of a scale by dividing the total set of measurement items in half and correlating the results.
A statistical measure of the degree to which items in a set of measures (interval or ratio) covary with all other items included in the measure
Ranges from 0.0 to 1.0
The most widely accept measure of reliability for constructs measured with sets of scales
Door to door Survery
Interviews conducted face to face with customers in their homes.
Pros - direct customer contact, can demonstrate products, responses rates still good.
Cons - expensive, bad image, liability, safety issues.
Face-to-face interviews conducted by intercepting people at high traffic locations.
Pros - direct customer contact, can test products, human interaction, interviewer present
to explain and probe.
Cons - expensive, not always representative of the population, bad image.
Interviews conducted by calling respondents from a central location.
Pros - good segmentation, can verify respondent as right person.
Cons - cost, response rates slipping, need to have short surveys.
Ad hoc / cross sectional and mail panels / longitudinal - (See following slide).
Pros - not too expensive, can get targeted mailing lists, can have longer questionnaires.
Cons - low response rates, mailing list often out of date, not sure who completed the survey, manual data entry common.
Self administered Questionares
Questionnaires filled out by respondents with no interviewer present.
Pros - respondents can take their time, good response rates.
Cons - respondents often take a long time, researcher might overcomplicate the survey since respondents have more time.
Factors to determine Survey Method
Speed of data collection: time allowable to complete survey
Need to expose respondent to various stimuli and have respondent perform specialized tasksQuality of data required
Are follow-up and probing questions needed?
Length of questionnaire
People don't like long mail or self-administered questionnaires
Degree of structure of questionnaire
Need for interviewer
If you are looking for a needle in a haystack, you need an inexpensive way to find it.
Respondents not initially informed of purpose and/or sponsor of survey
Researcher expects response bias to occur
Must debrief respondents after questions are answered
Methods to increase survey response rates
Gain attention and cooperation
Explain importance of study
Ask for respondents cooperation
"Your opinions are important."
"Not difficult, will take only a few minutes."
Ratio Scale Properties
Magnitude of difference between objects can be compared (meaningful zero point)
Examples: age, income, purchases, usage occasions, market share, sales
Itemized rating scales aka Category scales
scales in which the respondent selects an answer from a limited number of ordered categories, rather than by a continuum
scale provides numbers and/or brief descriptions associated with each category of response
easy to construct and to use
but often don't capture distinctions among respondents as well as graphic rating scales.
Basic considerations in scale selection
Ease of administration (data collection method)
Feasible to use for phone survey?
Ease of development
Decision-making needs of client
Precision of data
Level of measurement
Basic Considerations in scale design
Balanced vs. Unbalanced Scales
Balanced scales have the same number of positive and negative response categories
Unbalanced scales have more response categories at either positive or negative end
e.g. (Excellent, Very Good, Good, Fair, Poor)
If you expect the distribution of response to be skewed one way or the other use unbalanced in order to better capture the variation
If a symmetric distribution is expected use a balanced scale
Disadvantages of open ended questions
Not well-suited for self-administered questionnaires
most respondents will not write elaborate answers
answers may be more indicative of the respondent's ability to articulate a response than a measure of the respondent's knowledge about issue.
Interviewer bias can be a serious problem
Coding results can be difficult
two phase judgement is necessary
Categories can be precoded on the basis of a pilot study and placed into a fixed alternative question
Some uses for open ended quesitons
check and/or corroborate the results of quantitative studies with fixed alternative questions
develop a wider range of response than is possible using other types
obtain direct comparisons between brands
questions that require respondent to reply in his/her own words
allowed to choose any response deemed appropriate, within the limits implied by the question.
often require probes from interviewer
can provide a wealth of information
often used for exploratory objectives
Fixed alternative questions
questions that ask the respondent to choose from a list of answers provided with numbers and/or predetermined descriptions
Advantages of fixed alternative questions
easy to use for interviewer + respondent
reduces interviewer bias
reduces bias resulting from differences between articulate and inarticulate respondents
facilitates easy coding and data entry
choices can cue respondent memory
Disadvantages or fixed alternative questions
Require substantial effort to design and pretest
Response categories must be exhaustive and mutually exclusive and
at the appropriate level of precision
Two dichotomous response categories
easy to administer, code, analyze
evokes rapid response
prone to large amount of respondent error
wide range of possible choices between categories are ignored
Position bias of response categories can be a problem
Often requires preliminary open-ended survey, focus groups, brainstorming, secondary source research
Response categories must be exhaustive and mutually exclusive
problem solved by providing choice other___________
Position Bias (a form of response bias)
respondents favor 1st and last choices
overcome by rotating order of choices
A fixed-alternative question that allows the respondent to provide multiple answers to a single question by checking off items
Main concerns with questionare wording
-no hard and fast rules, only guidelines
-Be clear and precise
-should allow responses consistent with ----- --desired level of measurement
-use simple conversational language
-be aware of differences in terminology between social classes
-avoid ambiguous terms
-best to use terms with precise meanings
-use farmiliar language
-reducing threat or embarassment
-avoid leading questions
-avoid double-barreled questions
-avoid making assumptions
-avoid taxing the respondents memory
-forgetting can cause error like omission, creation, telescoping
-First third contain general questions
-second third are most specific
-last contains more sensitive threatening items
-respondents are conditioned to respond
-keep questions concerning a given topic together
-use transitional phrases
Formatting of questionnaire
Use booklet form if possible (stapled) if there are multiple pages
prevents lost pages
looks more professional
Use attractive typeface (fonts)
avoids photocopy look
instructions and questions should be in different fonts
italics, boldface, underlined, etc
Questionnaire should not look cluttered or crowded
better to have much blank space
gives clean appearance
looks less complicated & difficult
Provide adequate space to reply to open-ended
Multiple grid questions use space efficiently
two main types of online focus groupe
real time online focus groups
time extended online focus groups
advantages of online focus group
lack of geographic barriers
much lower costs
faster turn around time
respondents can be geographically separated
intangibles such as increased openness on the part of respondents when they do not have an interviewer staring at them
disadvantages of online focus groups
exposure to external stimuli
tole and skill of moderate
advantages of online surveys
rapid deployment- real time reporting
ability to contact hard to reach
simplified and enhanced panel management
external internet panels simplify life for research suppliers
disadvantages of online surveys
unrestricted internet sample
sample frame may not be avaiable online
lack of callback procedures
lack of bandwidth
how to increase participation for online surveys
open online panel recruitment
closed online panel recruitment
YOU MIGHT ALSO LIKE...
RM L6 Data collection: Questionnaires
Ch. 7 & 8