MKTG 440 Exam 2 Flashcards
Measurement
Rules for assigning numbers to objects to represent quantities of attributes.
Nominal Scale
numbers are assigned to objects or classes of objects solely for the purpose of identification
-mode
Ordinal Scale
numbers are assigned to data on the basis of some order of objects
- median
- mode
Interval Scale
the numbers assigned legitimately allow the comparison of the size of the differences among and between the numbers
Ratio Scale
Measurement that has a natural, or absolute zero and therefore allows the comparison of absolute magnitudes of the numbers
Systematic Error
Error in measurement that is known as constant error since it affects the measurement in a constant way. (personality, response styles, wording of questions, methods of admin)
Validity
The degree to which a measure measures what it is supposed to measure.
-As systematic and/or random error increases, validity of a measure decreases
Reliability
The degree to which a measure is consistent across time, evaluators, and the items forming the scale.
Performance of objective
People are most likely to recount things that are consistent with their attitudes
Self-report
Direct questioning; most common approach
Graphic-rating scale
Place an X to reflect perceptions
- “Unlimited” number of response categories
- Continuous scale
Itemized-ratings scale
List of items, options to choose perceptions for each item
- Limited number of response categories
- 5 to 9 categories
Summated-ratings scale
Likert Scale
-degree of agreement or disagreement
Semantic-rating scale
selection between a set of bipolar adjectives or phrases
Comparitive-ratings scale
Divide X number of points between attributes.
Constant-sum method
Divide 100 points among five areas
Response set bias
All negative, neutral, positive.
Reverse scaling
a technique in which some of the items on a multi-item scale are written so that the most positive responses are at the opposite end of the scale from where they would normally appear
Global measure
to provide an overall assessment of an object or phenomenon, typically using one or two items
Composite measure
provide a comprehensive assessment of an object or phenomenon, with items to assess all relevant aspects or dimensions
Filter question
Are you the person that makes decisions?
Telescoping Error
If the respondent did something a long time ago, they feel like they did it recently, but memory may not be as accurate
Recall loss
Can’t remember when they did it
Randomized-response model
Initial “benchmark” study
-second survey, 200 respondents, flip a coin and answer the question, coin won’t be known to researcher.
Multichotomous question
respondents are asked to choose the alternative that most closely reflects their position on a subject
Response order bias
an error that occurs when the response to a question is influenced by the order in which the alternatives are presented
Split-ballot technique
A technique in which on phrasing is used for a question in half of the questionnaires while an alternate phrasing is used in the other half
Leading question
Do you believe that Sontai Airlines should stop airing its misleading advertisements?
Assumed consequences
When a question is not framed to clearly state the consequences and this generates different responses from individuals who assume different consequences
Double-barreled question
Asking one question after another
Funnel Approach
Start with broad questions, then get more specific towards end
Question order bias
tendency for earlier questions on a questionnaire to influence respondents’ answers to later questions
Branching question
Ask questions based off of other questions or answers
Pretest
use of questionnaire on a trial basis in a small pilot study to determine how well the questionnaire works
Census
type of sample plan where data are collected from or about each member of a population
Sample
selection of a subset of elements from a larger group of objects
Population
all cases that meet designated specifications for a group
Incidence
percent of general population or group that qualifies for inclusion in the population
Parameter
- characteristic or measure of a population
- True value
Statistic
A characteristic or measure of a sample
Sampling error
difference between results obtained from sample and results that would have been obtained had info been gathered from population
- decreased by increasing sample size
- can be estimated
- usually less troublesome than other kinds of errors
Sampling frame
List of population elements from which a sample will be drawn
- customer database
- telephone directories
- lists developed by data compilers
Probability sample
has some chance to be selected
Non-probability sample
doesn’t have a chance to be selected
- convenience
- judgement
- quota
Sequential sample
sample formed on the basis of a series of successive decisions
Convenience sample
right place at the right time
Judgement sample
population elements are handpicked because they are expected to serve the research purpose
-non-probability
Snowball sample
a judgement sample that relies on the researcher’s ability to locate and initial set of respondents with the desired characteristics
Quota sample
certain important characteristics of the population are represented proportionately in the sample
- non-probability
- Better sense of overall geodemographic distribution (gender, income, etc.)
Simple random sample
each unit included in the population has a known and equal chance of being in the sample
Systematic sample
sample in which every x element in the population is selected for the sample pool after a random start
Sampling interval
k= Number in the sampling frame/Total sampling elements-k
Total sampling elements (TSE)
The number of population elements that must be drawn from the population and included in the initial sample pool in order to end up with the desired sample size
Stratified sample
Same within the group
Different between the groups
Cluster sample
Different within the group
Same between the groups
Precision
Degree of acceptable error in an estimate of a population parameter
Confidence
Degree to which the researcher can feel assured that an estimate approximates the true value
3 Factors researchers must take into account when selecting a sample size
Variance
Precision
Confidence
How to calculate a sample size when estimating means and proportions?
means
n=z^2/H^2 (o^2)
sample size = z-score/half-precision * (variance)
proportions
n= z-score / H^2 * estimated population proportion (1-estimated population proportion)
What way does the size of the population influence the size of the sample?
it doesn’t
-variance is the only thing that may indirectly affect it.
What are non statistical methods of determining the sample size for a project?
- Secondary data
- Other info
- Depending on analysis type
Random error
error in measurement due to temporary aspects of the person or measurement situation and which affects the measurement in irregular ways. (mood, state of health, fatigue, situation in which measure is taken)
Physiological reaction
a measure of intensity but not necessarily level of favorability
Steps in questionnaire development.
1) specify what info
2) determine admin method
3) Determine content of individual questions
4) Determine form of response to each question
5) Determine form of response to each question
6) Determine question sequence
7) Determine physical characteristics of questionnaire
8) Develop recruiting message or script
9) Reexamine steps 1-8 and revise if necessary
10) pretest questionnaire and revise if necessary
Technique used by researchers to handle to get respondents to cooperate
- randomized response technique
- Place sensitive questions near the end
- Include a counter biasing statement
- Ask about how others might feel
- Ask for general rather than specific info
Wording issues
Simple words Avoid ambiguous words Avoid leading questions Avoid Unstated Alternatives Avoid assumed consequences