Term
| What are the two types of non-comparative scaling techniques? |
|
Definition
|
|
Term
| what is a continuous scale? |
|
Definition
Respondents rate the objects by placing a mark at the appropriate position
on a line that runs from one extreme of the criterion variable to the other (called continuous because they place a mark on a line that runs continuously lol)
ex. reacting to a tv commercial |
|
|
Term
| what is an itemized scale? |
|
Definition
respondents are provided with a scale that has a number or brief description associated with each category, respondents select the category that best describes the object being rated
Commonly used scales: likert, semantic differential, stapel |
|
|
Term
|
Definition
very common, respondent indicates a degree of agreement or disagreement with series of statements
I like to shop at sears: strongly disagree, disagree, neither agree nor disagree, agree, strongly agree
ex. measuring attitudes |
|
|
Term
| what is a semantic differential scale? |
|
Definition
a seven point rating scale with end points associated with bipolar labels that have a semantic meaning (bad on left, good on right)
ex: sears is: (powerful_._._._._._._weak)
other answers might be unreliable vs. reliable, modern vs. old-fashioned
ex. learning about brand image |
|
|
Term
|
Definition
a unipolar rating scale with ten categories (numbered -5 to +5, no neutral point) scale is presented vertically
ex. sears: ratings shown vertically +5 down to +1, then the word high quality, then -1 to -5
(+5 means that word describes sears well, -5 means it doesn't describe sears at all)
ex. measuring attitudes |
|
|
Term
| advantages and disadvantages of continuous, likert, semantic differential, and stapel scales |
|
Definition
continuous: easy to construct, hard to score w/o a computer
likert: easy to construct, time consuming
semantic differential: versatile, controversy as to whether the data are interval (wut?)
stapel: easy to construct and can administer over telephone, confusing and difficult to apply |
|
|
Term
| what are the 6 decisions you need to make when designing an itemized scale? |
|
Definition
1) number of categories: greater number of categories = finer discrimination among categories
2) balanced vs. unbalanced: balanced means an equal number of choices in favorable and unfavorable side
3) odd/even number of categories: do you want a middle choice?
4) forced vs nonforced scales: can force an answer in order to go onto next page, can allow no answer or make a "no opinion" option
5) verbal description: will you provide some labeling on the questions?
6) physical form: scales can be horizontal or vertical, can have thermometer scale or smiling face scale |
|
|
Term
| describe the reliability of a scale |
|
Definition
the extent to which a scale produces a consistent result when repeated, extent to which answers are free from random error
might conduct a test-retest reliability test: do a test and then retest it
might conduct an alternative-forms reliability test: require two different forms of a scale to be made |
|
|
Term
| describe the true-score model for reliability of a test |
|
Definition
provides a framework for understanding accuracy of measurement
true score = score of characteristic + systematic error + random error
systematic error: errors that are constant
random error: random changes in respondents or measurement situations |
|
|
Term
|
Definition
| the extent to which differences in scores reflect TRUE differences among objects on the characteristic being measured, RATHER THAN systematic or random errors |
|
|
Term
| describe test generalizability |
|
Definition
| the extent to which a study based on a sample applies to a universe of generalizations |
|
|
