4. Survey Question Types
•
•
•
•
•
Open-ended text questions
Multiple choice questions
Ordinal scale questions
Interval scale questions
Ratio scale questions
The type of data generated
by the survey question
constrains the type of
analysis you can perform.
6. • These scales are mutually exclusive (no
overlap) and none of them have any
numerical significance)
http://www.mymarketresearchmethods.com/types-of-data-nominal-ordinal-interval-ratio/
9. 2) Ordinal Data: Rank Order Scale
create an ordinal scale of preference
• Rank order scaling questions allow a
certain set of variables to be ranked based
upon a specific attribute or characteristic.
http://www.questionpro.com/a/showArticle.do?articleID=survey-questions
10. Ranking questions are best to use when all the choices listed should be ranked
Ranking questions are best to use when all the choices listed should be ranked
according to a level of specification (e.g. level of importance).
according to a level of specification (e.g. level of importance).
If you have a question in which you need the respondents to indicate what items
If you have a question in which you need the respondents to indicate what items
are the “most important” to “least important,” then you can set up a ranking
are the “most important” to “least important,” then you can set up a ranking
question (Waddington 2000).
question (Waddington 2000).
http://s3.amazonaws.com/SurveyMonkeyFiles/SmartSurvey.pdf
11. Rating (Lickert* ) Scale: ordinal?
(non-numeric concepts like satisfaction, happiness, etc.)
(
• the order of the
In each case, we know that a #4 is better than
In each case, we know that a #4 is better than
a #3 or #2, but we don’t know–and cannot
a #3 or #2, but we don’t know–and cannot
quantify–how much better ititis.
quantify–how much better is.
* pronounced 'lick-urt' with a short "i"
sound
values is what’s
important and
significant, but
the differences
between each
one is not really
known
http://www.mymarketresearchmethods.com/types-of-data-nominal-ordinal-interval-ratio/
12. surveying the frequency of something like
behavior or attitude. It is best to present
the rating scale in a logical or consistent
order. Therefore, it makes sense to order
the ranking or rating choices from low to
high (e.g. Strongly Disagree to Strongly
Agree going from left to right).
http://s3.amazonaws.com/SurveyMonkeyFiles/SmartSurvey.pdf
• Rating type questions are used when
13. Interval Scale
• It is an interval scale because it is assumed to
have equidistant (equal distance) points
between each of the scale elements. This
means that we can interpret differences in the
distance along the scale. We contrast this to
an ordinal scale where we can only talk
about differences in order, not
differences in the degree of order .
14. Interval Scale
• When you are asked to rate your
satisfaction with a piece of software on a 7
point scale, from Dissatisfied to Satisfied,
you are using an interval scale
• it is important that the space between
each option, whether it's a number range
or a feeling range, are equal.
• scales asking about agreement strength,
likelihood or satisfaction (i.e. very
unsatisfied, unsatisfied, neither satisfied
nor unsatisfied, satisfied, very satisfied).
15. • …Similar to ordinal, but the intervals between
•
•
the values of the response options are evenly
spaced
…Can be used for any quantitative variable
…Measures variables that fall into logical ranges
• Example: What was your undergraduate GPA
upon graduation?
a) 3.5-4.0 b) 3.0-3.49 c) 2.5-2.99 d) 2.0-2.49
http://www.virginia.edu/processsimplification/resources/survey_design.pdf
16. According to James Dean Brown
(University of Hawai‘i at Manoa)
• Interval scales show the order of things, but with
•
•
equal intervals between the points on the scale.
Thus, the distance between scores of 50, 51, 52,
53 and so forth are all assumed to be the same
all along the scale. Test scores are usually
treated as interval scales in language research.
Scales based on Likert items are also commonly
treated as interval scales in our
(education/social research) field.
http://jalt.org/test/PDF/Brown34.pdf
17. Ordinal & Interval Example
http://cdn.informationmanagement.com/media/assets/article/1023904/few_fig3.gif
18. Ratio Scale
• Ratio scales differ from interval scales in that
they have a zero value and points along the
scale make sense as ratios. For example, a
scale like age can be zero, and it makes sense
to think of four years as twice as old as two
years
http://survey.cvent.com/blog/cvent-survey-blog/guide-to-the-five-types-of-survey-questions
19. • When respondents are asked to tell us some physical measure, such
as income, years of education, or how long their phone call was on
hold, these are ratio scale questions. The data they provide have a
true zero. (On an interval scale, a zero response option is simply
arbitrary. Zero income, for example, is real.)
• Frequently, we solicit ratio data with what appears to be an ordinal
•
scale with response options presented in ranges, such as if we were
to ask for the number of years of education the person had achieved,
asking the respondent to check one of the following options: 1) 1 to
12 years, 2) high school degree, 3) associates degree, 4) bachelors
degree, 5) graduate degree. While the question looks ordinal, we
could treat the data as ratio in our analysis.
Why present ranges?
– First, it's faster for the respondent to answer the question,
lowering respondent burden.
– Second, it's less invasive to ask someone to check an income
range, for example, then to ask them their annual income. Would
you tell a stranger your income level? Probably not, but you
might be willing to check a box that says your income is $50,000
to $75,000 per year.
http://www.greatbrook.com/survey_question.htm
21. • Nominal: mode crosstabulation - with chi-square, etc.
• Ordinal: use non-parametric statistics, i.e. Median and mode, rank order
•
http://efox.cox.smu.edu/mktg3342/dataanalysis.pdf
http://www.csse.monash.edu.au/~smarkham/resources/scaling.htm
Measurement
correlation, non-parametric analysis of variance
– Modelling techniques can also be used with ordinal data.
Interval: Interval scale data would use parametric statistical techniques:
– Mean and standard deviation
Correlation - r
Regression
Analysis of variance
Factor analysis
– Cronbach analysis
– Plus a whole range of advanced multivariate and modelling techniques
• Ratio: variables which are ratio scaled include weights,
lengths and times. virtually all statistical operations can be
performed on ratio scales