Hi Cathy
Ideally we would ontically discern the attitude of a person as distinct from the social norm.. And the modal zone of the distributuon may be a trace of the social norm, so I advise you to treat each variable in the careful, responsive way you suggest. there is no hard and fast rule. would you like a short briefing paper on this? see this one.
Olsen, W.K., and Min Zhang, How To Statistically Test Attitudes Over Space: Answers from the gender norms and labour supply project. Creative Commons, University of Manchester, 2015, Briefing Paper 3, the Gender Norms Project, URL http://hummedia.manchester.ac.uk/institutes/cmist/InnovationsProject/BP3OlsenZhang.pdf
Each person now may either agree with or disagree with the social norm for their region. there are often two forms of disagreemen t... but on the justifiability of wife beating only one. (Dhs)
so it is an empirical questioin.
if you wish to read, at much greater length,
I can send you a slide set and teaching paper. but that gets into the maths. wendy Olsen
THIS EMAIL IS FROM WENDY OLSEN.
Values for our Time
Reliability. Thoughtfulness. Honesty.
Guts. Fairness. Lovingness.
Wisdom built up over years.
R E S P E C T F O R A L L
T A K E T I M E T O T H I N K
________________________________________
From: email list for Radical Statistics [[log in to unmask]] on behalf of Cathy Baldwin [[log in to unmask]]
Sent: 29 November 2016 23:25
To: [log in to unmask]
Subject: using a 5-point likert scale to report attitudinal differences
Hi there,
My question is more qualitative/interpretative, in reporting descriptive statements citing percentages of interest from a small data set (sample size 509) for a report I'm writing (applied social anthro).
Has anyone reported on attitudinal data from a 5-point likert scale and can recommend any papers that discuss when it's okay/legit /preferable to cite the combined categories (Agree/disagree) and when it's preferable to cite the different categories of response by the scale? I've got a very sensitive applied research study topic, and sometimes find that a majority of people opt for strongly agree and a much smaller percentage opt for tend to agree, so find it easier to cite the combined overall agree, but other times there are interesting differences in the 5 response options so it's more interesting to cite those. Are there any rules/a rationale if we are looking at this from a subjective, descriptive point of view (not from a mathmatical point of view) for when to use the combined categories and when not to when descriibing the attitudes of a Western population in written form?
Any advice on this or recommendations of papers would be great.
Thank you very much!
Best wishes,
Cathy Baldwin, University of Oxford
****************************************************** Please note that if you press the 'Reply' button your message will go only to the sender of this message. If you want to reply to the whole list, use your mailer's 'Reply-to-All' button to send your message automatically to [log in to unmask] Disclaimer: The messages sent to this list are the views of the sender and cannot be assumed to be representative of the range of views held by subscribers to the Radical Statistics Group. To find out more about Radical Statistics and its aims and activities and read current and past issues of our newsletter you are invited to visit our web site www.radstats.org.uk. *******************************************************
******************************************************
Please note that if you press the 'Reply' button your
message will go only to the sender of this message.
If you want to reply to the whole list, use your mailer's
'Reply-to-All' button to send your message automatically
to [log in to unmask]
Disclaimer: The messages sent to this list are the views of the sender and cannot be assumed to be representative of the range of views held by subscribers to the Radical Statistics Group. To find out more about Radical Statistics and its aims and activities and read current and past issues of our newsletter you are invited to visit our web site www.radstats.org.uk.
*******************************************************
|