At 12:19 PM 11/6/2009, Rowe, Lesley wrote:
Elementary
Statistics: Picturing the World (Larson/Farber) has an
exercise where you prepare 2 sets of one-question surveys.
On one, you ask, "Should this school allow public speeches that
might incite violence?"
On the other, you ask," "Should this school forbid public
speeches that might incite violence?"
Supposedly, more people are willing to answer “no” to “allow,” than “yes”
to “forbid.” I have tried this with my regular stats class with
mixed results.
Well, these are not exactly the same questions ... so one might expect
some difference in the responses given.
If you answer NO to the first, it can mean
that your opinion
is that it should not ... but you might not think the school has the
right to BAN them (does not have the power)
If you answer YES to the second, it suggests that
your view is that
not only do you believe that they should not let it occur but also that
the school should take steps to bar them.
===========
I am not suggesting it's a big deal but it's a good example of a CONFOUND
... if there is a difference in responses, is it because of the
difference in the 2 words OR that the 2 questions are not the same ... OR
a bit of both?
Frequently asked questions (FAQ) http://www.mrderksen.com/faq.htm
To unsubscribe use this URL: http://lyris.collegeboard.com/read/my_forums/?forum=ap-stat
To change your subscription address or other settings use this URL: http://lyris.collegeboard.com/read/my_account/edit