That?s how I?ve interpreted it.
Don?t forget the measure of uncertainty.
I don?t think I would mention to Gary?s grandmother the effect of changing
education level on giving response 2: effectively it?s null. Also the
effects on 3 and 4 are perhaps similar enough for one to simplify the
statement without doing too much damage to the substantive interpretation.
I?m unsure how to phrase the lower bound measure of confidence on 1. If you
say to someone ?I?m very confident that someone with an advanced degree, but
otherwise just like someone else with no or very low qualifications, is
about 13% more likely to say they paid a lot of attention to the elections.
But the difference could be high as 28%, or it might even be slightly
negative? then I think the average person might find that much more of a
meaningless fudge of a statement than if you don?t mention that the lower
bound goes into negative territory. From my experience people first think in
terms of quality (?more of A causes more/less of B?) and then in terms of
quantity. Giving a negative lower bound makes the qualitative interpretation
harder to put across.
I guess this ? how to present results meaningfully to non-specialists- is
more ?art? than ?science?. Any advice/ideas on this?
From: gov2001-l-bounces at
lists.fas.harvard.edu
[mailto:gov2001-l-bounces at
lists.fas.harvard.edu] On Behalf Of Maya Sen
Sent: 21 March 2007 16:27
To: gov2001-l at
lists.fas.harvard.edu
Subject: [gov2001-l] 2.2 (gary's grandmother question)
I'm having a few second thoughts on interpreting my Zelig first differences
output. I'm basically getting something in my output that looks like this:
First Differences: P(Y=j|X1)-P(Y=j|X)
mean sd 2.5% 97.5%
1 0.13002 0.07375 -0.015032 0.275292
2 0.01048 0.01005 -0.002703 0.034747
3 -0.08027 0.04556 -0.164719 0.008768
4 -0.06023 0.03637 -0.134939 0.006545
Am I right in saying that this is telling me that a change from X to X1
results in a 13% increase in the chance that a respondent will give Answer
#1? Likewise, is this output telling me that the change from X to X1 results
in a 1% increase in the chance that a respondent will give Answer #2?
that's the way I'm reading this output and it seems to make sense that way.
but I might be wrong--I don't have much familiarity with Zelig or with first
differences analysis.
thanks,
Maya
--
No virus found in this incoming message.
Checked by AVG Free Edition.
Version: 7.5.446 / Virus Database: 268.18.16/729 - Release Date: 21/03/2007
07:52
--
No virus found in this outgoing message.
Checked by AVG Free Edition.
Version: 7.5.446 / Virus Database: 268.18.16/729 - Release Date: 21/03/2007
07:52