Not sure I'm a greater mind but here goes:
 
(1) Simple stuff first:  if you are doing t-tests, the general formula
for the t-test is the following:
 
Obtained t=(M1 - M2)/sqrt[VarErr1 + VarErr2 - 2*r*SE1*SE2]
 
Where M1=mean group1, M2=mean group2,VarErr1=Variance error group1,
VarErr2=Variance error group2, r=Pearson r between group1 and group2
valaues, SE1=standard error group1, SE2=standard error group2, and
2=constant (the number 2).
 
If you cannot calculate "r", you have to assume that it is equal to zero
which makes the t-test denominator = sqrt [ VarErr1 + VarErr1].  This
denominator will be larger than the denominator if "r" is known.  The
good news is if the t-test is significant under the assumption of r=0.00,
then it has to be significant if you can calculate r (NOTE: r is typically
a positive value -- a negative r should cause you to re-examine your data).
The bad news is if the t-test is non-significant, it could be so because
there is no real difference or you failed to find a significant difference
because you could not adjust (reduce) your denominator appropriately.
 
So, treating your data as independent groups makes the test more conservative
or less powerful.  I am open to correction on these points.
 
(2)  It seems to me that you should be able to get an estimate of the
Pearson r through bootstrapping or some other simulation procedure.
If there is a positive correlation between time 1 and time 2, then, assuming
data consisting only of 0 and 1, time1 zeros should co-occur with time2
zeros at a greater than chance level and the same holds for ones. even if
they are not matched up properly.  I haven't thought this through but
perhaps someone more familiar with bootstrapping with correlation
has more wisdom.
 
-Mike Palij
New York University
mp26@nyu.edu
 
 
 
----- Original Message -----
From: J P
To: SPSSX-L@LISTSERV.UGA.EDU
Sent: Friday, November 12, 2010 9:19 AM
Subject: non-SPSS: appropriate statistical test

Colleaguees,
 
This is not a SPSS question (at least not yet).
 
I am seeking advice on the appropriate test for comparing two non-independent samples when the non-independence cannot be modeled.
 
The proportions are drawn from the same employees pop  (~ 700, response rate of ~50%) employee population, surveyd one year apart. An example of an actual comparison is 98.4% vs 96.1% between time1 and time2. 
 
The problem, as I see it, is the two samples are not independent but there is no ID so neither a dependent t-test nor a mixed model can be used. I found a test for comparing proportions from two independent groups.
 
What is the risk of violating the assumption of independence? inflated type 1 error?
 
As far as I know there is no appropriate test for this situation, but I thought I'd check with minds greater than mine...
 
Thank you,
 
John