Soren,

I am, maybe, befuddled.  I created a social roll call vote scale for a new replication and extension of the 1996 election outcome analysis of Canes Wrone et al. That scale is from the 104th Congress and thus 1995 and 1996 RC's. I then merged that scale (that is appropriately party defining in the Poole and Rosenthal roll call vote data) into the Canes Wrone data set that you recently sent to me.  And I think, perhaps a dangerous thing to do given the problems of data set documentation we discussed Friday, that I matched the cases correctly.

But the scale scores are just about randomly distributed by party of the MC in the Canes Wrone data.  On Monday I can re-check my case matching logic, but here's another puzzle.  Exploring the CW data, I see that over 50 members are recorded as having been elected after 1996 -- and 73 were elected in 1996.  But I thought this file should only include those elected before 1996 and that the vote share dependent variable was for their election margin in 1996.

So on Monday will you chat with me at your convenience and at least briefly to determine whether I am puzzled, confused, befuddled, or ...something, and to determine how to un-puzzle me?

kqh  

Kim Quaile Hill
Cullen-McFadden Professor 
of Political Science, and
Eppright Professor in Undergraduate
Teaching Excellence
Department of Political Science
4348 TAMU
Texas A&M University
College Station, TX 77843-4348
ph. 979/845-8235
fax 979/847-8924
e-mail:  [log in to unmask]

**********************************************************
             Political Methodology E-Mail List
   Editors: Ethan Porter        <[log in to unmask]>
            Gregory Whitfield   <[log in to unmask]>
**********************************************************
        Send messages to [log in to unmask]
  To join the list, cancel your subscription, or modify
           your subscription settings visit:

          http://polmeth.wustl.edu/polmeth.php

**********************************************************