[R] Verifying lm results

Andrew Perrin andrew_perrin at unc.edu
Tue Feb 26 22:53:53 CET 2002


Greetings.

I'm planning to make a point in a meeting tomorrow and want to make sure
I've got my ducks in a row.

I've got four distinct vectors: years, fec, gss, and nes. Years is simply
seq(1972,1996,by=4), and the other three are measures of voter
participation in US elections in those years. fec is the Federal Election
Commission's numbers, gss and nes are the General Social Survey and the
National Election Survey, respectively.

What's interesting is that they are rather different, not only in absolute
numbers but in slopes of changes.  I wanted to measure these differences,
so figured that a quick regression would do the trick. DISCLAIMER: I may
very well not know what I'm doing :).

What I did was:
summary(lm(fec ~ gss))
summary(lm(fec ~ nes))

I got adjusted r-squared values that were pretty low (.1466 and .2473,
respectively) given that, theoretically, these measure the same
phenomenon. I would appreciate any comments from the list on why this
might be an invalid test for agreement among the three surveys.

Thanks.

----------------------------------------------------------------------
Andrew J Perrin - andrew_perrin at unc.edu - http://www.unc.edu/~aperrin
 Assistant Professor of Sociology, U of North Carolina, Chapel Hill
      269 Hamilton Hall, CB#3210, Chapel Hill, NC 27599-3210 USA


-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._



More information about the R-help mailing list