**Date:** Tue, 16 Jun 2009 08:39:22 -0400
**Reply-To:** Rebecca Stewart <restewar@psych.upenn.edu>
**Sender:** "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
**From:** Rebecca Stewart <restewar@psych.upenn.edu>
**Subject:** Scatterplot Problems: Residual over Precited
**Content-Type:** text/plain; charset=ISO-8859-1; format=flowed
Dear List,

Apologies for the remedial question. I am trying to look at some data
to see if it is appropriate for regression. All I want is a simple plot
of residuals over predicted, hoping that I'll see nothing interesting
(instead of say, a fan). However, when I plot this, I get a graph I've
never seen.

The graph I get is not the scatterplots I'm used to seeing but these 7
negatively sloped lines. My DV was a scale with 7 points (don't know if
that's related) but I'm wondering what this means and why I'm getting
this and most importantly, WHAT is this? Any advice or feedback on what
I am doing wrong or what this graph is indicating (if correct) would be
hugely appreciated. Maybe I am not picking the right sort of resids or
preds in the dropdown menus.

I've pasted the syntax and graph below.

Any help would be appreciated.

Thanks!
Becca

REGRESSION
/MISSING LISTWISE
/STATISTICS COEFF OUTS R ANOVA
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT minbar
/METHOD=ENTER wrkshp age avhrwk rsrtrn2 dub1 dub2 dub3 dub4 dub5
/SCATTERPLOT=(*ZRESID ,*ZPRED)
/RESIDUALS NORM(ZRESID) OUTLIERS (SDRESID)
/CASEWISE=ALL SDBETA
/SAVE SDBETA.

------------------------------------------------------------------------

=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD