| Date: | Tue, 29 Jul 2003 10:05:20 +0200 |
| Reply-To: | Markus Quandt <markus.quandt@uni-koeln.de> |
| Sender: | "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU> |
| From: | Markus Quandt <markus.quandt@uni-koeln.de> |
| Organization: | Universitaet zu Koeln |
| Subject: | Re: jittering in scatterplots |
| In-Reply-To: | <Pine.A41.4.44.0307281141250.43984-100000@mead4.u.washington.edu> |
| Content-Type: | text/plain; charset=us-ascii |
Hello SPSSX-L,
jittering as such is rather easy to do even with standard GRAPH
commands if you simply transform the original individual values to be
plotted with a random component.
The following example 'jitters' the existing variables EDUC and
OCCSTAT and then plots them. Obviously, you determine the degree
of jittering by the constant multiplied into the random
component.
*** Jittering.
comp xjitt=EDUC+.2*rv.uniform(-1,+1).
comp yjitt=OCCSTAT+.02*rv.uniform(-1,+1).
corr xjitt yjitt EDUC OCCSTAT.
variable labels /EDUC "education"
/xjitt "educ., jitt."
/OCCSTAT "occupational status"
/yjitt "occ. stat., jitt.".
GRAPH
/SCATTERPLOT(OVERLAY)=EDUC xjitt WITH OCCSTAT yjitt (PAIR)
/MISSING=LISTWISE .
HTH, MQ
Auszug aus Mail vom Montag, 28. Juli 2003 um 20:44:
> There is a nice web page about SPSS graph jittering at --
> http://www.ats.ucla.edu/stat/spss/faq/jitter.htm
> It includes the "sunflowers" in the main charts as well as an IGRAPH
> example.
> Sally in Seattle
> On Sat, 26 Jul 2003, John McConnell wrote:
>> Yes Jeff
>>
>> In Interactive Graphs (IGRAPH) at least. I don't believe you can specify
>> this upfront but a jitter, to a given %, can be applied after the plot
>> is produced.
>>
>> Cheers
>> John
>>
>> Significant Difference
>> Building 3
>> Chiswick Park
>> 566 Chiswick High Road
>> London, W4 5YA
>>
>> Mobile: +44 (0) 7711 786600
>> Office: +44 (0) 208 899-6029
>>
>>
>>
>>
>> -----Original Message-----
>> From: SPSSX(r) Discussion [mailto:SPSSX-L@LISTSERV.UGA.EDU] On Behalf Of
>> Jeff Stuewig
>> Sent: 25 July 2003 17:34
>> To: SPSSX-L@LISTSERV.UGA.EDU
>> Subject: jittering in scatterplots
>>
>> Can SPSS do jittering in scatterplots?
>>
--
Markus Quandt mailto:markus.quandt@uni-koeln.de
Institut fuer Angewandte Sozialforschung (IfAS)
Universitaet zu Koeln
Greinstr. 2
50939 Koeln
Tel. +49-221/470-4232 ### Fax. +49-221/470-5169
PGP-Key (2.6) verfuegbar unter:
http://www.uni-koeln.de/wiso-fak/ifas/html/personal/homepage/quandt-markus/pgpatunikoeln.txt
|