scatter plot table/grid
Locked
 
|
Dear list-members,
I wonder if there is a way of creating a scatter plot table/grid with different variables on the y-axis compared to the x-axis? I know that you can create scatter plot matrix with the same variables on the y-axis as on the x-axis, but this is not what I want. I basically want to get a visual representation of different dependent variables (y-axis) on various independent variables (x-axis). So I want it to look like a scatter plot matrix, but with my own specified variables on each axis. Secondly, to add to this, can I add a correlation line (linear and quadratic) through all scatter plots with R2 values? All help appreciated. Adel ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (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 |
|
|
The STATS REGRESS PLOT extension command
will do a set of small y by x plots with any number of y and x variables.
It can also include linear, quadratic, cubic, and/or loess fits in
the plots. The command has some other useful features. The
output isn't a SPLOM: it is a set of panels.
This command and the prerequisite Python Essentials are available from the SPSS Community website (www.ibm.com/developerworks/spssdevcentral). For Statistics 21, the Python Essentials are available from the regular Statistics download area or in the trial download site. The command generates a lot of GGRAPH/GPL code for this. You could write all that by hand, but it would be painful. Regards, Jon Peck (no "h") aka Kim Senior Software Engineer, IBM [hidden email] new phone: 720-342-5621 From: Adel Daoud <[hidden email]> To: [hidden email], Date: 03/07/2013 09:08 AM Subject: [SPSSX-L] scatter plot table/grid Sent by: "SPSSX(r) Discussion" <[hidden email]> Dear list-members, I wonder if there is a way of creating a scatter plot table/grid with different variables on the y-axis compared to the x-axis? I know that you can create scatter plot matrix with the same variables on the y-axis as on the x-axis, but this is not what I want. I basically want to get a visual representation of different dependent variables (y-axis) on various independent variables (x-axis). So I want it to look like a scatter plot matrix, but with my own specified variables on each axis. Secondly, to add to this, can I add a correlation line (linear and quadratic) through all scatter plots with R2 values? All help appreciated. Adel ===================== To manage your subscription to SPSSX-L, send a message to [hidden email] (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 |
|
|
Thanks Jon, for the quick reply! I have SPSS 21, so I will not need Python extensions, or do I ? Just installed the STATS REGRESS PLOT extension, but I get the following error in the output (missing Python extension maybe..?):
>Error # 1. Command name: STATS >The first word in the line is not recognized as an SPSS Statistics command. >Execution of this command stops. /OPTIONS CATEGORICAL=BARS GROUP=1 BOXPLOTS INDENT=15 YSCALE=75
/FITLINES APPLYTO=TOTAL. STATS REGRESS PLOT YVARS=watdeps_GM cfoodeps_GM ceddeps_GM XVARS=DisFre_1900 DisKill_1900 DisAff_1900 >Error # 1. Command name: STATS Thanks again Adel On Thu, Mar 7, 2013 at 5:26 PM, Jon K Peck <[hidden email]> wrote: The STATS REGRESS PLOT extension command will do a set of small y by x plots with any number of y and x variables. It can also include linear, quadratic, cubic, and/or loess fits in the plots. The command has some other useful features. The output isn't a SPLOM: it is a set of panels. Adel Daoud, PhD Department of Sociology and Work Science, University of Gothenburg Box 720 405 30 Göteborg, SWEDEN Visiting address: Sprängkullsgatan 25, room K109 +46 031-786 41 73 [hidden email] |
|
|
It was the missing Python extension - my bad. It is working now, thanks for writing this extension Jon! best /Adel
On Thu, Mar 7, 2013 at 6:04 PM, Adel Daoud <[hidden email]> wrote:
Adel Daoud, PhD Department of Sociology and Work Science, University of Gothenburg Box 720 405 30 Göteborg, SWEDEN Visiting address: Sprängkullsgatan 25, room K109 +46 031-786 41 73 [hidden email] |
|
|
Jon, thanks again for the STATS REGRESS PLOT extension I have been using it for the last couple of days and I am very impressed. Can I ask if there is a way of displaying the R2 values for the bath of scatter plots without having to click on each figure?
Thanks in advance Adel On Thu, Mar 7, 2013 at 6:23 PM, Adel Daoud <[hidden email]> wrote:
Adel Daoud, PhD Department of Sociology and Work Science, University of Gothenburg Box 720 405 30 Göteborg, SWEDEN Visiting address: Sprängkullsgatan 25, room K109 +46 031-786 41 73 [hidden email] |
|
|
I'm glad you find this extension command
useful. As for the R2, though, this is not practical. For small
panels, displaying the R2 for each fit in the chart would usually result
in a lot of overwriting. It would be possible to implement this for
a single-panel chart, but the command does not do this currently. The
Viz engine calculates the fit line internally and does not include the
actual R2 value in the chart xml, so it is not available for extraction
and display elsewhere.
Regards, Jon Peck (no "h") aka Kim Senior Software Engineer, IBM [hidden email] phone: 720-342-5621 From: Adel Daoud <[hidden email]> To: [hidden email], Date: 03/12/2013 08:27 AM Subject: Re: [SPSSX-L] scatter plot table/grid Sent by: "SPSSX(r) Discussion" <[hidden email]> Jon, thanks again for the STATS REGRESS PLOT extension I have been using it for the last couple of days and I am very impressed. Can I ask if there is a way of displaying the R2 values for the bath of scatter plots without having to click on each figure?
Thanks in advance Adel
Dear list-members, I wonder if there is a way of creating a scatter plot table/grid with different variables on the y-axis compared to the x-axis? I know that you can create scatter plot matrix with the same variables on the y-axis as on the x-axis, but this is not what I want. I basically want to get a visual representation of different dependent variables (y-axis) on various independent variables (x-axis). So I want it to look like a scatter plot matrix, but with my own specified variables on each axis. Secondly, to add to this, can I add a correlation line (linear and quadratic) through all scatter plots with R2 values? All help appreciated. Adel ===================== To manage your subscription to SPSSX-L, send a message to LISTSERV@... (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 -- Adel Daoud, PhD Department of Sociology and Work Science, University of Gothenburg Box 720 405 30 Göteborg, SWEDEN Visiting address: Sprängkullsgatan 25, room K109 <a href="tel:%2B46%20031-786%2041%2073" target=_blank>+46 031-786 41 73 Adel.daoud@... -- Adel Daoud, PhD Department of Sociology and Work Science, University of Gothenburg Box 720 405 30 Göteborg, SWEDEN Visiting address: Sprängkullsgatan 25, room K109 <a href="tel:%2B46%20031-786%2041%2073" target=_blank>+46 031-786 41 73 Adel.daoud@... -- Adel Daoud, PhD Department of Sociology and Work Science, University of Gothenburg Box 720 405 30 Göteborg, SWEDEN Visiting address: Sprängkullsgatan 25, room K109 +46 031-786 41 73 Adel.daoud@... |
«
Return to SPSSX Discussion
|
1 view|%1 views
| Free forum by Nabble | Edit this page |