lsmeans with sem

[UGUR SERBESTER]

Dear friends

I want to draw a line graphic Lsmeans (Least square means) and SEM (Standard error of mean) values. How can I draw this graphic using SPSS 17.

Thanks to all helps.

Dr. Uğur SERBESTER
Nigde University
The Vocational School of Bor
 Turkiye
Tel: [phone] / 23
Fax: [phone]

[Art Kendall]

  I am not sure what you mean by "lsmeans".  Do you mean "adjusted
means" for example from ANCOVA (analysis of covariance)?

Do you have predicted values from of the dependent variable Y-hat from
some least squares procedure?

I used the example file supplied by SPSS and then the chart builder in
the GUI to generate the syntax below.
Open a new instance of SPSS.
Copy and paste the syntax below into a syntax window.
Change the file name so it matches the name on your system.
Run the syntax.
Is this similar to what you want?
If it is try to use chart builder on your system.  If you still have
problems reply to this list and someone can go through the details of
what to click.

If it is not what you want, please give more detail.
What is on the X axis? The Y axis?
Do you have an adjusted Y variable?
Do you have raw data or only aggregated data?

Can you find an example of what you want in the GPL reference that comes
with SPSS? Or can you supply a link to an example of the kind of graph
you are looking for?

Art Kendall
Social Research Consultants

On 9/17/2010 10:01 AM, UGUR SERBESTER wrote:

> Dear friends
> I want to draw a line graphic Lsmeans (Least square means) and SEM
> (Standard error of mean) values. How can I draw this graphic using
> SPSS 17.
> Thanks to all helps.
>
> Dr. Uğur SERBESTER
> Nigde University
> The Vocational School of Bor
>  Turkiye
> Tel: [phone] / 23
> Fax: [phone]

=====================
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

[Art Kendall]

  oops forgot to paste the syntax.

GET
   FILE='C:\Program
Files\SPSSInc\PASWStatistics18\Samples\English\Employee data.sav'.
DATASET NAME DataSet1 WINDOW=FRONT.
* Chart Builder.
GGRAPH
   /GRAPHDATASET NAME="graphdataset" VARIABLES=jobcat MEANSE(salary,
1)[name="MEAN_salary"
     LOW="MEAN_salary_LOW" HIGH="MEAN_salary_HIGH"] MISSING=LISTWISE
REPORTMISSING=NO
   /GRAPHSPEC SOURCE=INLINE.
BEGIN GPL
   SOURCE: s=userSource(id("graphdataset"))
   DATA: jobcat=col(source(s), name("jobcat"), unit.category())
   DATA: MEAN_salary=col(source(s), name("MEAN_salary"))
   DATA: LOW=col(source(s), name("MEAN_salary_LOW"))
   DATA: HIGH=col(source(s), name("MEAN_salary_HIGH"))
   GUIDE: axis(dim(1), label("Employment Category"))
   GUIDE: axis(dim(2), label("Mean Current Salary"))
   GUIDE: text.footnote(label("Error Bars: +/- 1 SE"))
   SCALE: cat(dim(1), include("1", "2", "3"))
   SCALE: linear(dim(2), include(0))
   ELEMENT: point(position(jobcat*MEAN_salary))
   ELEMENT: interval(position(region.spread.range(jobcat*(LOW+HIGH))),
shape.interior(shape.ibeam))
END GPL.


On 9/17/2010 10:01 AM, UGUR SERBESTER wrote:

> Dear friends
> I want to draw a line graphic Lsmeans (Least square means) and SEM
> (Standard error of mean) values. How can I draw this graphic using
> SPSS 17.
> Thanks to all helps.
>
> Dr. Uğur SERBESTER
> Nigde University
> The Vocational School of Bor
>  Turkiye
> Tel: [phone] / 23
> Fax: [phone]

=====================
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

[Bruce Weaver]

Art Kendall wrote

  I am not sure what you mean by "lsmeans".  Do you mean "adjusted
means" for example from ANCOVA (analysis of covariance)?

--- snip ---

Hi Art.  I believe LSMEANS is the SAS version of EMMEANS.  E.g., look at examples 11.2b and 11.2c here (about halfway down the page):

   http://www.ats.ucla.edu/stat/sas/examples/da/dasas11.htm

Cheers,
Bruce