Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: AW: st: AW: AW: Plotting 3 way continuous interactions in regression


From   Kris Anderson <[email protected]>
To   [email protected]
Subject   Re: AW: st: AW: AW: Plotting 3 way continuous interactions in regression
Date   Thu, 13 Aug 2009 09:07:48 -0700

That solved it. Thanks!

Martin Weiss wrote:
<>
Ok, let me guess: You are entering these commands from the command line
where "/* slope 1*/" is not allowed as a comment delimiter. So Stata reads
the last part of your -global- which is "SAP" and then continues with the
"/" b/c it does not know about your intention to comment out. Drop those
comments and try again, or run from the do file editor.

My earlier code was used to check whether what you are trying to do is at
all feasible. I tend to post such things so that others can step into the
discussions more easily...



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Kris Anderson
Gesendet: Donnerstag, 13. August 2009 17:38
An: [email protected]
Betreff: Re: st: AW: AW: Plotting 3 way continuous interactions in
regression

Unfortunately, the _SAP was not the problem. It was an artifact of my cut and paste.

The message I receive is after the lincom $HPNHAF /* slope 1*/ command It says SAP/ invalid name.

I am sorry but I don't follow the code below. What is this doing? I am relatively new to coding in Stata.

Martin Weiss wrote:
<>
Apart from the problem mentioned before, your strategy is technically a
little cumbersome but valid...


*************
sysuse auto, clear
reg pr we len he

su he, mean
gl headmean=r(mean)

gl mycovariates /* */ "weight*($headmean)+2*le"

lincom $mycovariates
global b1 = r(estimate)

di $b1
*************



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Martin Weiss
Gesendet: Donnerstag, 13. August 2009 14:06
An: [email protected]
Betreff: st: AW: Plotting 3 way continuous interactions in regression


<>
You use "_SAP" in your -regress- command, but "SAP" in your -global-s....

What exactly does Stata say after which command?



HTH
Martin


-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Kris Anderson
Gesendet: Donnerstag, 13. August 2009 01:54
An: [email protected]
Betreff: st: Plotting 3 way continuous interactions in regression

Hi,

I am stuck on a piece of code that I can't seem to debug. I am trying to plot a 3-way interaction using the FAQ on plotting these interactions with covariates. The code hangs up as I try to compute 4 simple slopes. The program tells me the name of my interaction term is invalid. Can anyone see a problem here? I tried renaming the variable but it didn't
help.
Thanks

regress avgdrink age sex gradedich white hisp csocanx caffil cpn SAF SP AP _SAP if currentdrinker > 0

sum csocanx
global hi=r(max)
global lo=r(min)
sum caffil
global HAF=r(mean)+r(sd)
global LAF=r(mean)-r(sd)
sum cpn
global HPN=r(mean) +r(sd)
global LPN=r(mean) -r(sd)
sum age
global mage=r(mean)
sum gradedich
global mgrade=r(mean)
sum white
global mwhite=r(mean)
sum hisp
global mhisp=r(mean)
global HPNHAF "csocanx + ($HPN)*SP + ($HAF)*SAF + ($HPN)*($HAF)*SAP"
global HPNLAF "csocanx + ($HPN)*SP + ($LAF)*SAF + ($HPN)*($LAF)*SAP"
global LPNHAF "csocanx + ($LPN)*SP + ($HAF)*SAF + ($LPN)*($HAF)*SAP"
global LPNLAF "csocanx + ($LPN)*SP + ($LAF)*SAF + ($LPN)*($LAF)*SAP"
lincom $HPNHAF /* slope 1*/
global b1 = r(estimate)
lincom $HPNLAF /* slope 2*/
global b2 = r(estimate)
lincom $LPNHAF /* slope 3*/
global b3 = r(estimate)
lincom $LPNLAF /* slope 4*/
global b4 = r(estimate)





*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



--
Kristen G. Anderson, Ph.D.
Assistant Professor of Psychology, Reed College
Principal Investigator, Adolescent Health Research Program
Licensed Clinical Psychologist (OR)
3203 SE Woodstock Blvd., Portland, OR 97202
Phone: 503-517-7410
Fax: 503-517-7610
http://academic.reed.edu/psychology/ahrp/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index