Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: marginsplot after xtmixed with square term
From
Scott Merryman <[email protected]>
To
[email protected]
Subject
Re: st: marginsplot after xtmixed with square term
Date
Wed, 13 Mar 2013 21:16:51 -0500
The first i.pressure term was superfluous.
Terms like c.repl##c.repl mean repl repl*repl
c.repl##c.repl##i.pressure is the same as repl i.pressure
repl*i.pressure repl*repl repl*repl*i.pressure
See -help fvvarlist- for more information
Scott
On Wed, Mar 13, 2013 at 8:55 PM, Sun, Wensheng <[email protected]> wrote:
> Hi Scott,
>
> It works. By the way, could you explain what "i.pressure c.repl##c.repl##i.pressure" means?
>
> Thank you very much!
>
> Wensheng
>
> ________________________________________
> From: [email protected] [[email protected]] On Behalf Of Scott Merryman [[email protected]]
> Sent: Wednesday, March 13, 2013 8:09 PM
> To: [email protected]
> Subject: Re: st: marginsplot after xtmixed with square term
>
> Stata does not know that repl2 is the square of repl.
>
> Try:
>
>
> webuse acmemanuf
> lowess y repl, by(pressure)
> //gen repl2=repl^2
> gen id=.
> replace id=temp if pressure==1
> replace id=temp+3 if pressure==2
> replace pressure=0 if pressure==1
> replace pressure=1 if pressure==2
> xtmixed y i.pressure c.repl##c.repl##i.pressure || id: repl,
> cov(uns) res(ind) mle variance
> margins pressure, at(repl=(1(1)10))
> marginsplot
>
> Scott
>
>
> On Wed, Mar 13, 2013 at 12:43 PM, Sun, Wensheng <[email protected]> wrote:
>> Please help! Marginsplot after xtmixed model contend square-term (wish to get concaved curves instead of straight lines).
>> webuse acmemanuf
>> lowess y repl, by(pressure)
>> gen repl2=repl^2
>> gen id=.
>> replace id=temp if pressure==1
>> replace id=temp+3 if pressure==2
>> replace pressure=0 if pressure==1
>> replace pressure=1 if pressure==2
>> xtmixed y c.repl## i.pressure c.repl2##i.pressure || id: repl, cov(uns) res(ind) mle variance
>> margins pressure, at(repl=(1(1)10))
>> marginsplot
>>
>> I expected to get concaved curves from marginsplot like I usually got from modeling estimates with square terms; however, what I got here were two straight lines. Please help me to fix my codes.
>>
>> Thank you very much!
>>
>> Wensheng
>> *
>> * For searches and help try:
>> * http://www.stata.com/help.cgi?search
>> * http://www.stata.com/support/faqs/resources/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/faqs/resources/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/faqs/resources/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/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/