Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: lms command line


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: lms command line
Date   Thu, 2 Dec 2010 15:05:51 -0500

Gilberto Kac <kacetal@gmail.com> :
I have not used -lms- but it is easy enough to estimate a -qreg- (in
time or powers of time or splines in time) or local -qreg-s, e.g.

clear all
u weight age using http://www.stata-press.com/data/r11/nhanes2.dta
g q20=.
g q80=.
qui forv i=20/74 {
 g kw=max(5-abs(`i'-age),0)
 qreg weight age [aw=kw], q(20)
 predict hat
 replace q20=hat if age==`i'
 drop hat
 qreg weight age [aw=kw], q(80)
 predict hat
 replace q80=hat if age==`i'
 drop hat kw
 }
sort age
sc weight age, mc(gs12)||line q20 q80 age, leg(order(2 - 3))


On Thu, Dec 2, 2010 at 2:47 PM, Gilberto Kac <kacetal@gmail.com> wrote:
> Hi,
>
> I have been trying to estimate a lms for a prospective dataset of
> weight during pregnancy. I want to estimate selected percentiles for
> weight as dependent and time as independent in days as continuos or
> can be visit number. I am trying to write the command line but as I am
> new using stata I am having a hard time. I would appreciate if someone
> could help me here.
>
> cheers
*
*   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 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index