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, 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 <>
Subject   Re: st: lms command line
Date   Thu, 2 Dec 2010 15:05:51 -0500

Gilberto Kac <> :
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
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 <> 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:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index