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: Age-specific reference intervals (xrigls) - no equation for SD?
From
Nick Cox <[email protected]>
To
[email protected]
Subject
Re: st: Age-specific reference intervals (xrigls) - no equation for SD?
Date
Wed, 6 Jun 2012 21:59:25 +0100
-xrigls- is a user-written command, as you are asked to explain. It
was originally published in 1997 in the STB and is maintained by
Patrick Royston, who is not a member of Statalist. My guess from the
lack of response to the question is that you are best advised to email
Patrick directly for support.
Nick
On Wed, Jun 6, 2012 at 8:54 PM, Sofia Ramiro <[email protected]> wrote:
>
> I sent this question some days ago but did not get any answer, so I send it again. Please let me know if the problem is my question not being clear enough or missing some information.
>> > I am trying to define age-specific reference intervals with the command xrigls.
>
>> >
>> > However, when running it, for some of the variables for which I want to define the age intervals I get an equation for the mean (with the corresponding power), but no equation for the SD - example below. I don't understand why. Can any of you explain this?
>> > Are the values derived without the SD equation also right?
>> > I don't understand why in the 1st table (FP powers) the change appears always as 0. I inspected the data and there is variation in this variable and throughout the different ages.
>> >
>> >
>> > . xrigls schober15 age if sample==1, fp(m:df 4,s:df 2) centile(2.5 10 25 75 90 97.5) detail
>> >
>> > --- FP Powers ---
>> > Cycle Mean SD Deviance Change Residual SS
>> > -----------------------------------------------------------------
>> > 0 1 1217.262 0.000 509.4298
>> > 1 1 1217.262 0.000 509.4298
>> > 2 1 1217.262 0.000 509.4298
>> >
>> > Final deviance = 1217.262 (393 observations).
>> > Power(s) for mean curve = 1.
>> >
>> > Regression for mean curve
>> > -------------------------
>> > (sum of wgt is 3.4287e+02)
>> >
>> > Source | SS df MS Number of obs = 393
>> > -------------+------------------------------ F( 1, 391) = 24.05
>> > Model | 31.3308787 1 31.3308787 Prob > F = 0.0000
>> > Residual | 509.429806 391 1.30288953 R-squared = 0.0579
>> > -------------+------------------------------ Adj R-squared = 0.0555
>> > Total | 540.760685 392 1.37949154 Root MSE = 1.1414
>> >
>> > ------------------------------------------------------------------------------
>> > schober15 | Coef. Std. Err. t P>|t| [95% Conf. Interval]
>> > -------------+----------------------------------------------------------------
>> > age | -.0203814 .0041562 -4.90 0.000 -.0285528 -.01221
>> > _cons | 7.191451 .1913316 37.59 0.000 6.815284 7.567619
>> > ------------------------------------------------------------------------------
>> >
*
* 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/