Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: longitudinal data with non-detectable measurements


From   "Joseph Coveney" <jcoveney@bigplanet.com>
To   "Statalist" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: longitudinal data with non-detectable measurements
Date   Mon, 12 May 2008 22:02:27 +0900

It dawned on me that the illustrative do-file appended to the earlier post
omitted a line of code.

The lines

quietly centile xg, centile(5)
quietly replace a = .b if a < r(c_1)
label define LOQ .b "< LOQ"
label values a LOQ
intcens a b, distribution(gam) nolog

need to include one setting the right-hand response variable to the limit of
quantitation (detection) in order for -intcens- to give correct estimates

quietly centile xg, centile(5)
quietly replace a = .b if a < r(c_1)
quietly replace b = r(c_1) if b < r(c_1) // <- here
label define LOQ .b "< LOQ"
label values a LOQ
intcens a b, distribution(gam) nolog

So, for values below the hormone assay's minimum detectable value (MDL),
Leny would set a as missing and b to the MDL, followed by the predictors.

Joseph Coveney


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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   |   What's new   |   Site index