Re: st: Standard error of the estimate for svy: reg

[Steven Samuels <sjhsamuels@earthlink.net>]

Lineless Line

Here is a program to compute an estimate and C.I. for the RMSE or SER  
after -svy: reg- .   I did not apply a bias correction for the number  
of predictors  because I don't know how to do it.  However the bias  
should be small for large sample size. The concerns that Stas and I  
have about presenting this estimate still apply.

Steve


/***************************CODE FOLLOWS***************/

/* First, a program to compute a 95% CI after -nlcom- has estimated a  
parameter on the log scale*/

capture program drop _all
program antilog
local lparm  el(r(b),1,1)
local se    sqrt(el(r(V),1,1))
local bound  invttail(e(df_r),.025)*`se'
local parm  exp(`lparm')
local ll  exp(`lparm'  - `bound')
local ul  exp( `lparm' + `bound')
di  "parm =" `parm'  "    llim = " `ll'  "   ul = " `ul'
end

webuse nhanes2, clear
svyset
svy : reg weight height
predict predicted
display "number of predictors  = "  e(df_m)

gen resid= weight-predicted
gen resid2=resid*resid

svy: mean  resid2
nlcom .5*log(_b[resid2])

antilog











*
*   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/