Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Re: Simulation


From   Leonelo Bautista <lebautista@wisc.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: RE: Re: Simulation
Date   Mon, 12 Apr 2004 16:04:15 -0500

Thanks Tom. It works.

Leonelo 

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Steichen
Sent: Monday, April 12, 2004 10:00 AM
To: statalist@hsphsun2.harvard.edu
Subject: st: Re: Simulation

No need for -simulate-, Leonelo... just do it directly.

Note that there are a number of assumptions about distributions...   I
assume A is normally distributed and the odds ratio, B, is log normal.
Also, I assume that se(B) is really se(log(B)), which is what we usually
have for an OR.

Please note that this approach clears your existing dataset.  Be sure it
is
saved before you do this.  Change the -set obs 10000- to whatever size
you
want and plug your observed means, se's and K in below that.

You can plot Y after this via
   . histogram Y

Tom

----- leb_sim.do ----------------------------------------------------

clear all

set obs 10000

local meanA = 123
local seA = 3
local meanB = 2.1
local selogB = .5
local K = 4

gen A = `meanA' + `seA' * invnorm(uniform())
gen B = exp( log(`meanB') + `selogB' * invnorm(uniform()) )
gen Y = (A * B) / `K'

sort Y

local l025 = .025 * _N
local u025 = .975 * _N

di "95% CI of Y: (" Y[`l025'] ", " Y[`u025'] ")"

---------------------------------------------------------------------

----- Original Message ----- 
From: "Leonelo Bautista" <lebautista@wisc.edu>
To: <statalist@hsphsun2.harvard.edu>
Sent: Monday, April 12, 2004 11:05 AM
Subject: st: Simulation


> I'm trying to obtain 95% confidence intervals and standard errors from
> the following quantity (Y):
>
> Y= (A x B)/K
>
> Where, A is the mean of a continuous variable; B is an odds ratio; and
K
> is a constant. A and B are calculated from published reports, and I
can
> only obtain their standard error (SE) from the reported 95% confidence
> interval. Therefore, I have A and SE(A), B and SE(B), and K.
>
> I've checked the "simulate" command, but I'm not savvy enough to write
a
> do file to accomplish this task. Any help or suggestion would be
> appreciated.
>
>
> Leonelo E. Bautista, MD, DrPH
> Assistant Professor
> University of Wisconsin Medical School
> Population Health Sciences
> 610 Walnut Street, 703 WARF
> Madison, WI 53726-2397
> Phone: (608)265-6176
> Fax: (608)263-2820
>
>
>
> *
> *   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/
>

*
*   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/


*
*   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