The query was to find a 95% confidence interval of Y=A*B/K. A simple method
would be to take logs giving
Log(Y)=log(A)+log(B)-log(K)
If these are independent then var(log(Y))=var(A)/A2+var(B)/B2 +var(K)/K2 but
K is constant so the last term drops out. You can get a confidence interval
for log(Y) and then exponentiate the lower and upper limits. Note that the
logs here are natural logarithms.
Peter A. Lachenbruch
Director, Division of Biostatistics, OBE/CBER
Tel: (301) 827-3320
FAX: (301) 827-5218
*
* 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/
