This preview shows pages 1–8. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: 96 S n < < X + 1 . 96 S n ) . 95 95% confidence interval ( = 0.05) of an estimate is: ( X 1 . 96 S/ n ) 6 When to stop a simulation? Repeatedly generate data (sample) until 100(1 ) percent confidence interval estimate of is less than I Generate at least 100 data values. Continue generate, until you generated k values such that The 100(1 ) percent confidence interval of estimate is ( X z / 2 S/ k, X + z / 2 S/ k ) 2 z / 2 S/ k < I 7 Fix no. of simulation runs Suppose we only simulate 100 times k=100 What is the 95% confidence interval? ( X z / 2 S/ k, X + z / 2 S/ k ) ( X . 196 S/ k, X + 0 . 196 S/ k ) Example: Generating Expo. Distribution 8...
View
Full
Document
This note was uploaded on 01/14/2012 for the course CDA 6530 taught by Professor Zou during the Fall '11 term at University of Central Florida.
 Fall '11
 Zou

Click to edit the document details