SMS scnews item created by Rafal Kulik at Mon 16 Apr 2007 0900
Type: Seminar
Distribution: World
Expiry: 20 Apr 2007
Calendar1: 20 Apr 2007 1400-1500
CalLoc1: Carslaw 373
Auth: rkuli(.ststaff;2434.3001)@p818.pc.maths.usyd.edu.au

Statistics Seminar: Robinson -- Empirical Saddlepoint Approximations for Stratified Random Sampling

We would like to invite you to participate in the next seminar at the University of
Sydney.  Note that the venue for the seminar is Carslaw 373.  

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

Empirical Saddlepoint Approximations for Stratified Random Sampling 

 John Robinson (University of Sydney) 

 Friday, 20 April, 2.00pm Carslaw 373 

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

To obtain confidence intervals or tests concerning a finite population mean from simple
random sampling and stratified sampling, it is necessary to use Studentized statistics.
Normal or Student-t approximations have been used for many years.  Booth, Butler and
Hall (JASA, 1994) obtained bootstrap methods for both these situations.  For simple
random samples, Edgeworth approximations were obtained by Sugden and Smith (JRSS B,
1998, 2000) and Dai and Robinson (SPL, 2001) obtained empirical saddlepoint
approximations.  We extend the work on empirical approximations to the case of
stratified random sampling and note that this gives a saddlepoint approximation to the
bootstrap.  This is joint work with Zhishui Hu and Chunsheng Ma.  

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

Please visit: http://www.maths.usyd.edu.au/u/StatSeminar/ for more information about
past and coming seminars.  

Enquiries about the Statistics Seminar: Rafal Kulik, rkuli@maths.usyd.edu.au 


Actions:
ball Calendar (ICS file) download, for import into your favourite calendar application
ball UNCLUTTER for printing
ball AUTHENTICATE to mark the scnews item as read
School members may try to .