User Tools

Site Tools


seminars:stat:220421

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
seminars:stat:220421 [2022/04/09 11:59] qyuseminars:stat:220421 [2022/04/14 23:05] (current) qyu
Line 1: Line 1:
 +<WRAP centeralign>##Statistics Seminar##\\ Department of Mathematical Sciences</WRAP>
 +
 +<WRAP 70% center>
 +^  **DATE:**|Thursday, April 21, 2022 |
 +^  **TIME:**|1:15pm -- 2:15pm |
 +^  **LOCATION:**|Zoom meeting |
 +^  **SPEAKER:**|Mengyu Chen, Binghamton University |
 +^  **TITLE:**|An Empirical Likelihood Approach with Bivariate Data  |
 +</WRAP>
 +\\ 
 +
 +<WRAP center box 80%>
 +<WRAP centeralign>**Abstract**</WRAP>Bivariate data where the marginal distributions differ by a
 +location and
 +scale parameter are considered. Inference about these two parameters
 +is based on the empirical likelihood approach. As the first component and
 +the location and scale transformed second component have the same
 +distribution, there is a large supply of constraint functions. Both known
 +and estimated constraint functions are studied. Wilks' type theorems are
 +obtained for these settings leading to large sample confidence regions and
 +tests. The local asymptotic power of the resulting tests is derived.
 +Finally maximum empirical likelihood estimators of the location and scale
 +parameters are studied and shown to be asymptotically normal. An extensive
 +simulation study supports the theoretical findings.
 +</WRAP>
 +
 +
 +
 +