Colloquium

• Home
• About
• Academics
•     Courses
•     Undergraduate
•     Graduate
• Alumni
• Career Guidance
• Giving
• Research
• Resources
• Stat Consulting Center
• Directory
• Contact Us

 

Statistics Colloquium
February 17 (Fri) 11 a.m.
Alavi Commons Room, 6625 Everett Tower

Constrained Statistical Inference in Linear Mixed Models with Applications

Casey M. Jelsema
Department of Statistics
West Virginia University
Morgantown, WV
&
Shyamal D. Peddada
Biostatistics and Computational Biology Branch
National Institute of Environmental Health Sciences
Research Triangle Park, NC

Abstract:
In many applications researchers are interested in testing for inequality constraints in the context of linear fixed and/or mixed effects models. For example, a researcher may wish to test for an increasing response over increasing dose levels. Popular procedures such as ANOVA only test for differences and not trends or patterns in the means. Consequently, not only that they do not answer the underlying scientific question of interest, they could lose power to tests that are designed for testing inequality constraints.

While there exists a large body of literature for performing statistical inference under inequality constraints, user-friendly statistical software for implementing such methods is lacking. In this talk, we discuss constrained inference for linear fixed and/or mixed effects models using residual bootstrap, a general methodology that is reasonably robust to non-normality and can accommodate heteroscedasticity. This bootstrap based methodology, called CLME, is implemented in R using syntax similar to existing linear model packages. The CLME package also contains a graphical interface, enabling a researcher with minimal knowledge of R to easily utilize this more sophisticated model.

Bio:
Casey Jelsema is an Assistant Professor in the Department of Statistics, West Virginia University. He received his Ph.D. in Statistics from Western Michigan University in 2013, under the supervision of Prof. Rajib Paul. Following his graduation, Casey was a Postdoctoral Research Fellow at the National Institute of Environmental Health Sciences.

Shyamal Peddada is the Acting Branch Chief and Principal Investigator of the Biostatistics and Computational Biology Branch of the National Institute of Environmental Health Sciences. He received his PhD from University of Pittsburgh in 1983. Before joining the NIEHS in 2000 he as was a tenured full professor of statistics at the University of Virginia, Charlottesville.

---
All statistics graduate students are expected to attend.

---

Past colloquiums