Seminar Notice
 
                                    Statistical Laboratory
                                    Iowa State University
 
DATE AND TIME:      Tuesday, June 27    2:00 p.m.
 
PLACE:                  Sweeney 1116
 
SPEAKER:               Norma Leyva-Estrada
 
                                                                  
TITLE:  Approximate likelihood-based inference for weight-size distributions
           from sieving data     
 

ABSTRACT

 
In sieving there is a fixed number of sieves with progressively smaller size
openings. To study the size distribution of solid particles using sieving, the
weight (not number) of the particles in each size interval is obtained. This
produces a sample weight-size distribution. We assume that a sample of particles
can be described as randomly selected from a large population until a target
total weight is reached. Also, we assume that the size follows a standard
probability density (lognormal) and that the first and second moments of the
conditional distribution of weight given size can be described with a power law
relationship. Under these assumptions, we obtain approximate maximum likelihood
point and interval estimates of the population weight fractions, based on an
asymptotic multivariate normal distribution. We study the properties of these
estimators via simulation. Standard errors of the maximum likelihood estimates
of weight-size fractions are smaller than those of estimators previously
proposed in the literature, and the confidence intervals hold their nominal
coverage value.      
 
COFFEE:      1:45 a.m., 104 Snedecor Hall
 
Seminar schedules and abstracts are available via WWW:  http://www.stat.iastate.edu/
 

Denise Riker, Undergraduate Secretary
Department of Statistics
Iowa State University
320 Snedecor Hall
Ames, IA  50011
(515) 294-1076