Student Seminar Series - November 9, 2006
University of Minnesota
School of Statistics
College of Liberal Arts
An
Application of Empirical Sampling Study in Biomedical Science
Qiaoyang
Liu
Thursday, November 9, 2006
10:00 AM, 300
Ford Hall
Minneapolis, East Bank Campus
Refreshments at
9:30 AM
300 Ford Hall
Abstract
In
biomedical science, a good sampling plan can
save time to reduce some boring work like counting cells in mouse brain
with
enough precision. We comment on 3 sampling plans in the paper: Simple
Random
Sampling, Systematic Random Sampling, PPS Sampling, where the unbiased
estimator for the number of cells and its SE are simply discussed. The
simulation study method based on the data available is introduced and
the
comparison of the Root Mean Squared Error (RMSE) calculated from the
formulas
and the Monte Carlo Standard Error (MCSE) for each sampling plan
confirms its
feasibility. The Systematic Random Sampling and PPS Sampling plans are
decided
to be the best. It's also shown how many slices are required depend on
sampling
plan and desired