STAND (version 2.0)

cansdata: Container Data Used To Evaluate Beryllium Surface Contamination

Description

Surface wipe samples obtained from containers that are used to ship beryllium components.

Usage

data(cansdata)

Format

A data frame with 120 observations on the following 4 variables:

x

Surface wipe sample $\mu g/100cm^2$

det

1 if detect, 0 if non-detect

strata

a factor with levels A and B

sample

a factor with levels 1 and 2

Details

In a scoping survey, the investigator decides to divide the survey unit into two strata: A, used recently, and B, not used for several years. The specified limit that is used to determine if the survey unit is contaminated is $L = 0.2\mu g/100cm^2$. An initial sample of n = 30 was obtained from each stratum (sample = 1). The initial survey produced discrepant results that were hard to interpret. A second sample of n = 30 surface wipe samples was obtained from strata A and B. Results below the limit of quantification are reported as non-detects.

References

Frome, E. L. and Wambach, P. F. (2005), " Statistical Methods and Software for the Analysis of Occupational Exposure Data with Non-Detectable Values," ORNL/TM-2005/52,Oak Ridge National Laboratory, Oak Ridge, TN 37830. Available at: http://www.csm.ornl.gov/esh/aoed/ORNLTM2005-52.pdf

Examples

data(cansdata)
#     subset container data into stratum A and stratum B
sa60 <- cansdata[ cansdata$st=="A",] ; Ia <- "Be Samples From  Stratum A"
sb60 <- cansdata[ cansdata$st=="B",] ; Ib <- "Be Samples From  Stratum B"
mle.sa60 <- unlist(lnorm.ml(sa60))  # MLEs for stratum A
mle.sb60 <- unlist(lnorm.ml(sb60)) 
#     print MLE for stratum A and B
round( data.frame(mle.sa60,mle.sb60),3)
#
# Q-Q plot for each stratum
par( mfcol=c(1,2) )
qq.lnorm(plend(sa60),mle.sa60[1,2],ylim=c(0.01,1.2),xlim=c(-0.5,2.5),main=Ia )
qq.lnorm(plend(sb60),mle.sb60[1,2],ylim=c(0.01,1.2),xlim=c(-0.5,2.5),main=Ib )
#   list all summary statistics by Strata
round(IH.summary(cansdata,L=0.2,bcol=3),4)