percentile.ple: Calculate Nonparametric Estimate of Xp and Confidence Limits
Description
Find Xp, the 100pth percentile, and the $100\gamma$%
nonparametric confidence limits from PLE of F(x).
Usage
percentile.ple(dd, p = 0.95, gam = 0.95, interp = TRUE)
Arguments
dd
An n by 2 matrix or data frame with
x (exposure) variable in column 1, and
det= 0 for non-detect or 1 for detect in column 2
p
Find x such that the PLE of F(x) = p. Default 0.95
gam
one-sided confidence level $\gamma$. Default is 0.95
interp
if interp is TRUE use linear interpolation. Default TRUE
Value
A list with components:
Xp
PLE of the 100pth percentile
LXp
PLE of LX(p,$\gamma$) the $100*\gamma$% LCL for Xp
UXp
PLE of UX(p,$\gamma$) the $100*\gamma$% UCL for Xp
p
probability for Xp the 100pth percentile
gam
one-sided confidence level $\gamma$. Default is 0.95
Details
Find Xp the 100pth percentile and confidence limits from the
PLE of F(x) -- see plekm for additional details.
If interp is TRUE use linear interpolation; otherwise, the upper confidence
limit (UCL) for Xp, UX(p,$\gamma$), is the smallest value of $x$ such that
the LCL for F(x) is $\ge$ p, the lower confidence limit (LCL),
LX(p,$\gamma$), is the largest value of $x$ such that the UCL for F(x)
is $\le$ p.
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
# use data from example 2 in ORNL/TM-2005/52 to calculate# 95 percent UCL for 95th percentiledata(beTWA)
unlist(percentile.ple(beTWA))
unlist(percentile.ml(beTWA)) # compare ML estimates