LoBD: Cancer drug data use to provide an example of the use of the skew power distributions.
Description
A portion of an experiment to determine the limit of blank/limit of detection in a biochemical assay.
Usage
LoBD
Arguments
source
Used as an illustrative example for Box-Cox type transformations with
negative readings in Hawkins and Weisberg (2015).
For examples of its use, see skewPower.
Details
Important characteristics of a clinical chemistry assay are its
limit of blank (LoB), and its limit of detection (LoD).
The LoB, conceptually the highest reading likely to be obtained from
a zero-concentration sample, is defined operationally by the upper 95%
point of readings obtained from samples that do not contain the analyte.
The LoD, conceptually the lowest level of analyte that can be reliably
determined not to be blank, is defined operationally as true value at
which there is a 95% chance of the reading being above the LoB.
These data are from a portion of a LoB/D study
of an assay for a drug used to treat certain cancers.
Twelve pools were used, four of them blanks of different types,
and eight with successively increasing drug levels. The 8 columns
of the data set refer to measurements made using different instruments I
and reagent lots L.
References
Hawkins, D. and Weisberg, S. (2015)
Combining the Box-Cox Power and Generalized Log Transformations to
Accommodate Negative Responses,
submitted for publication.