diff options
Diffstat (limited to 'man/loq.Rd')
| -rw-r--r-- | man/loq.Rd | 58 |
1 files changed, 27 insertions, 31 deletions
@@ -5,14 +5,17 @@ \alias{loq.default} \title{Estimate a limit of quantification (LOQ)} \usage{ - loq(object, \dots, alpha = 0.05, k = 3, n = 1, w = "auto") + loq(object, \dots, alpha = 0.05, k = 3, n = 1, w.loq = "auto", + var.loq = "auto") } \arguments{ \item{object}{ A univariate model object of class \code{\link{lm}} or \code{\link[MASS:rlm]{rlm}} with model formula \code{y ~ x} or \code{y ~ x - 1}, - optionally from a weighted regression. + optionally from a weighted regression. If weights are specified + in the model, either \code{w.loq} or \code{var.loq} have to + be specified. } \item{alpha}{ The error tolerance for the prediction of x values in the calculation. @@ -29,53 +32,46 @@ The number of replicate measurements for which the LOQ should be specified. } - \item{w}{ + \item{w.loq}{ The weight that should be attributed to the LOQ. Defaults to one for unweighted regression, and to the mean of the weights for weighted regression. See \code{\link{massart97ex3}} for an example how to take advantage of knowledge about the variance function. } + \item{var.loq}{ + The approximate variance at the LOQ. The default value is + calculated from the model. + } } \value{ The estimated limit of quantification for a model used for calibration. } \description{ - A useful operationalisation of a limit of quantification is simply the - solution of the equation + The limit of quantification is the x value, where the relative error + of the quantification given the calibration model reaches a prespecified + value 1/k. Thus, it is the solution of the equation \deqn{L = k c(L)}{L = k * c(L)} - where c(L) is half of the length of the confidence interval at the limit L as - estimated by \code{\link{inverse.predict}}. By virtue of this formula, the - limit of detection is the x value, where the relative error - of the quantification with the given calibration model is 1/k. + where c(L) is half of the length of the confidence interval at the limit L + (DIN 32645, equivalent to ISO 11843). c(L) is internally estimated by + \code{\link{inverse.predict}}, and L is obtained by iteration. } \note{ - IUPAC recommends to base the LOQ on the standard deviation of the - signal where x = 0. The approach taken here is to my knowledge - original to the chemCal package. + - IUPAC recommends to base the LOQ on the standard deviation of the signal + where x = 0. + - The calculation of a LOQ based on weighted regression is non-standard + and therefore not tested. Feedback is welcome. } \examples{ data(massart97ex3) attach(massart97ex3) - m0 <- lm(y ~ x) - loq(m0) - - # Now we use a weighted regression - yx <- split(y,factor(x)) - s <- round(sapply(yx,sd),digits=2) - w <- round(1/(s^2),digits=3) - weights <- w[factor(x)] - mw <- lm(y ~ x,w=weights) - loq(mw) - - # In order to define the weight at the loq, we can use - # the variance function 1/y for the model - mwy <- lm(y ~ x, w = 1/y) + m <- lm(y ~ x) + loq(m) - # Let's do this with one iteration only - loq(mwy, w = 1 / predict(mwy,list(x = loq(mwy)$x))) - - # We can get better by doing replicate measurements - loq(mwy, n = 3, w = 1 / predict(mwy,list(x = loq(mwy)$x))) + # We can get better by using replicate measurements + loq(m, n = 3) +} +\seealso{ + Examples for \code{\link{din32645}} } \keyword{manip} |