Fix inverse predictions for replicate measurements

For details, see NEWS.md

6 files changed, 61 insertions, 27 deletions

diff --git a/man/din32645.Rd b/man/din32645.Rd
index 12c641a..ffcbaed 100644
--- a/man/din32645.Rd
+++ b/man/din32645.Rd
@@ -10,19 +10,18 @@
   A dataframe containing 10 rows of x and y values.
 }
 \examples{
-data(din32645)
 m <- lm(y ~ x, data = din32645)
 calplot(m)
 
 ## Prediction of x with confidence interval
-(prediction <- inverse.predict(m, 3500, alpha = 0.01))
+prediction <- inverse.predict(m, 3500, alpha = 0.01)
 
 # This should give 0.07434 according to test data from Dintest, which 
 # was collected from Procontrol 3.1 (isomehr GmbH) in this case
-round(prediction$Confidence,5)
+round(prediction$Confidence, 5)
 
 ## Critical value:
-(crit <- lod(m, alpha = 0.01, beta = 0.5))
+crit <- lod(m, alpha = 0.01, beta = 0.5)
 
 # According to DIN 32645, we should get 0.07 for the critical value
 # (decision limit, "Nachweisgrenze")
@@ -40,12 +39,12 @@ round(lod.din$x, 2)
 ## Limit of quantification
 # This accords to the test data coming with the test data from Dintest again, 
 # except for the last digits of the value cited for Procontrol 3.1 (0.2121)
-(loq <- loq(m, alpha = 0.01))
-round(loq$x,4)
+loq <- loq(m, alpha = 0.01)
+round(loq$x, 4)
 
 # A similar value is obtained using the approximation 
 # LQ = 3.04 * LC (Currie 1999, p. 120)
-3.04 * lod(m,alpha = 0.01, beta = 0.5)$x
+3.04 * lod(m, alpha = 0.01, beta = 0.5)$x
 }
 \references{
   DIN 32645 (equivalent to ISO 11843), Beuth Verlag, Berlin, 1994
diff --git a/man/inverse.predict.Rd b/man/inverse.predict.Rd
index 26ba6b8..373623e 100644
--- a/man/inverse.predict.Rd
+++ b/man/inverse.predict.Rd
@@ -52,7 +52,10 @@
 }
 \note{
   The function was validated with examples 7 and 8 from Massart et al. (1997). 
-}
+  Note that the behaviour of inverse.predict changed with chemCal version
+  0.2.1. Confidence intervals for x values obtained from calibrations with
+  replicate measurements did not take the variation about the means into account.
+  Please refer to the vignette for details.}
 \references{
   Massart, L.M, Vandenginste, B.G.M., Buydens, L.M.C., De Jong, S., Lewi, P.J.,
   Smeyers-Verbeke, J. (1997) Handbook of Chemometrics and Qualimetrics: Part A,
@@ -60,10 +63,26 @@
 }
 \examples{
 # This is example 7 from Chapter 8 in Massart et al. (1997)
-data(massart97ex1)
 m <- lm(y ~ x, data = massart97ex1)
 inverse.predict(m, 15)        #  6.1 +- 4.9
 inverse.predict(m, 90)        # 43.9 +- 4.9
 inverse.predict(m, rep(90,5)) # 43.9 +- 3.2
+
+# For reproducing the results for replicate standard measurements in example 8,
+# we need to do the calibration on the means when using chemCal > 0.2
+weights <- with(massart97ex3, {
+  yx <- split(y, x)
+  ybar <- sapply(yx, mean)
+  s <- round(sapply(yx, sd), digits = 2)
+  w <- round(1 / (s^2), digits = 3)
+})
+
+massart97ex3.means <- aggregate(y ~ x, massart97ex3, mean)
+
+m3.means <- lm(y ~ x, w = weights, data = massart97ex3.means)
+
+inverse.predict(m3.means, 15, ws = 1.67)  # 5.9 +- 2.5
+inverse.predict(m3.means, 90, ws = 0.145) # 44.1 +- 7.9
+
 }
 \keyword{manip}
diff --git a/man/lod.Rd b/man/lod.Rd
index 04aac1f..ce32670 100644
--- a/man/lod.Rd
+++ b/man/lod.Rd
@@ -74,7 +74,6 @@
   Analytica Chimica Acta 391, 105 - 126.
 }
 \examples{
-data(din32645)
 m <- lm(y ~ x, data = din32645)
 lod(m) 
 
diff --git a/man/loq.Rd b/man/loq.Rd
index 082cf34..c247f34 100644
--- a/man/loq.Rd
+++ b/man/loq.Rd
@@ -68,9 +68,7 @@
     and therefore not tested. Feedback is welcome.
 }
 \examples{
-data(massart97ex3)
-attach(massart97ex3)
-m <- lm(y ~ x)
+m <- lm(y ~ x, data = massart97ex1)
 loq(m)
 
 # We can get better by using replicate measurements
diff --git a/man/massart97ex3.Rd b/man/massart97ex3.Rd
index efdcf02..d7f8d00 100644
--- a/man/massart97ex3.Rd
+++ b/man/massart97ex3.Rd
@@ -5,29 +5,32 @@
 \description{
   Sample dataset from p. 188 to test the package.
 }
-\usage{data(massart97ex3)}
+\usage{massart97ex3}
 \format{
   A dataframe containing 6 levels of x values with 5
   observations of y for each level.
 }
 \examples{
-data(massart97ex3)
-attach(massart97ex3)
-yx <- split(y, x)
-ybar <- sapply(yx, mean)
-s <- round(sapply(yx, sd), digits = 2)
-w <- round(1 / (s^2), digits = 3)
-weights <- w[factor(x)]
-m <- lm(y ~ x, w = weights)
-calplot(m)
+# For reproducing the results for replicate standard measurements in example 8,
+# we need to do the calibration on the means when using chemCal > 0.2
+weights <- with(massart97ex3, {
+  yx <- split(y, x)
+  ybar <- sapply(yx, mean)
+  s <- round(sapply(yx, sd), digits = 2)
+  w <- round(1 / (s^2), digits = 3)
+})
+
+massart97ex3.means <- aggregate(y ~ x, massart97ex3, mean)
+
+m3.means <- lm(y ~ x, w = weights, data = massart97ex3.means)
 
 # The following concords with the book p. 200
-inverse.predict(m, 15, ws = 1.67)  # 5.9 +- 2.5
-inverse.predict(m, 90, ws = 0.145) # 44.1 +- 7.9
+inverse.predict(m3.means, 15, ws = 1.67)  # 5.9 +- 2.5
+inverse.predict(m3.means, 90, ws = 0.145) # 44.1 +- 7.9
 
 # The LOD is only calculated for models from unweighted regression
 # with this version of chemCal
-m0 <- lm(y ~ x) 
+m0 <- lm(y ~ x, data = massart97ex3) 
 lod(m0)
 
 # Limit of quantification from unweighted regression
@@ -38,7 +41,7 @@ loq(m0)
 # If we are not using a variance function, we can use the weight from
 # the above example as a first approximation (x = 15 is close to our
 # loq approx 14 from above).
-loq(m, w.loq = 1.67)
+loq(m3.means, w.loq = 1.67)
 # The weight for the loq should therefore be derived at x = 7.3 instead
 # of 15, but the graphical procedure of Massart (p. 201) to derive the 
 # variances on which the weights are based is quite inaccurate anyway. 
diff --git a/man/rl95_toluene.Rd b/man/rl95_toluene.Rd
new file mode 100644
index 0000000..1faafdc
--- /dev/null
+++ b/man/rl95_toluene.Rd
@@ -0,0 +1,16 @@
+\name{rl95_toluene}
+\docType{data}
+\alias{rl95_toluene}
+\title{Toluene amounts by GC/MS as reported by Rocke and Lorenzato (1995)}
+\description{
+  Dataset reproduced from Table 4 in Rocke and Lorenzato (1995).
+}
+\format{
+  A dataframe containing four replicate observations for each 
+  of the six calibration standards.
+}
+\source{
+  Rocke, David M. und Lorenzato, Stefan (1995) A two-component model for
+  measurement error in analytical chemistry. Technometrics 37(2), 176-184.
+}
+\keyword{datasets}