From 9e0dae397df8c18e7333d2604cae96b2a7927420 Mon Sep 17 00:00:00 2001 From: ranke Date: Fri, 23 Jun 2006 15:33:27 +0000 Subject: - inverse.predict now has a var.s argument instead of the never tested ss argument. This is documented in the updated vignette - loq() now has w.loq and var.loq arguments, and stops with a message if neither are specified and the model has weights. - calplot doesn't stop any more for weighted regression models, but only refrains from drawing prediction bands - Added method = "din" to lod(), now that I actually have it (DIN 32645) and was able to see which approximation is used therein. - removed the demos, as the examples and tests are already partially duplicated - The vignette is more of a collection of various notes, but should certainly be helpful for the user. - Version bump to 0.1-xxx git-svn-id: http://kriemhild.uft.uni-bremen.de/svn/chemCal@16 5fad18fb-23f0-0310-ab10-e59a3bee62b4 --- tests/din32645.R | 6 +++--- tests/din32645.Rout.save | 10 ++++++---- tests/massart97.R | 25 ++++++++++++++++--------- tests/massart97.Rout.save | 47 +++++++++++++++++++++++++++++++++++++---------- 4 files changed, 62 insertions(+), 26 deletions(-) (limited to 'tests') diff --git a/tests/din32645.R b/tests/din32645.R index dc0aee6..e5ffed7 100644 --- a/tests/din32645.R +++ b/tests/din32645.R @@ -1,7 +1,7 @@ -library(chemCal) +require(chemCal) data(din32645) -m <- lm(y ~ x, data=din32645) -inverse.predict(m,3500,alpha=0.01) +m <- lm(y ~ x, data = din32645) +inverse.predict(m, 3500, alpha = 0.01) lod <- lod(m, alpha = 0.01, beta = 0.5) lod(m, alpha = 0.01, beta = 0.01) loq <- loq(m, alpha = 0.01) diff --git a/tests/din32645.Rout.save b/tests/din32645.Rout.save index 10cd1ab..c5ed5a7 100644 --- a/tests/din32645.Rout.save +++ b/tests/din32645.Rout.save @@ -1,6 +1,6 @@ R : Copyright 2006, The R Foundation for Statistical Computing -Version 2.3.0 (2006-04-24) +Version 2.3.1 (2006-06-01) ISBN 3-900051-07-0 R is free software and comes with ABSOLUTELY NO WARRANTY. @@ -15,10 +15,12 @@ Type 'demo()' for some demos, 'help()' for on-line help, or 'help.start()' for an HTML browser interface to help. Type 'q()' to quit R. -> library(chemCal) +> require(chemCal) +Loading required package: chemCal +[1] TRUE > data(din32645) -> m <- lm(y ~ x, data=din32645) -> inverse.predict(m,3500,alpha=0.01) +> m <- lm(y ~ x, data = din32645) +> inverse.predict(m, 3500, alpha = 0.01) $Prediction [1] 0.1054792 diff --git a/tests/massart97.R b/tests/massart97.R index 7170ec4..58119d9 100644 --- a/tests/massart97.R +++ b/tests/massart97.R @@ -1,12 +1,19 @@ -library(chemCal) +require(chemCal) 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) +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) -# The following concords with the book -inverse.predict(m, 15, ws = 1.67) -inverse.predict(m, 90, ws = 0.145) +m <- lm(y ~ x, w = weights) +#calplot(m) + +inverse.predict(m, 15, ws = 1.67) # 5.9 +- 2.5 +inverse.predict(m, 90, ws = 0.145) # 44.1 +- 7.9 + +m0 <- lm(y ~ x) +lod(m0) + +loq(m0) +loq(m, w.loq = 1.67) diff --git a/tests/massart97.Rout.save b/tests/massart97.Rout.save index ae50275..9386a11 100644 --- a/tests/massart97.Rout.save +++ b/tests/massart97.Rout.save @@ -1,6 +1,6 @@ R : Copyright 2006, The R Foundation for Statistical Computing -Version 2.3.0 (2006-04-24) +Version 2.3.1 (2006-06-01) ISBN 3-900051-07-0 R is free software and comes with ABSOLUTELY NO WARRANTY. @@ -15,17 +15,20 @@ Type 'demo()' for some demos, 'help()' for on-line help, or 'help.start()' for an HTML browser interface to help. Type 'q()' to quit R. -> library(chemCal) +> require(chemCal) +Loading required package: chemCal +[1] TRUE > 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) +> 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) -> # The following concords with the book -> inverse.predict(m, 15, ws = 1.67) +> m <- lm(y ~ x, w = weights) +> #calplot(m) +> +> inverse.predict(m, 15, ws = 1.67) # 5.9 +- 2.5 $Prediction [1] 5.865367 @@ -38,7 +41,7 @@ $Confidence $`Confidence Limits` [1] 3.387082 8.343652 -> inverse.predict(m, 90, ws = 0.145) +> inverse.predict(m, 90, ws = 0.145) # 44.1 +- 7.9 $Prediction [1] 44.06025 @@ -52,3 +55,27 @@ $`Confidence Limits` [1] 36.20523 51.91526 > +> m0 <- lm(y ~ x) +> lod(m0) +$x +[1] 5.406637 + +$y +[1] 13.63822 + +> +> loq(m0) +$x +[1] 13.97767 + +$y +[1] 30.62355 + +> loq(m, w.loq = 1.67) +$x +[1] 7.346231 + +$y +[1] 17.90784 + +> -- cgit v1.2.1