R Under development (unstable) (2023-08-20 r84995 ucrt) -- "Unsuffered Consequences" Copyright (C) 2023 The R Foundation for Statistical Computing Platform: x86_64-w64-mingw32/x64 R is free software and comes with ABSOLUTELY NO WARRANTY. You are welcome to redistribute it under certain conditions. Type 'license()' or 'licence()' for distribution details. R is a collaborative project with many contributors. Type 'contributors()' for more information and 'citation()' on how to cite R or R packages in publications. 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. > require(DoE.wrapper) Loading required package: DoE.wrapper Loading required package: FrF2 Loading required package: DoE.base Loading required package: grid Loading required package: conf.design Attaching package: 'DoE.base' The following objects are masked from 'package:stats': aov, lm The following object is masked from 'package:graphics': plot.design The following object is masked from 'package:base': lengths Loading required package: rsm > ## try out all available designs with and without factor names > options(warn=-1) > > set.seed(1234) > > ## design with factor.names and constraint > plan <- Dopt.design(36,factor.names=list(eins=c(100,250),zwei=c(10,30),drei=c(-25,25)), + nlevels=c(4,3,6), + formula=~quad(.), + constraint="!(eins>=200 & zwei==30 & drei==25)") creating full factorial with 72 runs ... > summary(plan) Call: Dopt.design(36, factor.names = list(eins = c(100, 250), zwei = c(10, 30), drei = c(-25, 25)), nlevels = c(4, 3, 6), formula = ~quad(.), constraint = "!(eins>=200 & zwei==30 & drei==25)") Experimental design of type Dopt 36 runs Factor settings (scale ends): eins zwei drei 1 100 10 -25 2 150 20 -15 3 200 30 -5 4 250 5 5 15 6 25 Optimality criteria: D Dea A G 7780.44617 0.50700 22.87199 0.59600 The design itself: eins zwei drei 1 200 10 -25 2 150 30 25 3 200 20 -25 4 100 10 15 5 100 30 -15 6 200 30 15 7 150 20 5 8 250 20 25 9 200 30 -25 10 200 20 25 11 250 20 -25 12 200 10 -5 13 250 30 5 14 200 10 25 15 100 10 25 16 100 30 25 17 100 10 -15 18 250 10 -15 19 150 10 25 20 100 30 -25 21 100 20 -25 22 250 10 25 23 250 30 -5 24 100 20 -5 25 200 20 -5 26 100 30 5 27 250 30 -25 28 100 20 25 29 250 30 15 30 250 10 15 31 150 30 -25 32 100 20 15 33 100 10 -25 34 250 30 -15 35 250 10 -25 36 250 10 5 class=design, type= Dopt > design.info(plan) $type [1] "Dopt" $nruns [1] 36 $nfactors [1] 3 $factor.names $factor.names$eins [1] 100 150 200 250 $factor.names$zwei [1] 10 20 30 $factor.names$drei [1] -25 -15 -5 5 15 25 $nlevels [1] 4 3 6 $replications [1] 1 $repeat.only [1] FALSE $randomize [1] TRUE $seed NULL $creator Dopt.design(36, factor.names = list(eins = c(100, 250), zwei = c(10, 30), drei = c(-25, 25)), nlevels = c(4, 3, 6), formula = ~quad(.), constraint = "!(eins>=200 & zwei==30 & drei==25)") $quantitative eins zwei drei TRUE TRUE TRUE $digits NULL $constraint [1] "!(eins>=200 & zwei==30 & drei==25)" $formula ~(eins + zwei + drei)^2 + I(eins^2) + I(zwei^2) + I(drei^2) $optimality.criteria $optimality.criteria$D [1] 7780.446 $optimality.criteria$Dea [1] 0.507 $optimality.criteria$A [1] 22.87199 $optimality.criteria$G [1] 0.596 $response.names NULL > run.order(plan) run.no.in.std.order run.no run.no.std.rp 1 3 1 3 2 70 2 70 3 7 3 7 4 49 4 49 5 21 5 21 6 59 6 59 7 42 7 42 8 68 8 68 9 11 9 11 10 67 10 67 11 8 11 8 12 27 12 27 13 48 13 48 14 63 14 63 15 61 15 61 16 69 16 69 17 13 17 13 18 16 18 16 19 62 19 62 20 9 20 9 21 5 21 5 22 64 22 64 23 36 23 36 24 29 24 29 25 31 25 31 26 45 26 45 27 12 27 12 28 65 28 65 29 60 29 60 30 52 30 52 31 10 31 10 32 53 32 53 33 1 33 1 34 24 34 24 35 4 35 4 36 40 36 40 > cor(plan) eins zwei drei eins 1.00000000 -0.02600157 -0.06079573 zwei -0.02600157 1.00000000 -0.11562310 drei -0.06079573 -0.11562310 1.00000000 > y <- round(rnorm(36), 4) > r.plan <- add.response(plan, y) > summary(r.plan) Call: Dopt.design(36, factor.names = list(eins = c(100, 250), zwei = c(10, 30), drei = c(-25, 25)), nlevels = c(4, 3, 6), formula = ~quad(.), constraint = "!(eins>=200 & zwei==30 & drei==25)") Experimental design of type Dopt 36 runs Factor settings (scale ends): eins zwei drei 1 100 10 -25 2 150 20 -15 3 200 30 -5 4 250 5 5 15 6 25 Optimality criteria: D Dea A G 7780.44617 0.50700 22.87199 0.59600 Responses: [1] y The design itself: eins zwei drei y 1 200 10 -25 -2.0782 2 150 30 25 0.4852 3 200 20 -25 0.6968 4 100 10 15 0.1855 5 100 30 -15 0.7007 6 200 30 15 0.3117 7 150 20 5 0.7605 8 250 20 25 1.8425 9 200 30 -25 1.1124 10 200 20 25 0.0327 11 250 20 -25 -1.1144 12 200 10 -5 0.4181 13 250 30 5 -0.4002 14 200 10 25 1.4935 15 100 10 25 -1.6071 16 100 30 25 -0.4158 17 100 10 -15 0.4220 18 250 10 -15 -0.1517 19 150 10 25 -0.6062 20 100 30 -25 -0.3047 21 100 20 -25 0.6295 22 250 10 25 0.8952 23 250 30 -5 0.6602 24 100 20 -5 2.2735 25 200 20 -5 1.1735 26 100 30 5 0.2877 27 250 30 -25 -0.6598 28 100 20 25 2.9191 29 250 30 15 0.6774 30 250 10 15 -0.6843 31 150 30 -25 0.1865 32 100 20 15 -0.3244 33 100 10 -25 -0.2747 34 250 30 -15 -0.9335 35 250 10 -25 0.1168 36 250 10 5 0.3192 class=design, type= Dopt > summary(lm(r.plan)) Number of observations used: 36 Formula: y ~ (eins + zwei + drei)^2 + I(eins^2) + I(zwei^2) + I(drei^2) Call: lm.default(formula = fo, data = model.frame(fo, data = formula)) Residuals: Min 1Q Median 3Q Max -1.42671 -0.59617 0.07589 0.38235 2.24208 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) -3.570e+00 2.403e+00 -1.485 0.1494 eins 8.051e-03 2.456e-02 0.328 0.7457 zwei 3.946e-01 1.568e-01 2.516 0.0184 * drei -1.978e-02 3.264e-02 -0.606 0.5498 I(eins^2) -1.552e-05 6.885e-05 -0.225 0.8234 I(zwei^2) -8.703e-03 3.615e-03 -2.408 0.0235 * I(drei^2) -5.297e-04 6.448e-04 -0.821 0.4188 eins:zwei -1.752e-04 2.989e-04 -0.586 0.5628 eins:drei 2.077e-04 1.339e-04 1.551 0.1330 zwei:drei -3.137e-04 9.821e-04 -0.319 0.7520 --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.9556 on 26 degrees of freedom Multiple R-squared: 0.3249, Adjusted R-squared: 0.09126 F-statistic: 1.391 on 9 and 26 DF, p-value: 0.2427 > #plan2 <- Dopt.augment(r.plan, m=10) > #cor(plan2) > > ## design with candidates and constraint > candplan <- expand.grid(eins=c(100,150,200,250),zwei=c(10,20,30),drei=c(-25,-15,-5,5,15,25)) > planc <- Dopt.design(36, candplan, formula=~quad(.), + constraint="!(eins>=200 & zwei==30 & drei==25)", center=TRUE) > planc eins zwei drei 1 150 30 25 2 250 30 15 3 200 10 -25 4 200 20 25 5 100 10 -25 6 150 20 -5 7 100 10 -15 8 200 10 25 9 250 20 25 10 250 30 -5 11 200 30 5 12 200 20 -25 13 250 10 5 14 100 30 25 15 100 20 25 16 150 20 5 17 250 10 25 18 250 30 -25 19 100 20 -25 20 150 10 25 21 150 30 -25 22 250 20 -25 23 250 10 -5 24 100 30 15 25 150 10 -25 26 200 10 -5 27 100 30 -25 28 250 30 -15 29 100 10 15 30 250 20 15 31 250 10 15 32 100 10 25 33 100 20 5 34 150 30 -15 35 250 10 -25 36 100 30 5 class=design, type= Dopt > round(cor(desnum(planc)[,-1]), 4) eins zwei drei I(eins^2) I(zwei^2) I(drei^2) eins:zwei eins 1.0000 -0.0781 -0.0346 0.9940 -0.0760 -0.0911 0.5684 zwei -0.0781 1.0000 -0.0491 -0.0752 0.9913 -0.1099 0.7289 drei -0.0346 -0.0491 1.0000 -0.0283 -0.0561 -0.0681 -0.0911 I(eins^2) 0.9940 -0.0752 -0.0283 1.0000 -0.0724 -0.0976 0.5676 I(zwei^2) -0.0760 0.9913 -0.0561 -0.0724 1.0000 -0.1154 0.7217 I(drei^2) -0.0911 -0.1099 -0.0681 -0.0976 -0.1154 1.0000 -0.1411 eins:zwei 0.5684 0.7289 -0.0911 0.5676 0.7217 -0.1411 1.0000 eins:drei -0.0165 -0.0864 0.9431 -0.0121 -0.0956 -0.0735 -0.1129 zwei:drei -0.0805 -0.0572 0.9145 -0.0747 -0.0656 -0.0850 -0.1344 eins:drei zwei:drei eins -0.0165 -0.0805 zwei -0.0864 -0.0572 drei 0.9431 0.9145 I(eins^2) -0.0121 -0.0747 I(zwei^2) -0.0956 -0.0656 I(drei^2) -0.0735 -0.0850 eins:zwei -0.1129 -0.1344 eins:drei 1.0000 0.8513 zwei:drei 0.8513 1.0000 > > ## design with blocking without wholeBlockData (i.e. blocked, not splitplot) > planc <- Dopt.design(36, candplan, formula=~quad(.), + constraint="!(eins>=200 & zwei==30 & drei==25)", center=TRUE, + blocks=3) > summary(planc) Call: Dopt.design(36, candplan, formula = ~quad(.), constraint = "!(eins>=200 & zwei==30 & drei==25)", center = TRUE, blocks = 3) Experimental design of type Dopt.blocked 36 runs blocked design with 3 blocks of size 12 12 12 Factor settings (scale ends): eins zwei drei 1 100 10 -25 2 250 30 25 Optimality criteria: D 22245.56 The design itself: run.no run.no.std.rp Blocks eins zwei drei 1 1 60.1.8 1 250 30 15 2 2 57.1.7 1 100 30 15 3 3 63.1.10 1 200 10 25 4 4 68.1.12 1 250 20 25 5 5 49.1.6 1 100 10 15 6 6 16.1.5 1 250 10 -15 7 7 9.1.4 1 100 30 -25 8 8 8.1.3 1 250 20 -25 9 9 64.1.11 1 250 10 25 10 10 61.1.9 1 100 10 25 11 11 2.1.1 1 150 10 -25 12 12 4.1.2 1 250 10 -25 run.no run.no.std.rp Blocks eins zwei drei 13 13 59.2.10 2 200 30 15 14 14 11.2.5 2 200 30 -25 15 15 52.2.9 2 250 10 15 16 16 10.2.4 2 150 30 -25 17 17 62.2.11 2 150 10 25 18 18 69.2.12 2 100 30 25 19 19 12.2.6 2 250 30 -25 20 20 48.2.8 2 250 30 5 21 21 3.2.2 2 200 10 -25 22 22 1.2.1 2 100 10 -25 23 23 5.2.3 2 100 20 -25 24 24 36.2.7 2 250 30 -5 run.no run.no.std.rp Blocks eins zwei drei 25 25 65.3.10 3 100 20 25 26 26 70.3.12 3 150 30 25 27 27 24.3.4 3 250 30 -15 28 28 20.3.2 3 250 20 -15 29 29 28.3.5 3 250 10 -5 30 30 13.3.1 3 100 10 -15 31 31 40.3.8 3 250 10 5 32 32 37.3.7 3 100 10 5 33 33 33.3.6 3 100 30 -5 34 34 67.3.11 3 200 20 25 35 35 21.3.3 3 100 30 -15 36 36 56.3.9 3 250 20 15 class=design, type= Dopt.blocked NOTE: columns run.no and run.no.std.rp are annotation, not part of the data frame > round(cor(desnum(planc)[,-1]), 4) Blocks2 Blocks3 eins zwei drei I(eins^2) I(zwei^2) I(drei^2) Blocks2 1.0000 -0.5000 0.0149 0.2189 -0.1958 -0.0106 0.2398 0.1610 Blocks3 -0.5000 1.0000 -0.0747 0.0219 0.0979 -0.0614 -0.0054 -0.4187 eins 0.0149 -0.0747 1.0000 -0.0320 -0.0301 0.9956 -0.0467 -0.1808 zwei 0.2189 0.0219 -0.0320 1.0000 -0.0699 -0.0335 0.9940 -0.0790 drei -0.1958 0.0979 -0.0301 -0.0699 1.0000 -0.0351 -0.0799 -0.0467 I(eins^2) -0.0106 -0.0614 0.9956 -0.0335 -0.0351 1.0000 -0.0492 -0.2187 I(zwei^2) 0.2398 -0.0054 -0.0467 0.9940 -0.0799 -0.0492 1.0000 -0.1025 I(drei^2) 0.1610 -0.4187 -0.1808 -0.0790 -0.0467 -0.2187 -0.1025 1.0000 eins:zwei 0.2289 -0.0514 0.5917 0.7375 -0.0802 0.5874 0.7233 -0.1866 eins:drei -0.1730 0.0885 -0.0421 -0.0778 0.9428 -0.0480 -0.0891 -0.0589 zwei:drei -0.1992 0.1135 -0.0391 -0.0926 0.9128 -0.0439 -0.1036 -0.0710 eins:zwei eins:drei zwei:drei Blocks2 0.2289 -0.1730 -0.1992 Blocks3 -0.0514 0.0885 0.1135 eins 0.5917 -0.0421 -0.0391 zwei 0.7375 -0.0778 -0.0926 drei -0.0802 0.9428 0.9128 I(eins^2) 0.5874 -0.0480 -0.0439 I(zwei^2) 0.7233 -0.0891 -0.1036 I(drei^2) -0.1866 -0.0589 -0.0710 eins:zwei 1.0000 -0.1005 -0.1092 eins:drei -0.1005 1.0000 0.8501 zwei:drei -0.1092 0.8501 1.0000 > > ## design with blocking without wholeBlockData (i.e. blocked, not splitplot) > ## variable block sizes > planc <- Dopt.design(36, candplan, formula=~quad(.), + constraint="!(eins>=200 & zwei==30 & drei==25)", center=TRUE, + blocks=c(6,6,12,12)) > summary(planc) Call: Dopt.design(36, candplan, formula = ~quad(.), constraint = "!(eins>=200 & zwei==30 & drei==25)", center = TRUE, blocks = c(6, 6, 12, 12)) Experimental design of type Dopt.blocked 36 runs blocked design with 4 blocks Varying block sizes: [1] 6 6 12 12 Factor settings (scale ends): eins zwei drei 1 100 10 -25 2 250 30 25 Optimality criteria: D 22670.16 The design itself: run.no run.no.std.rp Blocks eins zwei drei 1 1 12.1.3 1 250 30 -25 2 2 68.1.6 1 250 20 25 3 3 64.1.5 1 250 10 25 4 4 4.1.2 1 250 10 -25 5 5 61.1.4 1 100 10 25 6 6 1.1.1 1 100 10 -25 run.no run.no.std.rp Blocks eins zwei drei 7 7 53.2.5 2 100 20 15 8 8 9.2.2 2 100 30 -25 9 9 11.2.3 2 200 30 -25 10 10 48.2.4 2 250 30 5 11 11 8.2.1 2 250 20 -25 12 12 65.2.6 2 100 20 25 run.no run.no.std.rp Blocks eins zwei drei 13 13 3.3.1 3 200 10 -25 14 14 13.3.5 3 100 10 -15 15 15 7.3.3 3 200 20 -25 16 16 5.3.2 3 100 20 -25 17 17 63.3.11 3 200 10 25 18 18 20.3.7 3 250 20 -15 19 19 57.3.10 3 100 30 15 20 20 10.3.4 3 150 30 -25 21 21 69.3.12 3 100 30 25 22 22 37.3.9 3 100 10 5 23 23 16.3.6 3 250 10 -15 24 24 36.3.8 3 250 30 -5 run.no run.no.std.rp Blocks eins zwei drei 25 25 24.4.4 4 250 30 -15 26 26 21.4.3 4 100 30 -15 27 27 2.4.1 4 150 10 -25 28 28 67.4.11 4 200 20 25 29 29 49.4.7 4 100 10 15 30 30 17.4.2 4 100 20 -15 31 31 70.4.12 4 150 30 25 32 32 52.4.8 4 250 10 15 33 33 62.4.10 4 150 10 25 34 34 32.4.5 4 250 20 -5 35 35 60.4.9 4 250 30 15 36 36 33.4.6 4 100 30 -5 class=design, type= Dopt.blocked NOTE: columns run.no and run.no.std.rp are annotation, not part of the data frame > round(cor(desnum(planc)[,-1]), 4) Blocks2 Blocks3 Blocks4 eins zwei drei I(eins^2) I(zwei^2) Blocks2 1.0000 -0.3162 -0.3162 -0.0470 0.2631 -0.0670 -0.0389 0.2319 Blocks3 -0.3162 1.0000 -0.5000 -0.0743 -0.0693 -0.1638 -0.0869 -0.0630 Blocks4 -0.3162 -0.5000 1.0000 -0.0297 0.0693 0.1830 -0.0424 0.0745 eins -0.0470 -0.0743 -0.0297 1.0000 0.0247 -0.0844 0.9956 0.0167 zwei 0.2631 -0.0693 0.0693 0.0247 1.0000 -0.0962 0.0317 0.9914 drei -0.0670 -0.1638 0.1830 -0.0844 -0.0962 1.0000 -0.0821 -0.0951 I(eins^2) -0.0389 -0.0869 -0.0424 0.9956 0.0317 -0.0821 1.0000 0.0228 I(zwei^2) 0.2319 -0.0630 0.0745 0.0167 0.9914 -0.0951 0.0228 1.0000 I(drei^2) 0.0731 -0.0825 -0.2806 -0.0446 -0.1648 -0.0309 -0.0912 -0.1721 eins:zwei 0.1642 -0.1228 0.0331 0.6638 0.7150 -0.1333 0.6671 0.7045 eins:drei -0.1163 -0.1839 0.2329 -0.1122 -0.1079 0.9416 -0.1106 -0.1059 zwei:drei -0.1256 -0.0808 0.1685 -0.0990 -0.1306 0.9164 -0.0954 -0.1325 I(drei^2) eins:zwei eins:drei zwei:drei Blocks2 0.0731 0.1642 -0.1163 -0.1256 Blocks3 -0.0825 -0.1228 -0.1839 -0.0808 Blocks4 -0.2806 0.0331 0.2329 0.1685 eins -0.0446 0.6638 -0.1122 -0.0990 zwei -0.1648 0.7150 -0.1079 -0.1306 drei -0.0309 -0.1333 0.9416 0.9164 I(eins^2) -0.0912 0.6671 -0.1106 -0.0954 I(zwei^2) -0.1721 0.7045 -0.1059 -0.1325 I(drei^2) 1.0000 -0.1910 -0.0343 -0.0470 eins:zwei -0.1910 1.0000 -0.1664 -0.1743 eins:drei -0.0343 -0.1664 1.0000 0.8506 zwei:drei -0.0470 -0.1743 0.8506 1.0000 > > ## design with blocking with wholeBlockData (splitplot) > within<-expand.grid(A=c(-1,0,1),B=c(-1,0,1),C=c(-1,0,1)) > whole<-expand.grid(D=factor(1:3),E=factor(1:3)) > > planc <- Dopt.design(54, within, formula=~D+E*(quad(A,B,C)), + center=TRUE, + blocks=rep(6,9), wholeBlockData=whole) > summary(planc) Call: Dopt.design(54, within, formula = ~D + E * (quad(A, B, C)), center = TRUE, blocks = rep(6, 9), wholeBlockData = whole) Experimental design of type Dopt.splitplot 54 runs Factor settings: D E A B C 1 1 1 -1 -1 -1 2 2 2 1 1 1 3 3 3 Optimality criteria: D 0.1263164 split-plot design: 9 whole plots first 2 factors are whole plot factors > > whole <- data.frame(semester=1:3,reader=c(1,2,1)) > planc <- Dopt.design(36, candplan, formula=~semester+reader+(eins+zwei+drei)^2,center=TRUE, + constraint="!(eins>=200 & zwei==30 & drei==25)", + blocks=c(12,12,12), wholeBlockData=whole) > summary(planc) Call: Dopt.design(36, candplan, formula = ~semester + reader + (eins + zwei + drei)^2, center = TRUE, constraint = "!(eins>=200 & zwei==30 & drei==25)", blocks = c(12, 12, 12), wholeBlockData = whole) Experimental design of type Dopt.splitplot 36 runs Factor settings (scale ends): semester reader eins zwei drei 1 1 1 100 10 -25 2 2 2 250 30 25 3 3 Optimality criteria: D 11558.36 split-plot design: 3 whole plots first 2 factors are whole plot factors The design itself: run.no run.no.std.rp Blocks semester reader eins zwei drei 1 1 16.1.5 1 1 1 250 10 -15 2 2 1.1.1 1 1 1 100 10 -25 3 3 37.1.6 1 1 1 100 10 5 4 4 8.1.2 1 1 1 250 20 -25 5 5 9.1.3 1 1 1 100 30 -25 6 6 61.1.10 1 1 1 100 10 25 7 7 68.1.11 1 1 1 250 20 25 8 8 11.1.4 1 1 1 200 30 -25 9 9 40.1.7 1 1 1 250 10 5 10 10 48.1.9 1 1 1 250 30 5 11 11 45.1.8 1 1 1 100 30 5 12 12 70.1.12 1 1 1 150 30 25 run.no run.no.std.rp Blocks semester reader eins zwei drei 13 13 65.2.12 2 2 2 100 20 25 14 14 60.2.9 2 2 2 250 30 15 15 15 64.2.11 2 2 2 250 10 25 16 16 10.2.3 2 2 2 150 30 -25 17 17 33.2.6 2 2 2 100 30 -5 18 18 13.2.5 2 2 2 100 10 -15 19 19 57.2.8 2 2 2 100 30 15 20 20 12.2.4 2 2 2 250 30 -25 21 21 2.2.1 2 2 2 150 10 -25 22 22 4.2.2 2 2 2 250 10 -25 23 23 62.2.10 2 2 2 150 10 25 24 24 56.2.7 2 2 2 250 20 15 run.no run.no.std.rp Blocks semester reader eins zwei drei 25 25 5.3.2 3 3 1 100 20 -25 26 26 21.3.3 3 3 1 100 30 -15 27 27 28.3.6 3 3 1 250 10 -5 28 28 63.3.11 3 3 1 200 10 25 29 29 36.3.7 3 3 1 250 30 -5 30 30 24.3.4 3 3 1 250 30 -15 31 31 49.3.8 3 3 1 100 10 15 32 32 69.3.12 3 3 1 100 30 25 33 33 25.3.5 3 3 1 100 10 -5 34 34 52.3.9 3 3 1 250 10 15 35 35 59.3.10 3 3 1 200 30 15 36 36 3.3.1 3 3 1 200 10 -25 class=design, type= Dopt.splitplot NOTE: columns run.no and run.no.std.rp are annotation, not part of the data frame > round(cor(desnum(planc)[,-1]), 4) Blocks2 Blocks3 semester reader eins zwei drei eins:zwei Blocks2 1.0000 -0.5000 0.0000 1.0000 0.0000 0.0212 0.0201 0.0092 Blocks3 -0.5000 1.0000 0.8660 -0.5000 0.0000 -0.0424 0.0201 -0.0323 semester 0.0000 0.8660 1.0000 0.0000 0.0000 -0.0367 0.0349 -0.0320 reader 1.0000 -0.5000 0.0000 1.0000 0.0000 0.0212 0.0201 0.0092 eins 0.0000 0.0000 0.0000 0.0000 1.0000 -0.0334 -0.0212 0.5949 zwei 0.0212 -0.0424 -0.0367 0.0212 -0.0334 1.0000 -0.0546 0.7307 drei 0.0201 0.0201 0.0349 0.0201 -0.0212 -0.0546 1.0000 -0.0695 eins:zwei 0.0092 -0.0323 -0.0320 0.0092 0.5949 0.7307 -0.0695 1.0000 eins:drei 0.0165 0.0248 0.0381 0.0165 -0.0275 -0.0702 0.9394 -0.0902 zwei:drei 0.0214 0.0143 0.0288 0.0214 -0.0413 -0.0776 0.9074 -0.1058 eins:drei zwei:drei Blocks2 0.0165 0.0214 Blocks3 0.0248 0.0143 semester 0.0381 0.0288 reader 0.0165 0.0214 eins -0.0275 -0.0413 zwei -0.0702 -0.0776 drei 0.9394 0.9074 eins:zwei -0.0902 -0.1058 eins:drei 1.0000 0.8410 zwei:drei 0.8410 1.0000 > r.planc <- add.response(planc, rnorm(36)) > summary(lm(r.planc)) Number of observations used: 36 Formula: rnorm.36. ~ semester + reader + (eins + zwei + drei)^2 Call: lm.default(formula = fo, data = model.frame(fo, data = formula)) Residuals: Min 1Q Median 3Q Max -2.22281 -0.44258 0.04916 0.53253 1.36389 Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 0.8207537 1.0271984 0.799 0.4313 semester -0.0686896 0.1667510 -0.412 0.6836 reader 0.2693425 0.2886238 0.933 0.3590 eins -0.0064428 0.0048398 -1.331 0.1942 zwei -0.0257780 0.0412523 -0.625 0.5373 drei -0.0528538 0.0264531 -1.998 0.0559 . eins:zwei 0.0002241 0.0002244 0.999 0.3269 eins:drei 0.0001059 0.0001120 0.946 0.3525 zwei:drei 0.0019161 0.0007907 2.423 0.0224 * --- Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1 Residual standard error: 0.8157 on 27 degrees of freedom Multiple R-squared: 0.2705, Adjusted R-squared: 0.05439 F-statistic: 1.252 on 8 and 27 DF, p-value: 0.3088 WARNING: This is a split plot design, whole plot effects may have larger variance! p-values for whole plot effects may be misleadingly low! The whole plot effects are: [1] semester reader > > proc.time() user system elapsed 1.37 0.26 1.62