Lundrigan, Cyril
2013-May-09 11:58 UTC
[R] Paritioning of Interaction SS in ANOVA - Gomez and Gomez(1984) example
Hello I'm a new user of R and I'm using Deducer as the interface but also making use of the command interface where necessary. I'm trying to replicate Table 6.18 on page 262 in Statistical Procedures in Agricultural Research, by K. A. Gomez and A. A. Gomez. New York, Chichester, etc.: Wiley (1984). http://pdf.usaid.gov/pdf_docs/PNAAR208.pdf. This example is highly relevant to the type of data we will be analyzing in our department but nobody here has experience doing partitioning of interactions with software. I've managed to replicate all previous steps for that particular exercise up to this point. If I interpret the syntax correctly, the table is showing comparisons of specific treatment combinations within the time variable P. Is this the correct interpretation? If so, I don't know how to achieve that with R. I had initially used SYSTAT for this exercise and had sent the problem along to their support person and after a few days the response was that he did not understand the syntax and, thus, could not replicate the table results. Unfortunately, it's also one of the few Gomez and Gomez examples not covered in the "agridat" package. I was trying to do the partiioning with interactionMeans and testInteractions functions in phia package but made no headway. Greatly appreciate any help or direction with this. Thanks! “This email and any attached files are intended for the sole use of the primary and copied addressee(s) and may contain privileged and/or confidential information. Any distribution, use or copying by any means of this information is strictly prohibited. If you received this email in error, please delete it immediately and notify the sender.” [[alternative HTML version deleted]]
peter dalgaard
2013-May-09 16:01 UTC
[R] Paritioning of Interaction SS in ANOVA - Gomez and Gomez(1984) example
On May 9, 2013, at 13:58 , Lundrigan, Cyril wrote:> Hello > I'm a new user of R and I'm using Deducer as the interface but also > making use of the command interface where necessary. I'm trying to > replicate Table 6.18 on page 262 in Statistical Procedures in > Agricultural Research, by K. A. Gomez and A. A. Gomez. New York, > Chichester, etc.: Wiley (1984). > http://pdf.usaid.gov/pdf_docs/PNAAR208.pdf. This example is highly > relevant to the type of data we will be analyzing in our department but > nobody here has experience doing partitioning of interactions with > software. >(Did you _have_ to give us a 600 page book to download to look at one table??) This was likely done manually, and the syntax therefore may be a bit idiosyncratic, but according to what I _think_ is going on, you could set up Ta, Tb,..., Te as vectors or matrices with specific contrasts and then replace the term T:P in the model by (Ta+Tb+Tc+Td+Te):P As far as I can tell, Ta is a vector which is 1 when T=7, 0 elsewhere Tb is 1 when T=8 Tc is 1 when T=2 or T=5 Td is 1 when T=2 Te is a matrix with three columns one is 1 when T=3 one is 1 when T=4 one is 1 when T=6 (you can probably also do this via releveled versions of the T factor in which certain levels are combined.)> I've managed to replicate all previous steps for that particular > exercise up to this point. If I interpret the syntax correctly, the > table is showing comparisons of specific treatment combinations within > the time variable P. Is this the correct interpretation? If so, I don't > know how to achieve that with R. I had initially used SYSTAT for this > exercise and had sent the problem along to their support person and > after a few days the response was that he did not understand the syntax > and, thus, could not replicate the table results. Unfortunately, it's > also one of the few Gomez and Gomez examples not covered in the > "agridat" package. I was trying to do the partiioning with > interactionMeans and testInteractions functions in phia package but made > no headway. Greatly appreciate any help or direction with this. > > Thanks! > > > > > ?This email and any attached files are intended for the sole use of the primary and copied addressee(s) and may contain privileged and/or confidential information. Any distribution, use or copying by any means of this information is strictly prohibited. If you received this email in error, please delete it immediately and notify the sender.? > > [[alternative HTML version deleted]] > > ______________________________________________ > R-help at r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code.-- Peter Dalgaard, Professor, Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: pd.mes at cbs.dk Priv: PDalgd at gmail.com
Richard M. Heiberger
2013-May-09 18:26 UTC
[R] Paritioning of Interaction SS in ANOVA - Gomez and Gomez(1984) example
Thank you for this example.
The way to handle it is with the split argument to the summary.aov function.
Look at ?summary.aov for details.
I use the reshape package to get the data ordered the way aov wants it.
I use the HH package for the graph.
## from: Lundrigan, Cyril <cyrillundrig@gov.nl.ca>
## to: r-help@r-project.org
## date: Thu, May 9, 2013 at 7:58 AM
## subject: [R] Paritioning of Interaction SS in ANOVA - Gomez and
Gomez(1984) example
## Statistical Procedures in Agricultural Research, by K. A. Gomez and A.
A. Gomez. New York,
## Chichester, etc.: Wiley (1984).
## http://pdf.usaid.gov/pdf_docs/PNAAR208.pdf.
## Table 6.14 Data on Nitrogen Content of the Soil, Subjected to Eight
## Fertilizer Treatments In a RCB Design with Four Replications,
## Collected at Three Growth Stages of the Rice Crop
## Soil Nitrogen Content, %
## Treatment Rep. I Rep. II Rep. III Rep. IV
## Number P1 P2 P3 P2 P2 P3 P1 P2 P3 P1 P2 P3
library(reshape)
library(HH)
GG614.in <- read.table(textConnection("
1 3.26 1.88 1.40 2.98 1.74 1.24 2.78 1.76 1.44 2.77 2.00 1.25
2 3.84 2.36 1.53 3.74 2.14 1.21 3.09 1.75 1.28 3.36 1.57 1.17
3 3.50 2.20 1.33 3.49 2.28 1.54 3.03 2.48 1.46 3.36 2.47 1.41
4 3.43 2.32 1.61 3.45 2.33 1.33 2.81 2.16 1.40 3.32 1.99 1.12
5 3.43 1.98 1.11 3.24 1.70 1.25 3.45 1.78 1.39 3.09 1.74 1.20
6 3.68 2.01 1.26 3.24 2.33 1.44 2.84 2.22 1.12 2.91 2.00 1.24
7 2.97 2.66 1.87 2.90 2.74 1.81 2.92 2.67 1.31 2.42 2.98 1.56
8 3.11 2.53 1.76 3.04 2.22 1.28 3.20 2.61 1.23 2.81 2.22 1.29
"))
closeAllConnections()
names(GG614.in) <- c("Treatment",
"I.P1", "I.P2", "I.P3",
"II.P1", "II.P2", "II.P3",
"III.P1", "III.P2", "III.P3",
"IV.P1", "IV.P2",
"IV.P3")
GG614 <- melt(GG614.in, id=1)
GG614$Rep <-
rep(c("I","II","III","IV"), each=24)
GG614$GrowthStage <-
factor(rep(c("P1","P2","P3"), each=8, times=4))
names(GG614)[3] <- "Nitrogen"
GG614$Treatment <- factor(GG614$Treatment)
GG614
## plot the data
interaction2wt(Nitrogen ~ Rep/Treatment + Treatment*GrowthStage, data=GG614)
interaction2wt(Nitrogen ~ Treatment*GrowthStage, data=GG614, simple=TRUE)
## Table 6.16
GG614.aov <- aov(Nitrogen ~ Error(Rep/Treatment) + Treatment*GrowthStage,
data=GG614)
summary(GG614.aov)
Treatment.contrasts <-
## 1 2 3 4 5 6 7 8
cbind("7-1234568" = c( 1, 1, 1, 1, 1, 1,-7, 1),
"8-123456" = c( 1, 1, 1, 1, 1, 1, 0,-6),
"25-1346" = c(-1, 2,-1,-1, 2,-1, 0, 0),
"2-5" = c( 0, 1, 0, 0,-1, 0, 0, 0))
contrasts(GG614$Treatment)
contrasts(GG614$Treatment) <- Treatment.contrasts
contrasts(GG614$Treatment)
## Table 6.18
GG614.aov <- aov(Nitrogen ~ Error(Rep/Treatment) + Treatment*GrowthStage,
data=GG614)
summary(GG614.aov, expand.split=FALSE,
split=list(Treatment=list(
"7-1234568"=1,
"8-123456"=2,
"25-1346"=3,
"2-5"=4,
rest=c(5,6,7)),
"Treatment:GrowthStage"=list(
"7-1234568:P"=c(1,8),
"8-123456:P"=c(2,9),
"25-1346:P"=c(3,10),
"2-5:P"=c(4,11),
"rest:P"=c(5,6,7,12,13,14))
))
On Thu, May 9, 2013 at 7:58 AM, Lundrigan, Cyril
<cyrillundrig@gov.nl.ca>wrote:
> Hello
> I'm a new user of R and I'm using Deducer as the interface but also
> making use of the command interface where necessary. I'm trying to
> replicate Table 6.18 on page 262 in Statistical Procedures in
> Agricultural Research, by K. A. Gomez and A. A. Gomez. New York,
> Chichester, etc.: Wiley (1984).
> http://pdf.usaid.gov/pdf_docs/PNAAR208.pdf. This example is highly
> relevant to the type of data we will be analyzing in our department but
> nobody here has experience doing partitioning of interactions with
> software.
>
> I've managed to replicate all previous steps for that particular
> exercise up to this point. If I interpret the syntax correctly, the
> table is showing comparisons of specific treatment combinations within
> the time variable P. Is this the correct interpretation? If so, I
don't
> know how to achieve that with R. I had initially used SYSTAT for this
> exercise and had sent the problem along to their support person and
> after a few days the response was that he did not understand the syntax
> and, thus, could not replicate the table results. Unfortunately, it's
> also one of the few Gomez and Gomez examples not covered in the
> "agridat" package. I was trying to do the partiioning with
> interactionMeans and testInteractions functions in phia package but made
> no headway. Greatly appreciate any help or direction with this.
>
> Thanks!
>
>
>
>
> “This email and any attached files are intended for the sole use of the
> primary and copied addressee(s) and may contain privileged and/or
> confidential information. Any distribution, use or copying by any means of
> this information is strictly prohibited. If you received this email in
> error, please delete it immediately and notify the sender.”
>
> [[alternative HTML version deleted]]
>
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
>
[[alternative HTML version deleted]]