Reputation: 31
I'm trying to run a 2-way MANOVA in r and I'm struggling with the output. My problem is that the output I'm getting is wrong: it doesn't include all the lines it's suppose to under coefficients (such as Stressno
or Mgroup3TW:Stressyes
) and I don't know what to do. I'll appreciate any advise you can give me.
This is my code:
EPMmanova <- read.csv('EPMmanova.csv')
EPMmanova$Animal<-factor(EPMmanova$Animal)
EPMmanova$Mgroup<-factor(EPMmanova$Mgroup)
EPMmanova$Stress<-factor(EPMmanova$Stress)
attach(EPMmanova)
names(EPMmanova)
Man.EPM<-lm(cbind(Oahdips,Oadur,Cdur)~Mgroup+Stress+Mgroup*Stress -1)
summary(Man.EPM)
Manova(Man.EPM, multivariate=T, type=c("III"), test=("Pillai"))
This is my data:
structure(list(Animal = c("OC13/N", "OC13/B", "OC13/2B", "OC5/N",
"OC5/B", "OC4/N", "OC4/B", "OC3/N", "OC3/B", "OC2/N", "OC2/B",
"OC11/N", "OC11/B", "OC6/N", "OC6/B", "OC12/N", "OC12/B", "OC14/N",
"OC14/B", "OC22/N", "OC22/B", "OC23/N"), Mgroup = c("3TW", "3TW",
"3TW", "3TW", "3TW", "3TW", "3TW", "3TW", "3TW", "3TW", "3TW",
"3TW", "3TW", "3TW", "3TW", "3TW", "3TW", "3TW", "3TW", "3TW",
"3TW", "3TW"), Stress = c("yes", "yes", "yes", "yes", "yes",
"yes", "yes", "no", "no", "no", "no", "no", "no", "no", "no",
"no", "no", "no", "no", "no", "no", "no"), Oafreq = c(4L, 4L,
2L, 2L, 0L, 0L, 0L, 1L, 0L, 3L, 6L, 1L, 11L, 6L, 0L, 2L, 2L,
2L, 2L, 6L, 8L, 8L), Oahdips = c(8L, 5L, 20L, 7L, 13L, 2L, 4L,
12L, 1L, 16L, 20L, 11L, 30L, 11L, 0L, 17L, 26L, 10L, 5L, 25L,
27L, 18L), Oadur = c(18.6057, 38.1755, 72.5497, 2.00081, 0, 0,
0, 7.48303, 0, 30.4095, 83.6341, 4.28175, 111.795, 10.4833, 0,
24.5301, 31.3696, 43.0164, 29.2118, 84.0747, 81.6733, 91.5486
), Cfreq = c(22L, 25L, 15L, 22L, 7L, 3L, 12L, 17L, 16L, 19L,
18L, 35L, 30L, 19L, 13L, 17L, 14L, 16L, 10L, 20L, 17L, 21L),
Cdur = c(111.834, 92.5577, 80.8331, 101.641, 111.205, 15.4863,
64.5828, 124.971, 40.2964, 136.523, 123.69, 100.361, 96.7104,
75.2235, 42.7358, 81.7535, 172.973, 122.167, 153.382, 92.7182,
96.2392, 60.0188)), row.names = c(NA, 22L), class = "data.frame")
And this is my output:
Response Cdur :
Call:
lm(formula = Cdur ~ Mgroup + Stress + Mgroup * Stress - 1, data = EPMmanova)
Residuals:
Min 1Q Median 3Q Max
-70.140 -21.639 -0.498 17.187 97.339
Coefficients:
Estimate Std. Error t value Pr(>|t|)
Mgroup3TW 75.6343 4.8589 15.566 <2e-16 ***
Mgroup5TW 75.4630 5.8075 12.994 <2e-16 ***
Stressyes 0.1456 7.2267 0.020 0.984
Mgroup5TW:Stressyes 1.0543 11.2699 0.094 0.926
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 30.73 on 120 degrees of freedom
Multiple R-squared: 0.8629, Adjusted R-squared: 0.8583
F-statistic: 188.7 on 4 and 120 DF, p-value: < 2.2e-16
Upvotes: 1
Views: 54