我是R和编码新手，所以请耐心等待。我的数据如下所示：
Names Prof_A Prof_B...............Prof_Z cond
Aaliya 2.1 3.1 ................ 2.3 A
Adam 1.87 2.3 .................2.2 A
.
.
Brett 1.69 2.6...................1.78 B
等(约1700次观察(
我正在尝试通过每个数字列运行方差分析，然后是 Tukey 的测试。我只想打印对比度的重要值。
library(car)
require(graphics)
options(max.print = 99999)
ANV <- rep(NA,ncol(total))
sink("Anova-Tukey-sig.doc")
for (i in 2:(ncol(total)-1)) {
column <- names(total[i])
ANV <- summary(aov(total[,i]~cond,data=total))
posthocresult <- TukeyHSD(aov(total[,i]~cond,data=total))
print(column)
print(ANV)
print(posthocresult[posthocresult$cond[,4]<=.05])
}
sink()
但是，代码给了我一个奇怪的输出，我给出了一些片段(：
[1] "Prof_A"
Df Sum Sq Mean Sq F value Pr(>F)
cond 25 0.0228 0.0009111 1.864 0.00597 **
Residuals 1690 0.8262 0.0004889
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
named list()
[1] "Prof_B"
Df Sum Sq Mean Sq F value Pr(>F)
cond 25 0.0468 0.0018719 2.889 2.54e-06 ***
Residuals 1690 1.0949 0.0006479
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
$<NA>
NULL
$<NA>
NULL
$<NA>
NULL
跳过某些输出
[1] "Prof_R"
Df Sum Sq Mean Sq F value Pr(>F)
cond 25 0.0284 0.0011345 3.404 3.1e-08 ***
Residuals 1690 0.5633 0.0003333
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
$cond
diff lwr upr p adj
B-A 9.802223e-03 1.237889e-03 0.0183665561 6.894820e-03
C-A 6.243324e-03 -1.302350e-03 0.0137889986 2.940579e-01
D-A 1.054579e-02 1.713554e-03 0.0193780265 3.204823e-03
E-A 4.295824e-03 -3.942431e-03 0.0125340784 9.752564e-01
F-A 4.607934e-03 -8.302024e-03 0.0175178915 9.999225e-01
等。有人可以帮忙吗？
首先，我认为我们不需要整个数据集都有一个可重现的示例，子集应该可以。
total <- read.csv("https://www.dropbox.com/s/trb7d7twm703di8/total.csv?dl=1")[-1]
set.seed(1)
total.sub <- total[sample(1:400, 30), c(1:4, 26)]
total.sub[1] <- droplevels(total.sub[1])
total.sub[5] <- droplevels(total.sub[5])
total.sub[2:4] <- sapply(total.sub[2:4], function(x) round(x*1000))
rownames(total.sub) <- NULL
创建子集后，您现在可以使用 dput() 创建一个具体的表示形式，您可以将其提供给其他人使用
dput(total.sub)
structure(list(V1 = structure(c(8L, 13L, 15L, 25L, 5L, 23L, 26L, 17L, 16L, 2L, 6L,
4L, 18L, 30L, 21L, 14L, 19L, 27L, 12L, 20L, 24L, 28L, 29L, 3L, 7L, 11L, 1L, 10L,
22L, 9L), .Label = c("Abigail", "Adriel", "Alden", "Ali", "Aliya", "Aliyah",
"Amari", "Amia", "Andrea", "Annabelle", "Annalise", "Anne", "Ansley", "Aubree",
"Beckham", "Blaise", "Bradley", "Brayden", "Brett", "Bruce", "Bruno", "Camron",
"Cecilia", "Cedric", "Chad", "Charlotte", "Christian", "Clay", "Clementine",
"Coleman"), class = "factor"), Profession_A = c(24, 30, -13, 33, 17, 38, 33, 31,
31, 50, 39, 11, 20, 27, 24, 54, 53, 9, 42, 56, 39, 9, 7, 54, 0, 46, 22, 16, 1, 45),
Profession_B = c(51, 76, 3, 35, 38, 40, 14, 42, 79, 76, 19, 16, 62, 37, 25, 71, 62,
-21, 36, 50, 53, 2, 37, 84, 25, 77, 45, 45, 42, 36), Profession_C = c(29, 26, -8,
29, 16, 47, 21, 34, 42, 56, 21, 4, 32, 31, 24, 55, 37, -3, 36, 43, 49, 14, 19, 52,
4, 51, 26, 28, 33, 45), cond = structure(c(1L, 1L, 2L, 3L, 1L, 3L, 3L, 2L, 2L, 1L,
1L, 1L, 2L, 3L, 2L, 1L, 2L, 3L, 1L, 2L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 1L, 3L, 1L),
.Label = c("A", "B", "C"), class = "factor")), row.names = c(NA, -30L), class =
"data.frame") -> total
然后任何人都可以跟随，即使有一天那个保管箱链接会消失。
anv.l <- list()
hsd.l <- list()
for (i in 2:(ncol(total)-1)) {
column <- names(total[i])
ANV <- aov(total[, i] ~ cond, data=total)
anv.l[[i - 1]] <- ANV
names(anv.l)[i - 1] <- column
posthocresult <- TukeyHSD(ANV)
hsd.l[[i - 1]] <- posthocresult
names(hsd.l)[i - 1] <- column
}
coeff <- sapply(anv.l, coef)
summ <- sapply(anv.l, summary)
p.val <- sapply(hsd.l, function(x) round(x[[1]][,4], 3))