Dunnetts测试以比较对照组和治疗组

如何解决Dunnetts测试以比较对照组和治疗组

方差分析返回重要结果的一种方法。因此，我想进行Dunnetts检验，以比较对照组和治疗组的控制方法（方法D）。我刚接触R时，有人会帮我做这个吗？这是我的数据：

mydata <- tibble(
  score = c(14,12,10,9,6,5,17,15,7,14,11,8,4,2,2),method = as.factor(paste0("Method ",rep(c("A","B","C","D"),each=7)))
)

解决方法

首先，我读入数据：

mydata <- tibble(
  score = c(14,12,10,9,6,5,17,15,7,14,11,8,4,2,2),method = as.factor(paste0("Method ",rep(c("A","B","C","D"),each=7))
))

接下来，如果要与Method D进行比较，则应将因子设为第一级：

mydata$method <- relevel(mydata$method,"Method D")

接下来，估算方差分析：

a <- aov(score ~ method,data=mydata)

最后，使用multcomp包，您可以生成为您提供适当检验的常规线性假设检验：

library(multcomp)
g <- glht(a,linfct = mcp(method = "Dunnett"))
summary(g)

# 
# Simultaneous Tests for General Linear Hypotheses
# Multiple Comparisons of Means: Dunnett Contrasts
# Fit: aov(formula = score ~ method,data = mydata)
# 
# Linear Hypotheses:
#                          Estimate Std. Error t value Pr(>|t|)   
# Method A - Method D == 0    5.286      1.630   3.243  0.00940 **
# Method B - Method D == 0    6.714      1.630   4.120  0.00116 **
# Method C - Method D == 0    5.429      1.630   3.331  0.00761 **
# ---
# Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
# (Adjusted p values reported -- single-step method)