Week 7

set.seed(1234)
my_data <- data.frame(
  name = paste0(rep("M_", 10), 1:10),
  weight = round(rnorm(10, 20, 2), 1)
)
head(my_data, 10)
   name weight
1   M_1   17.6
2   M_2   20.6
3   M_3   22.2
4   M_4   15.3
5   M_5   20.9
6   M_6   21.0
7   M_7   18.9
8   M_8   18.9
9   M_9   18.9
10 M_10   18.2
summary(my_data$weight)
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  15.30   18.38   18.90   19.25   20.82   22.20 
library(ggpubr)
Warning: package 'ggpubr' was built under R version 4.4.2
Loading required package: ggplot2
ggboxplot(my_data$weight, 
          ylab = "Weight (g)", xlab = FALSE,
          ggtheme = theme_minimal())

shapiro.test(my_data$weight)

    Shapiro-Wilk normality test

data:  my_data$weight
W = 0.9526, p-value = 0.6993
library("ggpubr")
ggqqplot(my_data$weight, ylab = "Men's weight",
         ggtheme = theme_minimal())

res <- t.test(my_data$weight, mu = 25)
res 

    One Sample t-test

data:  my_data$weight
t = -9.0783, df = 9, p-value = 7.953e-06
alternative hypothesis: true mean is not equal to 25
95 percent confidence interval:
 17.8172 20.6828
sample estimates:
mean of x 
    19.25 
res$p.value
[1] 7.953383e-06
res$estimate
mean of x 
    19.25 
res$conf.int
[1] 17.8172 20.6828
attr(,"conf.level")
[1] 0.95
women_weight <- c(38.9, 61.2, 73.3, 21.8, 63.4, 64.6, 48.4, 48.8, 48.5)
men_weight <- c(67.8, 60, 63.4, 76, 89.4, 73.3, 67.3, 61.3, 62.4) 
my_data <- data.frame( 
                group = rep(c("Woman", "Man"), each = 9),
                weight = c(women_weight,  men_weight)
                )
print(my_data)
   group weight
1  Woman   38.9
2  Woman   61.2
3  Woman   73.3
4  Woman   21.8
5  Woman   63.4
6  Woman   64.6
7  Woman   48.4
8  Woman   48.8
9  Woman   48.5
10   Man   67.8
11   Man   60.0
12   Man   63.4
13   Man   76.0
14   Man   89.4
15   Man   73.3
16   Man   67.3
17   Man   61.3
18   Man   62.4
library(dplyr)

Attaching package: 'dplyr'
The following objects are masked from 'package:stats':

    filter, lag
The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union
group_by(my_data, group) %>%
  summarise(
    count = n(),
    mean = mean(weight, na.rm = TRUE),
    sd = sd(weight, na.rm = TRUE)
  )
# A tibble: 2 × 4
  group count  mean    sd
  <chr> <int> <dbl> <dbl>
1 Man       9  69.0  9.38
2 Woman     9  52.1 15.6 
library("ggpubr")
ggboxplot(my_data, x = "group", y = "weight", 
          color = "group", palette = c("#00AFBB", "#E7B800"),
        ylab = "Weight", xlab = "Groups")

with(my_data, shapiro.test(weight[group == "Man"]))

    Shapiro-Wilk normality test

data:  weight[group == "Man"]
W = 0.86425, p-value = 0.1066
with(my_data, shapiro.test(weight[group == "Woman"]))

    Shapiro-Wilk normality test

data:  weight[group == "Woman"]
W = 0.94266, p-value = 0.6101
res.ftest <- var.test(weight ~ group, data = my_data)
res.ftest

    F test to compare two variances

data:  weight by group
F = 0.36134, num df = 8, denom df = 8, p-value = 0.1714
alternative hypothesis: true ratio of variances is not equal to 1
95 percent confidence interval:
 0.08150656 1.60191315
sample estimates:
ratio of variances 
         0.3613398 
res <- t.test(women_weight, men_weight, var.equal = TRUE)
res

    Two Sample t-test

data:  women_weight and men_weight
t = -2.7842, df = 16, p-value = 0.01327
alternative hypothesis: true difference in means is not equal to 0
95 percent confidence interval:
 -29.748019  -4.029759
sample estimates:
mean of x mean of y 
 52.10000  68.98889 
res <- t.test(weight ~ group, data = my_data, var.equal = TRUE)
res

    Two Sample t-test

data:  weight by group
t = 2.7842, df = 16, p-value = 0.01327
alternative hypothesis: true difference in means between group Man and group Woman is not equal to 0
95 percent confidence interval:
  4.029759 29.748019
sample estimates:
  mean in group Man mean in group Woman 
           68.98889            52.10000 
t.test(weight ~ group, data = my_data,
        var.equal = TRUE, alternative = "less")

    Two Sample t-test

data:  weight by group
t = 2.7842, df = 16, p-value = 0.9934
alternative hypothesis: true difference in means between group Man and group Woman is less than 0
95 percent confidence interval:
     -Inf 27.47924
sample estimates:
  mean in group Man mean in group Woman 
           68.98889            52.10000 
res$p.value
[1] 0.0132656
res$estimate
  mean in group Man mean in group Woman 
           68.98889            52.10000 
res$conf.int
[1]  4.029759 29.748019
attr(,"conf.level")
[1] 0.95
women_weight <- c(38.9, 61.2, 73.3, 21.8, 63.4, 64.6, 48.4, 48.8, 48.5)
men_weight <- c(67.8, 60, 63.4, 76, 89.4, 73.3, 67.3, 61.3, 62.4) 
my_data <- data.frame( 
                group = rep(c("Woman", "Man"), each = 9),
                weight = c(women_weight,  men_weight)
                )
print(my_data)
   group weight
1  Woman   38.9
2  Woman   61.2
3  Woman   73.3
4  Woman   21.8
5  Woman   63.4
6  Woman   64.6
7  Woman   48.4
8  Woman   48.8
9  Woman   48.5
10   Man   67.8
11   Man   60.0
12   Man   63.4
13   Man   76.0
14   Man   89.4
15   Man   73.3
16   Man   67.3
17   Man   61.3
18   Man   62.4
library(dplyr)
group_by(my_data, group) %>%
  summarise(
    count = n(),
    mean = mean(weight, na.rm = TRUE),
    sd = sd(weight, na.rm = TRUE)
  )
# A tibble: 2 × 4
  group count  mean    sd
  <chr> <int> <dbl> <dbl>
1 Man       9  69.0  9.38
2 Woman     9  52.1 15.6 
library("ggpubr")
ggboxplot(my_data, x = "group", y = "weight", 
          color = "group", palette = c("#00AFBB", "#E7B800"),
        ylab = "Weight", xlab = "Groups")

res <- wilcox.test(women_weight, men_weight)
Warning in wilcox.test.default(women_weight, men_weight): cannot compute exact
p-value with ties
res

    Wilcoxon rank sum test with continuity correction

data:  women_weight and men_weight
W = 15, p-value = 0.02712
alternative hypothesis: true location shift is not equal to 0
res <- wilcox.test(weight ~ group, data = my_data,
                   exact = FALSE)
res

    Wilcoxon rank sum test with continuity correction

data:  weight by group
W = 66, p-value = 0.02712
alternative hypothesis: true location shift is not equal to 0
res$p.value
[1] 0.02711657

#```{r}

set.seed(1234) dplyr::sample_n(my_data, 10) levels(my_data\(group) my_data\)group <- ordered(my_data\(group, levels = c("ctrl", "trt1", "trt2")) library(dplyr) group_by(my_data, group) %>% summarise( count = n(), mean = mean(weight, na.rm = TRUE), sd = sd(weight, na.rm = TRUE) ) library("ggpubr") ggboxplot(my_data, x = "group", y = "weight", color = "group", palette = c("#00AFBB", "#E7B800", "#FC4E07"), order = c("ctrl", "trt1", "trt2"), ylab = "Weight", xlab = "Treatment") library("ggpubr") ggline(my_data, x = "group", y = "weight", add = c("mean_se", "jitter"), order = c("ctrl", "trt1", "trt2"), ylab = "Weight", xlab = "Treatment") boxplot(weight ~ group, data = my_data, xlab = "Treatment", ylab = "Weight", frame = FALSE, col = c("#00AFBB", "#E7B800", "#FC4E07")) library("gplots") plotmeans(weight ~ group, data = my_data, frame = FALSE, xlab = "Treatment", ylab = "Weight", main="Mean Plot with 95% CI") res.aov <- aov(weight ~ group, data = my_data) summary(res.aov) TukeyHSD(res.aov) glht(model, lincft) library(multcomp) summary(glht(res.aov, linfct = mcp(group = "Tukey"))) pairwise.t.test(my_data\)weight, my_data$group, p.adjust.method = “BH”) plot(res.aov, 1)



#```{r}
before <-c(200.1, 190.9, 192.7, 213, 241.4, 196.9, 172.2, 185.5, 205.2, 193.7)
after <-c(392.9, 393.2, 345.1, 393, 434, 427.9, 422, 383.9, 392.3, 352.2)
my_data <- data.frame( 
                group = rep(c("before", "after"), each = 10),
                weight = c(before,  after)
                )
print(my_data)
library("dplyr")
group_by(my_data, group) %>%
  summarise(
    count = n(),
    mean = mean(weight, na.rm = TRUE),
    sd = sd(weight, na.rm = TRUE)
  )
library("ggpubr")
ggboxplot(my_data, x = "group", y = "weight", 
          color = "group", palette = c("#00AFBB", "#E7B800"),
          order = c("before", "after"),
          ylab = "Weight", xlab = "Groups")
before <- subset(my_data,  group == "before", weight,
                 drop = TRUE)
after <- subset(my_data,  group == "after", weight,
                 drop = TRUE)
if (!require("PairedData")) install.packages("PairedData")
library(PairedData)
pd <- paired(before, after)
plot(pd, type = "profile") + theme_bw()
d <- with(my_data, 
        weight[group == "before"] - weight[group == "after"])
shapiro.test(d) # => p-value = 0.6141
res <- t.test(before, after, paired = TRUE)
res
res <- t.test(weight ~ group, data = my_data, paired = TRUE)
res

c
  
library(dplyr)
group_by(my_data, group) %>%
  summarise(
    count = n(),
    mean = mean(weight, na.rm = TRUE),
    sd = sd(weight, na.rm = TRUE)
  )
# A tibble: 2 × 4
  group count  mean    sd
  <chr> <int> <dbl> <dbl>
1 Man       9  69.0  9.38
2 Woman     9  52.1 15.6