Hand Module 4 Code
# download packages
library(ggplot2)
library(dplyr)
mean_mpg <- mean(mtcars$mpg)
# Task 1
# load data set mtcars
data(mtcars)
head(mtcars)
## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1
group_data <- mtcars %>% group_by(cyl)
summary(mtcars)
## mpg cyl disp hp
## Min. :10.40 Min. :4.000 Min. : 71.1 Min. : 52.0
## 1st Qu.:15.43 1st Qu.:4.000 1st Qu.:120.8 1st Qu.: 96.5
## Median :19.20 Median :6.000 Median :196.3 Median :123.0
## Mean :20.09 Mean :6.188 Mean :230.7 Mean :146.7
## 3rd Qu.:22.80 3rd Qu.:8.000 3rd Qu.:326.0 3rd Qu.:180.0
## Max. :33.90 Max. :8.000 Max. :472.0 Max. :335.0
## drat wt qsec vs
## Min. :2.760 Min. :1.513 Min. :14.50 Min. :0.0000
## 1st Qu.:3.080 1st Qu.:2.581 1st Qu.:16.89 1st Qu.:0.0000
## Median :3.695 Median :3.325 Median :17.71 Median :0.0000
## Mean :3.597 Mean :3.217 Mean :17.85 Mean :0.4375
## 3rd Qu.:3.920 3rd Qu.:3.610 3rd Qu.:18.90 3rd Qu.:1.0000
## Max. :4.930 Max. :5.424 Max. :22.90 Max. :1.0000
## am gear carb
## Min. :0.0000 Min. :3.000 Min. :1.000
## 1st Qu.:0.0000 1st Qu.:3.000 1st Qu.:2.000
## Median :0.0000 Median :4.000 Median :2.000
## Mean :0.4062 Mean :3.688 Mean :2.812
## 3rd Qu.:1.0000 3rd Qu.:4.000 3rd Qu.:4.000
## Max. :1.0000 Max. :5.000 Max. :8.000
# calculating mean
mean_mpg <- mean(mtcars$mpg) +
print(mean_mpg)
## [1] 20.09062
# mean_mpg = 20.0962
# calculating Standard Error from SD
sd_mpg <- sd(mtcars$mpg, na.rm = TRUE)
# creating a sample size vriable
n <- sum(!is.na(mtcars$mpg))
se_mpg <- sd_mpg / sqrt(n)
print(se_mpg)
## [1] 1.065424
# SE_mpg = 1.065
# summarize data in new dataframe
data_summary <- mtcars %>% group_by(cyl) %>% summarise(se_mpg = sd_mpg / sqrt(n), mean_mpg = mean(mpg))
print(data_summary)
## # A tibble: 3 × 3
## cyl se_mpg mean_mpg
## <dbl> <dbl> <dbl>
## 1 4 1.07 26.7
## 2 6 1.07 19.7
## 3 8 1.07 15.1
# Task 2 creating a bar plot
ggplot(data_summary, aes(x = factor(cyl), y = mean_mpg,)) + geom_col(fill = c("skyblue", "orange", "green"), width = 0.7) +
geom_errorbar(aes(ymin = mean_mpg - se_mpg, ymax = mean_mpg + se_mpg), width = 0.25, size = 2) +
theme_classic() +
labs(title = "Bar Plot of Mean MPG by Cylinders", x = "Number of Cylinders", y = "Mean MPG")
#messed up on the summary stats at first but fixed it