lundquist-ecology-lab

# Importing built in data

data(iris) # This imports the built-in Iris dataset

print(iris$Species) # Example code, printing the species of Iris in the dataset

# List all built-in datasets

data()

lundquist-ecology-lab

# Download data from the internet

# If the file is in .csv format

tmp <- tempfile(fileext = ".csv")
download.file(url = "https://data.cdc.gov/resource/9bhg-hcku.csv",
            destfile = tmp)
covid_data <- read.csv(tmp, header = TRUE, stringsAsFactors = TRUE)
head(covid_data)

lundquist-ecology-lab

# How to import local data files

# For .csv files
data_name <- read.csv("/path/to/file_name.csv", head = TRUE,
                     stringsAsFactors = TRUE)
head(data_name)

# For .xlxs
library(readxl)
data_name <- read_excel("/path/to/file/_name.xlsx")

lundquist-ecology-lab

# Calculating mean, and other summary statistics in R with examples

# Set up
library(palmerpenguins)
data(penguins)
penguins <- na.omit(penguins)

# Mean
mean(penguins$bill_length_mm)

lundquist-ecology-lab

# Six-sided die flipped 24 times and lands on three exactly 6 times
binom.test(x = 6, n = 24, p = 1 / 6, alternative = "greater")

# Flip coin 30 times and it lands on heads exactly 19 times
binom.test(x = 19, n = 30, p = 1 / 2, alternative = "greater")

lundquist-ecology-lab

# Example chi-square
chi_square <- ((50 - 56.25)^2 / 56.25) +
               ((20 - 18.75)^2 / 18.75) +
               ((20 - 18.75)^2 / 18.75) +
               ((10 - 6.25)^2 / 6.25)

print(chi_square)

## Chi-square distribution
pchisq(3.11, df = 3, lower.tail = FALSE)

lundquist-ecology-lab

data(iris)
df <- iris

# Box plots
boxplot(Petal.Width ~ Species, data = df)

# Strip plot
library(lattice)
stripplot(Petal.Width ~ Species, data = df, jitter = TRUE)

lundquist-ecology-lab

data(iris)
df <- subset(iris, iris$Species == "setosa")

wilcox.test(df$Sepal.Width, df$Sepal.Length)

lundquist-ecology-lab

data(iris)
df <- iris

kruskal.test(Petal.Width ~ Species, data = df)

lundquist-ecology-lab

library(palmerpenguins)
data(penguins)
penguins <- na.omit(penguins)

# Correlation
cor.test(penguins$bill_length_mm, penguins$bill_depth_mm)

# Regression (linear model)
model_1 <- lm(bill_length_mm ~ bill_depth_mm, data = penguins)
summary(model_1)