#load correlation package install.packages("ggpubr") #load data read.csv my_data <- read.csv("[file directory]", encoding="UTF-8") #check data colnames(my_data) #visualization scatter plot library("ggpubr") ggscatter(my_data, x = "rugzakken", y = "statusscore12", add = "reg.line", conf.int = TRUE, cor.coef = TRUE, cor.method = "pearson", xlab = "Percentage rugzakken", ylab = "Status van het postcodegebied") # Selecting observations based on variable values new_data <- my_data [which (my_data$rugzakken < 10.0),] #visualization scatter plot library("ggpubr") ggscatter(new_data, x = "rugzakken", y = "statusscore12", add = "reg.line", conf.int = TRUE, cor.coef = TRUE, cor.method = "pearson", xlab = "Percentage rugzakken", ylab = "Status van het postcodegebied") #correlation tests cor.test(new_data$rugzakken, new_data$statusscore12, method = "kendall") cor.test(new_data$rugzakken, new_data$statusscore12, method = "spearman")