Midterm code summer 2025

#Always load your libraries and data first
library(ggplot2)
library(dplyr)
library(lsr)
library(descr)
library(Hmisc)
library('lehmansociology')
data(gss123)
options(scipen = 999)

#My example variables are fear (nominal dichotomous), wrkstat (nominal non-dichotomous,
#health (ordinal), and speduc (interval-ratio). 
#Replace the variable names I use with your own variables
#Remember to change the titles, labels, etc. too
#You may also need to change the binwidth for the histogram

#FREQUENCY TABLES
#NOMINAL DICHOTOMOUS
frequency(gss123$fear, title= "Frequency Distribution of 
          Fear of Walking Alone at Night, GSS")
          
#NOMINAL NON-DICHOTOMOUS
frequency(gss123$wrkstat, title= "Frequency Distribution of 
          Employment Status, GSS")
#ORDINAL
frequency(gss123$health, cumulative.percent = TRUE, 
          title = "Frequency Distribution of 
          Self-Reported Health, GSS")
          
#INTERVAL RATIO
frequency(gss123$speduc, cumulative.percent = TRUE,
          title = "Distribution of Spouses'
          Highest Year of Education Attained, GSS")

#GRAPHS
#NOMINAL DICHOTOMOUS
ggplot(data=subset(gss123, !is.na(fear)), aes(x = fear)) + 
  geom_bar(color="red", fill="white", aes(y = ((..count..)/sum(..count..)))) + 
  scale_y_continuous(labels = scales::percent) + 
  ggtitle("Bar Graph of Whether Respondent is Afraid 
  to Walk Alone at Night, GSS") + 
  labs(y="Percent", x="Afraid to Walk Alone") +
  theme(axis.text.x=element_text(angle=-45))

#NOMINAL NON-DICHOTOMOUS
ggplot(data=subset(gss123, !is.na(wrkstat)), aes(x = wrkstat)) + 
  geom_bar(color="red", fill="white", aes(y = ((..count..)/sum(..count..)))) + 
  scale_y_continuous(labels = scales::percent) + 
  ggtitle("Bar Graph of Respodents' Employment Status, GSS") + 
  labs(y="Percent", x="Employment Status") +
  theme(axis.text.x=element_text(angle=-45))

#ORDINAL
ggplot(data=subset(gss123, !is.na(health)), aes(x=health)) + 
  geom_bar(color="red", fill="white", aes(y = ((..count..)/sum(..count..)))) + 
  scale_y_continuous(labels = scales::percent) + 
  ggtitle("Bar Graph of the Distribution of 
          Self-Reported Health, GSS") + 
  labs(y="Percent", x="Health Condition") +
  theme(axis.text.x=element_text(angle=-45))

#INTERVAL RATIO
ggplot(data = gss123, aes(x = speduc)) + 
  geom_histogram(color="blue", fill="pink", binwidth =1, 
                 aes(y=(..count../sum(..count..))*100)) + 
  ggtitle("Distribution of Spouse's Highest Year
          of Education Attained, GSS") + 
  labs(y="Percent", x="Highest Year of Education") 

#CENTRAL TENDENCY
#NOMINAL DICHOTMOUS AND NON-DICHOTOMOUS
MODE(gss123$fear)
MODE(gss123$wrkstat)

#ORDINAL
frequency(gss123$health, cumulative.percent=TRUE, title="GSS Repondents' 
          Health Condition")
frequency(as.numeric(gss123$health))
MODE(gss123$health)
median(as.numeric(gss123$health), na.rm=TRUE)

#INTERVAL RATIO
summary(gss123$speduc)
MODE(gss123$speduc)
median(gss123$speduc, na.rm=TRUE)
mean(gss123$speduc, na.rm=TRUE)

#MEASURES OF VARIABILITY - INTERVAL RATIO
#Remember that the range = maximum-minimum
summary(gss123$speduc, na.rm=TRUE)
IQR(gss123$speduc, na.rm=TRUE)
var(gss123$speduc, na.rm=TRUE)
sd(gss123$speduc, na.rm=TRUE)