Research Project(SOC222)
Anmol Khangura (1009012015) Aryan Dogra (1009191964) Nicholas Sallay (1008257397)
# List of packages
packages <- c("tidyverse", "modelsummary", "flextable",
"fst", "viridis", "knitr", "kableExtra", "rmarkdown", "ggridges", "questionr")
# Install packages if they aren't installed already
new_packages <- packages[!(packages %in% installed.packages()[,"Package"])]
if(length(new_packages)) install.packages(new_packages)
# Load the packages
lapply(packages, library, character.only = TRUE)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.0
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
##
## Attaching package: 'flextable'
##
##
## The following object is masked from 'package:purrr':
##
## compose
##
##
## Loading required package: viridisLite
##
##
## Attaching package: 'kableExtra'
##
##
## The following objects are masked from 'package:flextable':
##
## as_image, footnote
##
##
## The following object is masked from 'package:dplyr':
##
## group_rows## [[1]]
## [1] "lubridate" "forcats" "stringr" "dplyr" "purrr" "readr"
## [7] "tidyr" "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [13] "grDevices" "utils" "datasets" "methods" "base"
##
## [[2]]
## [1] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [6] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [11] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [16] "datasets" "methods" "base"
##
## [[3]]
## [1] "flextable" "modelsummary" "lubridate" "forcats" "stringr"
## [6] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [11] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [16] "utils" "datasets" "methods" "base"
##
## [[4]]
## [1] "fst" "flextable" "modelsummary" "lubridate" "forcats"
## [6] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [11] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [16] "grDevices" "utils" "datasets" "methods" "base"
##
## [[5]]
## [1] "viridis" "viridisLite" "fst" "flextable" "modelsummary"
## [6] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [11] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [16] "stats" "graphics" "grDevices" "utils" "datasets"
## [21] "methods" "base"
##
## [[6]]
## [1] "knitr" "viridis" "viridisLite" "fst" "flextable"
## [6] "modelsummary" "lubridate" "forcats" "stringr" "dplyr"
## [11] "purrr" "readr" "tidyr" "tibble" "ggplot2"
## [16] "tidyverse" "stats" "graphics" "grDevices" "utils"
## [21] "datasets" "methods" "base"
##
## [[7]]
## [1] "kableExtra" "knitr" "viridis" "viridisLite" "fst"
## [6] "flextable" "modelsummary" "lubridate" "forcats" "stringr"
## [11] "dplyr" "purrr" "readr" "tidyr" "tibble"
## [16] "ggplot2" "tidyverse" "stats" "graphics" "grDevices"
## [21] "utils" "datasets" "methods" "base"
##
## [[8]]
## [1] "rmarkdown" "kableExtra" "knitr" "viridis" "viridisLite"
## [6] "fst" "flextable" "modelsummary" "lubridate" "forcats"
## [11] "stringr" "dplyr" "purrr" "readr" "tidyr"
## [16] "tibble" "ggplot2" "tidyverse" "stats" "graphics"
## [21] "grDevices" "utils" "datasets" "methods" "base"
##
## [[9]]
## [1] "ggridges" "rmarkdown" "kableExtra" "knitr" "viridis"
## [6] "viridisLite" "fst" "flextable" "modelsummary" "lubridate"
## [11] "forcats" "stringr" "dplyr" "purrr" "readr"
## [16] "tidyr" "tibble" "ggplot2" "tidyverse" "stats"
## [21] "graphics" "grDevices" "utils" "datasets" "methods"
## [26] "base"
##
## [[10]]
## [1] "questionr" "ggridges" "rmarkdown" "kableExtra" "knitr"
## [6] "viridis" "viridisLite" "fst" "flextable" "modelsummary"
## [11] "lubridate" "forcats" "stringr" "dplyr" "purrr"
## [16] "readr" "tidyr" "tibble" "ggplot2" "tidyverse"
## [21] "stats" "graphics" "grDevices" "utils" "datasets"
## [26] "methods" "base"italy_data <- read.fst("italy_data.fst")- infer package
# Filter data for Italy
italy_data <- italy_data %>%
filter(cntry == "IT") %>%
# Mutate variables
mutate(
ccrdprs = case_when(
ccrdprs %in% c(66, 77, 88, 99) ~ NA_character_,
TRUE ~ as.character(ccrdprs)
),
lrscale = case_when(
lrscale %in% 0:3 ~ "Left",
lrscale %in% 7:10 ~ "Right",
TRUE ~ NA_character_
)
)
# Create contingency table
cont_table <- table(italy_data$ccrdprs, italy_data$lrscale)
# Ensure at least one observation in each cell
cont_table[is.na(cont_table)] <- 0
# Calculate expected values
expected_values <- outer(rowSums(cont_table), colSums(cont_table)) / sum(cont_table)
# Calculate chi-square statistic
chi_square_stat <- sum((cont_table - expected_values) ^ 2 / expected_values)
# Degrees of freedom
df <- (nrow(cont_table) - 1) * (ncol(cont_table) - 1)
# Calculate p-value
p_val <- 1 - pchisq(chi_square_stat, df)
print(chi_square_stat)## [1] 27.5058print(p_val)## [1] 0.002164869#the ch-square statistic is 27.5 and the p-value is 0.002 which indicates to reject the null hypothesis
- Regression Models
N/A
- Visual
# Bar chart for 'What Impact Does Socioeconomic Status Have on Health Outcomes in Italy'
ggplot(italy_data %>%
mutate(clsprty = ifelse(clsprty %in% c(7, 8), NA, clsprty)),
aes(x = clsprty)) +
geom_bar(na.rm = TRUE) +
labs(title = "Distribution of Socioeconomic Status in Italy",
x = "Socioeconomic Status",
y = "Frequency")