1 Part 1

library(foreign) 
library(tidyverse)
## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.1 ──
## ✓ ggplot2 3.3.5     ✓ purrr   0.3.4
## ✓ tibble  3.1.4     ✓ dplyr   1.0.7
## ✓ tidyr   1.1.3     ✓ stringr 1.4.0
## ✓ readr   2.0.1     ✓ forcats 0.5.1
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()
library(boot)
SCS <- read.spss("SCS_QE.sav", to.data.frame = TRUE)
## re-encoding from CP1252
## Warning in read.spss("SCS_QE.sav", to.data.frame = TRUE): Undeclared level(s) 0
## added in variable: married
b.stat <- function(data, i) {
   b.dat <- data[i ,]
   out.lm <- lm(mars ~ mathpre, b.dat)
   predict(out.lm, data.frame(mathpre=SCS$mathpre))
}
b.out <- boot(SCS, b.stat, R = 2000)

b.ci <- t(sapply(1:nrow(SCS), function(x) boot.ci(b.out, index = x, type = 'perc')$percent))[, 4:5]
dimnames(b.ci) <- list(rownames(SCS), c('lower', 'upper'))

combined <- cbind(SCS, b.ci)

ggplot(combined, aes(x = mathpre, y = mars)) + geom_jitter() + theme_bw() + labs(x = 'Mathematics Achievement Score', y = 'Mathematics Anxiety Score', title = 'Scatterplot of Mathematics Achievement and Mathematics Anxiety Scores') + geom_smooth(method='lm', formula = y~x, se=FALSE) + geom_ribbon(aes(ymin=lower, ymax=upper), alpha = 0.3, fill='#69b3a2')

2 Part 2

data <- read_csv("WHO COVID-19 global table data October 28th 2021 at 2.03.36 PM.csv")
## New names:
## * `` -> ...13
## Rows: 238 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr  (2): Name, WHO Region
## dbl (10): Cases - cumulative total, Cases - cumulative total per 100000 popu...
## lgl  (1): ...13
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
focus <- c('Brazil', 'United States of America', 'Canada', 'South Africa', 'Ethiopia', 'Kenya', 'Iran (Islamic Republic of)', 'Iraq', 'Pakistan', 'The United Kingdom', 'Russian Federation', 'Italy', 'Philippines', 'Japan', 'Malaysia', 'India', 'Indonesia', 'Thailand')

data %>% filter(Name %in% focus) %>%   mutate(rate = `Deaths - cumulative total`/`Cases - cumulative total`, SE = sqrt(rate*(1-rate)/`Cases - cumulative total`)) %>%
ggplot(aes(x=Name, y=rate)) + geom_bar(position=position_dodge(), stat='identity') + theme_bw() + xlab('WHO: # Reported Deaths / # Reported Cases') + facet_grid(~ `WHO Region`, scale="free") + geom_errorbar(aes(ymin=rate-1.96*SE, ymax=rate+1.96*SE), width=.2) + theme(axis.text.x = element_text(size=8, angle=90), strip.text=element_text(size=7)) + ylab('Mortality Rate') + xlab('Countries') + ggtitle('WHO Reporting Barplots by Region')

3 Part 3

library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
vaccine <- read_csv('covid_vaccines.csv')
## Rows: 8 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): Vaccine, Period
## dbl (3): VE against COVID-19 hospitalization (95% CI), Lower CI, Upper CI
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
vaccine
## # A tibble: 8 × 5
##   Vaccine                     Period    `VE against COVID… `Lower CI` `Upper CI`
##   <chr>                       <chr>                  <dbl>      <dbl>      <dbl>
## 1 Moderna                     Full sur…                 93         91         95
## 2 Moderna                     14–120 d…                 93         90         95
## 3 Moderna                     >120 day…                 92         87         96
## 4 Pfizer-BioNTech             Full sur…                 88         85         91
## 5 Pfizer-BioNTech             14–120 d…                 91         88         93
## 6 Pfizer-BioNTech             >120 day…                 77         67         84
## 7 Janssen (Johnson & Johnson) Full sur…                 71         56         81
## 8 Janssen (Johnson & Johnson) >28 days…                 68         49         80
plot <- ggplot(vaccine, aes(x=Period, y=`VE against COVID-19 hospitalization (95% CI)`)) + theme(axis.title.x = element_text(margin = margin(t = 70))) + geom_bar(position=position_dodge(), stat='identity') + theme_bw() + facet_grid(~ `Vaccine`, scale="free") + geom_errorbar(aes(ymin=`Lower CI`, ymax=`Upper CI`), width=.2) + theme(axis.text.x = element_text(size=8, angle=15), strip.text=element_text(size=8)) + ylab('Vaccine Effectiveness') + ggtitle('COVID-19 Vaccine Effectiveness Against Hospitalization')
ggplotly(plot)

Overall, it is clear that the Moderna Vaccine has higher effectiveness than the other vaccines. The error bars are also shorter, indicating a smaller margin of error for this vaccine. The Pfizer Vaccine is the second most effective, with shorter error bars for the ‘14-120 days after full vaccination’ and ‘Full surveillance period’ periods. The Johnson & Johnson vaccine is the least effective overall. This vaccine also has the largest error bars, indicating a greater margin of error for this vaccine.