---

title: “Global CO2 Emissions from Fossil Fuels from 1751-2010”

author: “Xavier Tuominen”

date: “2024-11-18”

output: html_document

---

Introduction This report provides descriptive statistics for selected columns in the data frame, with values measured in million metric tons.

Load Data

#url of data
url <- "https://datahub.io/core/co2-fossil-global/r/global.csv"
#reads data from url
data <- read.csv(url)
#displays data
head(data)

##   Year Total Gas.Fuel Liquid.Fuel Solid.Fuel Cement Gas.Flaring Per.Capita
## 1 1751     3        0           0          3      0           0         NA
## 2 1752     3        0           0          3      0           0         NA
## 3 1753     3        0           0          3      0           0         NA
## 4 1754     3        0           0          3      0           0         NA
## 5 1755     3        0           0          3      0           0         NA
## 6 1756     3        0           0          3      0           0         NA

Descriptive Statistics

Total CO2 Emissions

  mean_total <- mean(data$Total, na.rm = TRUE)
  sd_total = sd(data$Total, na.rm = TRUE)

  cat("The mean of total CO2 is ", mean_total, ".\n", sep = "")

## The mean of total CO2 is 1402.788.

  cat("The standard deviation of total CO2 is ", sd_total, ".\n", sep = "")

## The standard deviation of total CO2 is 2253.099.

Total CO2 Emissions Per Capita

  mean_total_per_capita <- mean(data$Per.Capita, na.rm = TRUE)
  sd_total_per_capita = sd(data$Per.Capita, na.rm = TRUE)

  cat("The mean of total CO2 per capita is ", mean_total_per_capita, ".\n", sep = "")

## The mean of total CO2 per capita is 1.054754.

    cat("The standard deviation of total CO2 per capita is ", sd_total_per_capita, ".\n", sep = "")

## The standard deviation of total CO2 per capita is 0.17863.

Probability

Probability of Total Amount of Emissions Increasing

  count <- 0
  max_num = nrow(data) - 1

  for(i in 1:max_num)
  {
    if(data$Total[i] > data$Total[i+1])
    {
      count <- count + 1
    }
  }
  
  probability <- count / nrow(data)
  cat("The probability that total CO2 emissions increased is ", probability, ".\n", sep = "")

## The probability that total CO2 emissions increased is 0.1076923.

Probability that Gas Flaring > 40 and Gas Fuel > 1000

  count <- 0
  max_num = nrow(data) - 1
  GAS_FLARING_TARGET <- 40
  GAS_FUEL_TARGET <- 1000
  for(i in 1:nrow(data))
  {
    if(data$Gas.Flaring[i] > GAS_FLARING_TARGET && data$Gas.Fuel[i] > GAS_FUEL_TARGET)
    {
      count <- count + 1
    }
  }
  
  probability <- count / nrow(data)
  cat("The probability that gas flaring emissions is over 40 and gas fuel emissions is over 1000 is  ", probability, ".\n", sep = "")

## The probability that gas flaring emissions is over 40 and gas fuel emissions is over 1000 is  0.04615385.

Confidence Interval for Total Emissions

  mean_total <- mean(data$Total, na.rm = TRUE)
  sd_total <- sd(data$Total, na.rm = TRUE)
  confidence_level <- 0.95
  sample_size <- nrow(data)
  
  value <- qt((1 + confidence_level) / 2, sample_size)
  
  error_margin <- value * (sd_total / sqrt(sample_size))
  
  lower_interval <- mean_total - error_margin
  upper_interval <- mean_total + error_margin
  
  cat("Confidence intervals of total CO2 emissions with a confidence of ", confidence_level, "%. Has a lower confidence interval of: ", lower_interval, "and an upper confidence of ", upper_interval, ".\n", sep = "")

## Confidence intervals of total CO2 emissions with a confidence of 0.95%. Has a lower confidence interval of: 1127.639and an upper confidence of 1677.937.