- HTML: https://www.opencasestudies.org/ocs-bp-co2-emissions
- GitHub: https://github.com//opencasestudies/ocs-bp-co2-emissions
- Bloomberg American Health Initiative: https://americanhealth.jhu.edu/open-case-studies
The purpose of the Open Case Studies project is to demonstrate the use of various data science methods, tools, and software in the context of messy, real-world data. A given case study does not cover all aspects of the research process, is not claiming to be the most appropriate way to analyze a given dataset, and should not be used in the context of making policy decisions without external consultation from scientific experts.
To cite this case study:
Wright, Carrie and Ontiveros, Michael and Jager, Leah and Taub, Margaret and Hicks, Stephanie. (2020). https://github.com/opencasestudies/ocs-bp-co2-emissions. Exploring CO2 emissions across time (Version v1.0.0).
We would like to acknowledge Megan Latshaw for assisting in framing the major direction of the case study.
We would also like to acknowledge the Bloomberg American Health Initiative for funding this work.
Exploring CO2 emissions across time
C02 emissions have been on the rise for many countries. CO2 emissions trap heat in the atmosphere which can lead to increased global temperatures which can cause vast influences on the health of people and our planet. In this case study we explore national differences in CO2 emissions overtime. We evaluate the relationship between CO2 emissions and average annual temperatures in the US. And we also examine the relationship between emissions and natural disasters, as well as other factors that may influence, be influenced by CO2 emissions.
- How have global CO2 emission rates changed over time? In particular for the US, and how does the US compare to other countries?
- Are CO2 emissions in the US, global temperatures, and natural disaster rates in the US associated?
In this case study we will be using data related to CO2 emissions, as well as other data that may influence, be influenced or relate to CO2 emissions.
In addition, we will use some data that is specific to the United States from the National Oceanic and Atmospheric Administration (NOAA), which is an agency that collects weather and climate data.
The skills, methods, and concepts that students will be familiar with by the end of this case study are:
Data Science Learning Objectives:
- Importing data from various types of Excel files and CSV files
- Apply action verbs in
dplyrfor data wrangling
- How to pivot between “long” and “wide” datasets
- Joining together multiple datasets using
- How to create effective longitudinal data visualizations with
- How to add text, color, and labels to
- How to create faceted
Statistical Learning Objectives:
- Introduction to correlation coefficient as a summary statistic
- Relationship between correlation and linear regression
- Correlation is not causation
Data from several .xlsx files and a couple of .csv files were imported
This case study particularly focuses on renaming variables, modifying
variables, creating new variables, and modifying the shape of the data
using fuctions from the
dplyr package such as:
This case study also covers combining data with
full_join() of the
dplyr package, including a comparison of the two
We also cover filtering with the
filter() function of the
package, removing NA values with the
drop_na() function of the
package, arrange data with the
arrange() function of the
package, as well as grouping and summarizing data with the
summarize() functions of the
We include a thorough and introductory explanation of ggplot2 including how to add color, facets and labels to plots.
In this case study we look at the correaltion between CO2 emissions and annual average temperatures in the US. We also evaluate the assocation between the two using a linear regression. We discuss the relationship between correlation and linear regression and how we interpret the findings.
Other notes and resources
RStudio cheatsheets Introduction to correlation Correlation coefficient
Correlation does not imply causation
Locally estimated scatterplot smoothing
Local polynomial regression
Methods to account for autocorrelation
US Environmental Protection Agency (EPA) Inventory of U.S. Greenhouse Gas Emissions and Sinks 2020 Report
National Climate Assessment Report
Greenhouse gases Climate change
Packages used in this case study:
|Package||Use in this case study|
|here||to easily load and save data|
|readxl||to import the excel file data|
|readr||to import the csv file data|
|dplyr||o view and wrangle the data, by modifying variables, renaming variables, selecting variables, creating variables, and arranging values within a variable|
|magrittr||to use and reassign data objects using the
|stringr||to select only the first 4 characters of date data|
|purrr||to apply a function on a list of tibbles (tibbles are the tidyverse version of a data frame)|
|tidyr||to drop rows with
|forcats||to reorder the levels of a factor|
|ggplot2||to make visualizations|
|directlabels||to add labels to plots easily|
|ggrepel||to add labels that don’t overlap to plots|
|broom||to make the output form statistical tests easier to work with|
|patchwork||to combine plots|
There is a
Makefile in this folder that allows you to type
make to knit the case study contained in the
index.html and it will also knit the
README.Rmd to a
markdown file (
README.md). Users can start at any section after the
“What are the data?” section, however some aspects about the code may be
explained in an earlier section.
Instructors can start at any section after the “What are the data?”
section. There is additional data about mortality over time in different
countries from the World Bank in the
extra subdirectory of the
directory. This could be used for additional analyses.
This case study is appropriate for those new to R programming and new to statistics. It is also appropriate for more advanced R users who are new to the Tidyverse.
Ask students to create a plot with labels showing the countries with the lowest CO2 emission levels.
Ask students to plot CO2 emissions and other variables (e.g. energy use) on a scatter plot, calculate the Pearson’s correlation coefficient, and discuss results.