Skip to main content

Analyzing Election and Polling Data in R

Learn R for data science by wrangling, visualizing, and modeling political data like polls and election results.

Start Course for Free
4 Hours15 Videos55 Exercises6,756 Learners4650 XP

Create Your Free Account

GoogleLinkedInFacebook

or

By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.

Loved by learners at thousands of companies

Course Description

This is an introductory course to the R programming language as applied in the context of political data analysis. In this course students learn how to wrangle, visualize, and model data with R by applying data science techniques to real-world political data such as public opinion polling and election results. The tools that you'll use in this course, from the dplyr, ggplot2, and choroplethr packages, among others, are staples of data science and can be used to analyze almost any dataset you get your hands on. Students will learn how to mutate columns and filter datasets, graph points and lines on charts, make maps, and create models to understand relationships between variables and predict the future. This course is suitable for anyone who already has downloaded R and knows the basics, like how to install packages.
  1. 1

    Presidential Job Approval Polls

    Free

    Chapter one uses a dataset of job approval polling for US presidents since Harry Truman to introduce you to data wrangling and visualization in the tidyverse.

    Play Chapter Now
    Introduction
    50 xp
    Selecting columns of data
    100 xp
    Filtering rows of data
    100 xp
    Averaging job approval by president
    50 xp
    Averaging approval ratings by president
    100 xp
    Averaging a column
    100 xp
    Visualizing Trump's approval over time
    50 xp
    Averaging president Trump's approval by month
    100 xp
    Calculating a rolling average of polls
    100 xp
    Visualizing Donald Trump's approval polls
    100 xp
    Bonus: Visualizing every president's approval
    100 xp
  2. 2

    U.S. House and Senate Polling

    In this chapter, you will embark on a historical analysis of "generic ballot" US House polling and use data visualization and modeling to answer two big questions: Has the country changed over time? Can polls predict elections?

    Play Chapter Now
    Elections and political parties
    50 xp
    Tidyverse refresher
    50 xp
    Measuring support for U.S. political parties
    100 xp
    Mutating a new column
    100 xp
    73 Years of "generic ballot" polls
    50 xp
    Comparing the Democratic lead by year
    100 xp
    A time series of House and Senate polling
    100 xp
    Visualizing a time series
    100 xp
    Graphing trend lines with geom_smooth()
    100 xp
    Calculating and visualizing error in polls
    50 xp
    Calculating error in polls
    100 xp
    Confidence intervals
    100 xp
    Geom_point() and geom_errorbar()
    100 xp
    Predicting winners with linear regression
    50 xp
    Fitting a model to past polls and results
    100 xp
    Making a prediction on new data
    100 xp
  3. 3

    Election Results and Political Demography

    This chapter teaches you how to make maps and understand linear regression in R. With election results from the United States and the United Kingdom, you'll also learn how to use regression models to analyze the relationship between two (or more!) variables.

    Play Chapter Now
    The 2016 US presidential election
    50 xp
    County-level election results and spread()
    100 xp
    County-level demographic data and left_join()
    100 xp
    Merging demographic and voting data
    100 xp
    Analyzing votes and demographic data
    100 xp
    Making county-level maps in R
    50 xp
    Mapping the Democratic vote by county
    100 xp
    Mapping the concentration of white Americans
    100 xp
    Analyzing results with linear regression
    50 xp
    Answering "why" questions for elections
    100 xp
    Multivariate regression in R
    100 xp
    The 2016 UK referendum to leave the EU (Brexit)
    50 xp
    Who was "supposed" to win?
    100 xp
    Brexit results
    100 xp
    UKIP and Brexit
    100 xp
    The "why" question for Brexit
    100 xp
  4. 4

    Predicting the Future of Politics

    In this ensemble of applied statistics and data analysis, you will wrangle, visualize, and model polling and prediction data for two sets of very important US elections: the 2018 House midterms and 2020 presidential election.

    Play Chapter Now
    The House of Representatives in 2018
    50 xp
    The "generic ballot" in 2018
    100 xp
    Polls in August and September
    100 xp
    Training a model to predict the future with polls
    50 xp
    Training a model
    100 xp
    Predictions on new data
    100 xp
    Uncertainty
    50 xp
    The presidency in 2020
    50 xp
    A model for presidential elections
    100 xp
    Training the model
    100 xp
    Predicting 2020 with the model
    100 xp
    Course recap
    50 xp

Datasets

Brexit PollsBrexit ResultsGallup Approval PollsGeneric BallotUS Pres 2016 by County

Collaborators

dcamposliz
David Campos
chester
Chester Ismay
shoninouye
Shon Inouye

Prerequisites

Introduction to the Tidyverse
G Elliott Morris Headshot

G Elliott Morris

Data Journalist

Elliott Morris is a data journalist who uses applied statistics and data science techniques with R to analyze, visualize, and model political (and other) data. Before he wrote articles and code professionally, he studied government, history, and computer science at the University of Texas at Austin. He shares his work frequently on Twitter (@gelliottmorris) and writes about data in politics at his blog, The Crosstab.
See More

What do other learners have to say?

    Join over 10 million learners and start Analyzing Election and Polling Data in R today!

    Create Your Free Account

    GoogleLinkedInFacebook

    or

    By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.