August 19, 2021 EXPO 2021 Oral

Mathematical Modeling to Forecast U.S. Elections

[et_pb_section fb_built=”1″ fullwidth=”on” _builder_version=”3.22.6″][et_pb_fullwidth_post_title author=”off” comments=”off” featured_image=”off” _builder_version=”3.23.3″ title_font=”Standard||||||||” title_text_color=”#ffffff” title_font_size=”61px” title_line_height=”1.3em” meta_font=”Standard2||||||||” meta_text_color=”#ffffff” background_color=”#000000″ custom_padding=”||60px” title_font_size_tablet=”39px” title_font_size_phone=”28px” title_font_size_last_edited=”on|phone”][/et_pb_fullwidth_post_title][/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”3.23.3″][et_pb_row _builder_version=”3.23.3″ max_width=”1221px”][et_pb_column type=”2_5″ _builder_version=”3.23.3″][et_pb_image src=”https://thenurj.com/wp-content/uploads/2021/08/20210819155218_IMG_2548_2-scaled.jpg” align_tablet=”center” align_last_edited=”on|phone” module_id=”circle-image” _builder_version=”3.23.3″ width=”43%” width_tablet=”26%” width_last_edited=”on|desktop” custom_margin=”|49px||||”][/et_pb_image][et_pb_text _builder_version=”3.23.3″ text_font=”Standard2||||||||” text_font_size=”27px” min_height=”40px” custom_padding=”18px||”]William He[/et_pb_text][et_pb_image src=”https://thenurj.com/wp-content/uploads/2021/08/image_6487327.jpg” align_tablet=”center” align_last_edited=”on|phone” module_id=”circle-image” _builder_version=”3.23.3″ width=”43%” width_tablet=”26%” width_last_edited=”on|desktop” custom_margin=”|49px||||”][/et_pb_image][et_pb_text _builder_version=”3.23.3″ text_font=”Standard2||||||||” text_font_size=”27px” min_height=”40px” custom_padding=”18px||”]Emma Mansell[/et_pb_text][et_pb_text _builder_version=”3.23.3″ text_font=”Times New Roman||||||||” text_text_color=”#000000″ text_font_size=”18px”]

Adviser: Dr. Alexandria Volkening
Subject: Social Sciences
DOI: 10.21985/n2-9pqb-zz27

[/et_pb_text][et_pb_text _builder_version=”3.23.3″ text_font=”Times New Roman||||||||” text_font_size=”16px” custom_margin=”|70px||”]

William He is a third-year undergraduate student studying Pure and Applied Mathematics and Statistics at Northwestern University’s McCormick School of Engineering. He also has interests in Computer Science, and would like to pursue a career related to mathematical modeling. This research project is the first he has been involved in, with funding from the Undergraduate Research Assistant Program. During the summer of 2021, he participated in the UCLA Computational and Applied Math REU. At Northwestern, William is also a Murphy Scholar and president of the ASA Statistics Club.

Emma Mansell is a sophomore from Oakland, California majoring in Computer Science with a ISEN (Sustainability and Energy at Northwestern) certificate. She is focused on the intersections of tech and social and environmental justice, and her recent research has been in mathematical modeling of U.S. elections.

[/et_pb_text][/et_pb_column][et_pb_column type=”3_5″ _builder_version=”3.23.3″][et_pb_text _builder_version=”3.23.3″ text_font=”Standard2|600|||||||” text_font_size=”25px”]Abstract[/et_pb_text][et_pb_text _builder_version=”3.23.3″ text_font=”Times New Roman||||||||” text_font_size=”19px” text_line_height=”1.5em”]Now more than ever, forecasting the outcomes of U.S. elections is an important and challenging task. Traditionally, statistical or political-science methods have been employed to better understand how individuals will vote. Our approach differs in that we use mathematical modeling. Adapting methods commonly used in epidemiology to understand biological disease transmission, we model the spread of political affiliation (Democratic or Republican) across states using differential equations. We simulate thousands of possible election scenarios, accounting for uncertainty, to make a range of forecasts at the state level. The model’s final forecasts for presidential, senatorial, and gubernatorial elections from 2004 through 2016 have had accuracy comparable to popular forecasting sites, such as FiveThirtyEight. A new focus of our research is on how the accuracy of gubernatorial and senatorial forecasts changes over the months leading up to the election day. We will also discuss our forecasts of the 2020 U.S. elections, which we posted in real time last fall on a website that we created (https://modelingelectiondynamics.gitlab.io/2020-forecasts/). Finally, we will share our work on improving the accuracy of the model by weighting the polling data in different ways. Our research highlights how mathematical modeling can be used for data-driven forecasting on a topic of broad interest and suggests additional research in this field.
[/et_pb_text][/et_pb_column][/et_pb_row][et_pb_row _builder_version=”3.23.3″][et_pb_column type=”4_4″ _builder_version=”3.23.3″][et_pb_code _builder_version=”3.23.3″][/et_pb_code][/et_pb_column][/et_pb_row][et_pb_row _builder_version=”3.23.3″][et_pb_column type=”4_4″ _builder_version=”3.23.3″][et_pb_code _builder_version=”3.23.3″][/et_pb_code][/et_pb_column][/et_pb_row][/et_pb_section]