Overview

Faculty in the department have active research programs that involve students during the academic year and summer. Summer research positions are open to Carleton students and are paid positions.

The faculty research projects for the summer of 2023 that have positions open for students are described below. Direct any questions you have about a project to the faculty running the project. The student stipend rate for the summer of 2023 is $540/week. A list of all science research opportunities and fellowships at Carleton College is also available.

If you would like to apply, please fill out out this application form by midnight February 17, 2023. You will be asked to list the project(s) of interest to you and provide an unofficial transcript. The number of students hired for each project is dependent on funding which is likely, but not certain, so the number of students ultimately hired for each project could change.

Summer 2023 Project Descriptions

Can We Use Differential Equations to Model Bias in Predictive Policing? (Joseph Johnson)

  • 1-2 students (student research partners)
  • 40 hours per week, June 19th-August 25th (10 weeks)
  • Mode: In-person is preferred, but virtual is acceptable if necessary

Differential equations have been used to model the spread of crime within an area. Specifically an SIR framework that assumes that contact between criminals and non-criminals lead to an increase in criminals and criminals can be removed from the system by incarcerating those individuals (but they will be placed back into society after serving their time behind bars). 

This summer our focus will be on the final part of the system, looking at the rate that criminals are removed from the system by incarceration. We will incorporate predictive policing⸺the use of mathematics, data analytics, and other techniques to hypothesize where crime will occur⸺into the SIR model in order to see if bias is generated due to the inclusion of predictive policing.

During this summer project you will:

  • Learn how to simulate differential equations using Python or MATLAB (depending on coding experience)
  • Develop your skill in Mathematica and use Mathematica to analyze ODEs
  • Write a report summarizing your findings over the summer

Prerequisites are differential equations (MATH 241). Experience with Mathematica, Python, or MATLAB is appreciated.

Analysis of Spatial Uncertainty in Modern Public Data (Claire Kelling)

  • 2 students (student research partners)
  • 40 hours per week, July 10- August 18 (6 weeks)
  • Mode: hybrid, virtual, or in-person (open to discussion) but students will need to be on the same timeline.

Spatial point process models rely on the availability of point-level data, or the precise location (ex: latitude/longitude coordinates) associated with each observed event. Uncertainty in point-level datasets is introduced for many reasons such as privacy-preserving efforts, geocoding algorithms, and data-gathering mechanisms. Privacy-preserving methods, such as radial perturbation, purposefully move points to allow for protection of the original location. Geocoding, the process of transforming addresses into coordinates, often introduces uncertainty into the geocoded point due to technological limitations. Datasets collected from news articles allow for novel analyses of challenging problems but also can lead to imprecise point locations of events. The students will analyze the impact of spatial uncertainty in point locations and we will work to propose measures that analysts can take to address this uncertainty. The research project will consist of a simulation study that introduces spatial uncertainty due to multiple structures, including purposeful structures due to privacy protection and more random structure, such as due to modern imprecise data collection efforts. After the conclusion of the simulation study, the students will implement a Bayesian approach to incorporating this spatial uncertainty into a model-based approach to analyzing spatially uncertain data. The students will benefit both from learning simulation approaches to spatial point process data and working with spatial analysis of point process models. This work has high potential to be published in peer reviewed journals and used by criminology and public health practitioners in the near future after the completion of the project. The students will work on different aspects of the simulation study simultaneously and collaboratively throughout the research period. This project will be computationally intensive and will require and further develop a significant amount of organizational and computational skills. At the conclusion of the project, the expectation is that the results are also written up as a report.

Prerequisites: Required: Regression, Statistical Inference; Preferred: Time Series OR Spatial Statistics, Bayesian Statistics

 Police Use of Force Ingram Olkin Forum Planning Assistant (Claire Kelling)

  • 1 student (student research assistant)
  • 7 hours per week, June 19- August 25 (10 weeks)
  • Mode: hybrid, virtual, or in-person (open to discussion)

The Student Research Assistant will be advised by Professor Kelling who chairs the Ingram Olkin Forum (IOF) Police Use of Force (UOF) Organizing Committee and will work closely with the National Institute of Statistical Sciences to help finalize planning of the upcoming Police Use of Force Ingram Olkin Forum in Fall 2023. We plan for the forum to be hosted at Carleton College. Tasks include finalizing the program, selecting topics for working group sessions, inviting participants (faculty, students, industry professionals, etc.), and other final logistics, such as meal, hotel, and conference venue logistics. The student will meet regularly with the Ingram Olkin Forum Organizing Committee. The student will also have the opportunity to attend and be recognized at the Fall forum and be recognized as an official member of the Organizing committee. The student will benefit from the experience of helping to organize a national forum on a statistical and substantive issue of significant importance, working closely with academic leaders in the field of statistics, and will be exposed to research at the intersection of statistics and social sciences. The position will be on average seven hours per week (could be more or less during some weeks depending on the needs of the faculty member and student) with a maximum of 75 hours over the span of the summer.

Prerequisites: None (Intro stats preferred for session coordination)