This assignment is designed for us to develop a better understanding of how you approach the types of research tasks that are part of the research associate role. You will have a week to complete this assignment. We expect it to take approximately four hours or less to complete.
You do not need to complete the assignment all at once; you can work on whatever schedule you’d like. Feel free to consult outside resources for help, as needed, but the work must be your own.
Please answer questions 1a and 1b in complete sentences and return your answers in a Word document or other type of text file. Maximum 250 words per question please.
Question 1a. Administrative police data are notoriously “messy” and variable across agencies. Imagine the VP of science provides you with calls for service (CFS) data from 10 local law enforcement agencies and asks you to produce a research memo summarizing (a) the annual volume/frequency of calls in each department, and (b) how those calls are distributed across neighborhoods. Explain how you would go about approaching this assignment. (Note: You do not need to have worked with CFS data before to answer this question well; we are interested in the process you would use to undertake this task.)
Question 1b. CPE’s Science program works with police administrative data on use of force, vehicle stops, pedestrian stops, arrests, and calls for service. We also supplement those data with contextual information from the American Community Survey. If you joined our team, what additional types of data (community economic indicators, health indicators, etc.) would you suggest we include in our database? And what are 2 general research questions you would be interested in exploring using these data?
We rarely receive law enforcement data in a form where it is ready to be analyzed without any cleaning/ wrangling. In this section, you will perform data wrangling tasks to show how you would approach the types of problems we often deal with, and then report results based on your processed data sets. This section is designed to test your ability to analyze data using tools and techniques employed by CPE. We are aiming to learn more about your skill set, as well as your analytic reasoning. Accordingly, please thoroughly document the decisions that inform your answers for each exercise.
All code should be in Stata or in R with accompanying markdown. If using Stata, you should submit a .do file. If using R, you may submit either an RMD document or a Jupyter notebook
using an R kernel. In order for your assignment to be considered complete, you will need to submit the following:
1)a .do with comments (if using Stata), or .rmd or .ipynb file(s) (if using R) with all of your code and documentation/explanation.
2)A .pdf or .html version of your markdown (if using R) or log file (if using Stata) in case there are problems with knitting or running your file).
Your answers to this assignment will be evaluated according to the following criteria:
1)Were the instructions followed and are the results correct?
2)Were decisions properly documented and was detailed motivation given?
3)Was the code cleanly written and efficient? (If using R, we encourage, but do not require, you to use the Tidy framework and accompanying Tidyverse packages).
For this assignment, we will be using data from the City of Minneapolis Open Data Portal. These are public datasets, and we are hosting them in S3 so that everyone will be working with the same version. The datasets we will be referencing will be the following:
-Police Use of Force: Records of each time an officer in the department used force against a civilian
-Police Stops: Records of pedestrian and vehicle stops
Question 2a. Counting Use of Force Incidents. CPE defines an incident of use of force as one person having force used against them by the police on one occasion, regardless of how many officers or types of force are involved. Some departments might define a single incident as involving multiple suspects, while some other departments record a use of force incident for each type of force used against a person or for each officer who used force during the incident. Using the Police Use of Force dataset, along with your understanding of the data and the definition we just gave you, please deduplicate the use of force dataset so that it meets our definition. You can either “tidy” the dataset so that each row represents an incident according to our definition, or you can create a unique identifier for each incident as defined here. If you are deduplicating the dataset by creating a “tidy” dataset, you may disregard columns that are not important to the definition of an incident. Report the number of unique incidents you identified in the dataset according to our definition.
Question 2b. Examining Racial/Ethnic Distribution of Pedestrian Stops. In Minneapolis, the Police Stops dataset contains records of both pedestrian and vehicle stops. In addition, this data set contains a number of stops that do not meet our definition of a valid stop. These might be cancelled interactions, incidents where the police could not find the person they were looking for, incidents where the police helped a stranded motorist, etc. Please complete the data wrangling tasks outlined in Steps 1-3 below to process this data set, and then create and interpret 1-2 figures presenting findings from these data as described in Steps 4 and 5.
Step 1. Exclude rows with the following Disposition codes:
●GOA-Gone on Arrival
●AOK- All OK
●UTL-Unable to Locate
●TOW-Towed
●SEC- Secured
●CNL-Cancel
●UNF-Unfounded
●NOS-No Service
●AQT-All Quiet
●FTC-Fail to Clear
●FAL-False
Step 2. Divide the dataset into vehicle stops and pedestrian stops using indicator variables as flags or by creating separate dataframes. Vehicle stops are stops where the “problem” is either “Traffic Law Enforcement (P)” or “Suspicious Vehicle (P)”; pedestrian stops are all other stops.
Step 3. Recode race/ethnicity into the following categories: Black, White, Latinx, Asian, Native American, and “other race” (which includes multiple races or unknown race).
Step 4. Using whatever data visualization package you prefer (Stata, ggplot, base R, etc.), please create 1-2 figures that answer these questions about pedestrian stops only.
●What percentage of all pedestrian stops are experienced by each racial/ethnic group?
●For each racial/ethnic group, what percentage of stops results in a search being conducted?
Please keep data visualization best practices in mind. The figure(s) you produce should be of a quality level that you would feel comfortable submitting for publication; please avoid charts with interactive elements.
Step 5. Write 2-3 sentences interpreting the data displayed in your figure(s). For context, the city of Minneapolis is 62.4% white, 16.9% Black, 9.1% Latinx, 6% Asian, and 0.9% American Indian (the remaining 4.7% identified with other or multiple races) according to the 2017 American Community Survey 5-year estimate.
CS 340 Milestone One Guidelines and Rubric Overview: For this assignment, you will implement the fundamental operations of create, read, update,
Retail Transaction Programming Project Project Requirements: Develop a program to emulate a purchase transaction at a retail store. This
7COM1028 Secure Systems Programming Referral Coursework: Secure
Create a GUI program that:Accepts the following from a user:Item NameItem QuantityItem PriceAllows the user to create a file to store the sales receip
CS 340 Final Project Guidelines and Rubric Overview The final project will encompass developing a web service using a software stack and impleme
