Group Data Project

Overview

Your group will:

  • Propose a research question using ACS/Census data from IPUMS (or another dataset if you so choose).
  • Propose a methodology for answering the question.
  • Acquire the necessary data.
  • Conduct the analysis.
  • Present the results to the class.

Deliverables

  1. Research report
  2. Replication instructions
  3. Replication code
  4. Presentation

Research Report

The research report must be submitted as a Google Doc. Be sure to give edit access to edward.kung@gmail.com. The report should not exceed 5 pages, except to include tables and figures. The research report should include the following sections:

  • Project Description
    • What was the research question that you studied?
  • Background and Motivation
    • Why is the question important or interesting?
  • Hypothesis
    • What did you expect to find?
  • Data and Methodology
    • What data did you use to conduct the analysis?
      • What was the outcome variable?
      • What were the main covariates of interest?
      • What were the nuissance variables?
      • What was the unit of analysis?
    • Why did you choose to use this data?
    • How will you use the data to answer the research question?
  • Results and Discussion
    • Report your results here. Include tables and figures. Discuss your results as you present them.
    • Do the results support your hypothesis?
    • What are the implications of your results?
    • Are there alternative explanations for your results? What are the limitations of your methodology? How would you address those limitations in future work?
  • Conclusion
    • A brief, one paragraph concluding remarks.
  • References

The research report will be graded holistically on the following factors:

  • Clarity. Was I able to understand the report? Were parts of it confusing or hard to understand?
  • Accuracy. Did the report accurately describe the results? Were the interpretations of the results accurate?
  • Professionalism. Was the report formatted attractively? Was the language professional? Were the appropriate tables and figures included? Were references properly cited?
  • Contribution. Did the results meaningfully contribute to answering the research question? (Even if the hypothesis is rejected, that is still a meaningful contribution.)

Replication Instructions

The replication instructions must be submitted as a Google Doc. Be sure to give edit access to edward.kung@gmail.com. The replication instructions should:

  1. Explain the steps necessary to acquire the data you used for your project, exactly as described in the report.
  2. Say how many rows and columns the resulting data should have.
  3. If you have more than one script, explain how you used the different scripts to obtain your results. If you only used one script, simply say that the results can be obtained by running that script.

The replication instructions will be graded on whether or not I can successfully replicate your data and results.

Replication Code

The replication code must be submitted as a Google Doc. Be sure to give edit access to edward.kung@gmail.com. You can simply copy and paste your R code into a Google Doc. The reason I require it in a Google Doc is so I can make comments and suggestions more easily.

The replication code will be graded on the same general rubric as explained here.

Presentation

The presentations will be held during the normally scheduled final exam period. The presentations should use Google Slides and be about 10-15 minutes long. Not everyone in the group has to present. Choose to present in whatever way best conveys the results of your project.

The presentations will be graded according to the following rubric:

  • Clarity. Was the audience able to understand the presentation? Were parts of it hard or confusing to understand?
  • Comprehensiveness. Did the presentation contain all the key pieces of information from the report?
  • Professionalism. Were the slides formatted attractively? Was the language professional? Did the speaker make eye contact and speak engagingly?
  • Mastery. Did the presenters demonstrate a mastery of the topic? Were they able to answer questions thoughtfully and accurately?

Important Dates

  • Monday 11/11: Preferences Survey Due
  • Monday 11/18: Progress Report #1 Due
  • Monday 11/25: Progress Report #2 Due
  • Monday 12/2: Progress Report #3 Due
  • Monday 12/9: Progress Report #4 Due
  • Monday 12/16: Final Project Report Due
  • Date TBD: Presentations

Grading

  • Research Report (25 pts)
  • Replication Instructions (5 pts)
  • Replication Code (10 pts)
  • Presentation (15 pts)

You will also be required to submit frequent drafts of your report, replication instructions, and replication code. Each draft is worth 5 points and will simply be graded on whether or not you followed instructions, not on whether they are accurate or polished.

Example Project

An example project (written by me) is available.