Project Instructions

As a major component of this class, you will work in teams of three1 to complete a statistical analysis focused on a topic of your choice. This task will require you to acquire relevant, publicly available data; analyze that data appropriately; and hand in a written technical report describing your analysis and its findings. This project is an opportunity to show off what you’ve learned about data analysis, statistical modeling, and written statistical communication.

Your project should be centered around a problem or question that you find interesting and that must be addressed (at least in part) using either multiple linear or multiple logistic regression. Projects from past semesters have considered questions such as:

Count on brainstorming at least half a dozen serious ideas before you can develop one of them into a full-fledged project. You’re free to use and analyze data from any source (so long as you are not repeating the same analysis as the original source).

Project Requirements

There are two core requirements that your project must satisfy:

  1. Your main analysis must use a multiple regression model. The response variable in this model may be either a numeric variable (i.e., fit a linear regression model) or a binary categorical variable (i.e., fit a logistic regression model). Your explanatory variables can be of any type.
  2. You must write a formal final report describing your analysis and its findings. More detailed expectations about this report are given below.

Timeline and Project Components

The project will be completed in 3 stages, though only the final stage will be formally graded:

  • Oct. 31: Group Selection
    One group member should fill out the Google form linked on Moodle with the names and email addresses of all final project group members.
  • Nov. 14: Topic and Data Selection
    One group member will submit a .csv file with your analysis dataset and a PDF (rendered from a .qmd file) that outlines your research topic and presents at least two exploratory visualizations. This is due at 11:59 p.m. on Moodle.
  • Dec. 12: Final Report
    Complete assignment (including the .qmd file, the corresponding PDF, and a .csv file with your data) due at 11:59 p.m. on Moodle.

Topic and Data Selection

Note

Due Friday November 14, 2025 at 11:59 p.m.

For this stage of the project, one group member should submit a .csv file with your analysis dataset and a PDF (rendered from a .qmd file) with the following information:

  1. Group Members: List the members of your group
  2. Data: Describe the data that you plan to use and the place/site that you sourced it from
  3. Research Question/Purpose: What specific question(s) do you hope to answer/what specifically do you hope to learn from analyzing these data with a regression model?
  4. Population: Specify what the observational units are (i.e. the rows of the data frame), describe the larger population/phenomenon to which you’ll try to generalize, and (if appropriate) estimate roughly how many such individuals there are in the population.
  5. Response Variable: Identify which variable from the data set will be your response variable.
    • If your outcome is numeric, explain: What are its units of measurement? What range of possible values can it take on?
    • If your outcome is categorical, explain: What are the levels of this variable? Which is considered a “success”, and which is considered “failure”?
  6. Explanatory Variables: Identify the explanatory variables that you plan to include in the richest possible model you consider. For each of these, explain:
    • If the explanatory variable is numeric: What are its units of measurement? What range of possible values can it take on?
    • If the explanatory variable is categorical, explain: What are the levels of this variable
  7. Exploratory Visualizations: To support your argument that you can use this data to address your question(s) of interest, create at least two exploratory data visualizations showing the relationships between variables of interest in your data.

Final Report

Note

Due Friday December 12, 2025 at 11:59 p.m.

For this stage of the project, one group member should submit a .csv file with your raw analysis dataset, the .qmd file that contains your analysis code, and the corresponding final report, rendered as a PDF. I should be able to download your submission, render your .qmd file, and reproduce the same report that your group submitted. There is no page minimum or maximum for the final report, but it should be no longer than is necessary. Your report must contain the following six sections:

  1. Abstract: A short, one paragraph summary of your project. The abstract should not consist of more than 5 or 6 sentences (150–250 words), but should relate what you studied and what you found. It need only convey a general sense of what you actually did and the high-level conclusions. The purpose of the abstract is to give a prospective reader enough information to decide if they want to read the full paper.
  2. Introduction: In a few paragraphs, you should explain clearly and precisely what your research question is, why it is interesting, what hypothesis you are testing, and what contribution you have made towards answering your research question (i.e., what you’re doing and why you’re doing it). Think of this section as an elaborated version of the “Purpose” section from your proposal. You should have at least 2–3 citations to previous research in this area to support your ideas and show what has already been done and what gap you are filling.
  3. Methods: The methods used to obtain and analyze the data (i.e., how you are addressing your research question). This should include a brief description of your data set. Some questions you should consider (though this is not an exhaustive list): What is the population that was sampled? How was the sample collected? What variables are included in your analysis? Where did they come from? What are units of measurement? How much missing data did you have and what did you do about it? How did you choose which variables to include in your model? What kind of model did you fit? What is the population form of that model? How did you evaluate the assumptions of this model? What hypothesis tests and inferential procedures did you conduct to investigate your research question? Don’t tell us the results, just tell us the steps you took. Think of this as like a reproducible lab report—someone else should be able to download the same data, follow your steps, and get the same results.
  4. Results: This section is an explanation of what your model tells us about the research question (i.e., what you found in the data through your analysis), presented through descriptive text, tables, and at least one figure/data visualization. I will be looking for a clear interpretation of your fitted model: you should interpret relevant coefficients in context, explain their practical importance, and provide corresponding confidence intervals. You should also interpret the results of any/all hypothesis tests in context. Remember that null results are equally as important to report as statistically significant findings. All figures and tables must look nice and professional.
  5. Discussion: A summary of your findings and a discussion of their limitations. First, remind the reader of the question that you originally set out to answer, and summarize your findings. Second, discuss the limitations of your model, and what could be done to improve it. You might also want to do the same for your data. Also include a few sentences about the strength(s) of your analysis / study. This is your last opportunity to clarify the scope of your findings before a journalist misinterprets them and makes wild extrapolations! Protect yourself by being clear about what is and is not implied by your research.

In addition to the above main content, you should include a title page with the project title and the names of all group members. You should also include any supporting details of your analysis in a “Data Analysis Appendix.” This is an excellent place to include things like large regression tables you don’t have space for in the main report, visualizations checking model assumptions, ANOVA tables for nested F-tests, tables of VIF statistics for multicollinearity, visualizations checking for influential points, etc. Finally, you should include a bibliography at the end of your report with properly formatted references.

Possible Data Sources

You should identify a data set that has a sample size large enough for analysis (ideally between 200 and 2,000 observations), that has a mix of continuous and categorical variables, and that comes from a reliable source. Potential starting points when looking for data include: