Term Paper

Due by 11 PM Friday, May 5, 2023.

Your term paper should incorporate a revised version of what you wrote for your Analysis Task and be 4-6 pages longer than that revision of what you wrote for your Analysis Task. That is, the rest of your paper beyond what you wrote for the Analysis Task should be 4-6 pages.

Here are some of the main things I’ll look for in your term paper:

  1. Write well: have a thesis statement and a theme that you follow through

  2. Critique a paper in the academic literature on topics related to things we have discussed in class. Don’t choose one of my papers. But the references lists in my papers on happiness and of the other papers listed below are good places to find a paper.

  3. (Drilling down on point 2.) Assume that the paper has flawed statistical interpretation. (In particular, results are typically overinterpreted to make them sound more exciting.) Do better on the statistical interpretation front. Use all of the things you learned about statistical interpretation in class that are relevant. (I’ll subtract points if a statistical interpretation principle was clearly relevant to what you are critiquing or to your own analysis and you don’t discuss it and add points if you do a great job discussing an issue.) The goal is not to solve everything but to show your awareness of the issues and do what can readily be done to think about what the issue implies. (For example, it is great if you can say which direction a bias is.)

  4. Weave in a revision of your analysis task. The integration of this with your critique of a paper in the literature doesn’t have to be perfect, but it is a plus if you can make the critique of a paper in the literature and your own statistical analysis fit together with a theme.

  5. Be timely: because of the exigencies of making grades for this and my other course, it is especially important that I get these term papers by the due date. However, I will still accept them, but with some points off, up to two days late.

The main idea for the term paper is to discuss an academic journal article on well-being skeptically. (I’ll add suggestions for academic journal articles to write about to this post when I get a chance.)

Here are some ways you might want to be skeptical:

  1. Scale-use differences might be creating an illusion. (How?)

  2. There is likely to be statistical bias relative to what the author or authors seem to be claiming or implying. (Make sure to explain which direction you think any story of possible statistical bias would bias things. Is the estimate in the paper likely to be higher than the truth or lower than the truth? What does that say about the truth?)

  3. A result that has a nominal p-value of 5% (t-statistic of 2 or so) really has about a 50% chance of being spurious, as indicated by replication studies. (By contrast, a result with a nominal p-value of 1/2 % (t-statistic of 3 or more) has only about a 5% chance of being spurious, and so is relatively trustworthy. Here though, “trustworthy” had to be taken in a narrow sense. Something is probably going on with that coefficient, but what is going on may be very different from what the authors claim. (See for example the rest of this list of reasons to be skeptical!)

  4. Happiness is not the same as utility. As my coauthored papers “Utility and Happiness,” “What Do You Think Would Make You Happier? What Do You Think You Would Choose?” “Can Marginal Rates of Substitution Be Inferred from Happiness Data? Evidence from Residency Choices” and “Beyond Happiness and Satisfaction: Toward Well-Being Indices Based on Stated Preference” suggest, there are many distinct meaning of happiness. Among them are:

    • utility

    • feeling happy

    • what people report on a survey about their happiness, life satisfaction or position on the ladder of life (all of which have a lot of data available)

    • Aristotelian noble happiness, often called “eudaimonia” or “eudaemonic well-being” in the literature

  5. Other theoretical issues

Papers with References Lists in which You Can Find a Paper to Critique (Note: Don’t Critique a Paper with Miles as a Coauthor—those papers are only included because they have highly relevant references lists):