Final Paper Assignment
Sociology 229A: Event History Analysis
Due: Start of class (2:00) June 3
Length: 4-5 Pages
Overview
The goal of this project is to conduct some simple event history analyses of a dataset and (briefly) write up the results. I will provide a dataset and some general hypotheses to test. Your task will be to analyze the data, conduct diagnostics, and accurately describe your findings.
The dataset includes information about the founding and
demise of “licensed lenders” in
The unit of analysis is the organization. The event of interest is “organizational mortality,” the failure or dissolution of a bank. The dataset contains multiple-record-per-case data with information on organizational founding and death, as well as constant and time-varying covariates.
CHOOSE FIVE OUT OF THE FOLLOWING SEVEN RESEARCH QUESTIONS TO EXAMINE IN YOUR PAPER. Some questions cannot be answered with a Cox model, depending on the time-clock that you choose. If you use a Cox model, be sure to choose questions that you can actually answer!
Research Questions:
Issues & Diagnostics:
The Paper
Start with an abstract that briefly summarizes the topic and results. That will serve as an introduction to your paper. Write up your paper in the form of a “Methods” and “Results” section of a journal article. (You need not include a background, intro, lit review or theory section. Nor do you need a discussion section or conclusion.)
In the methods section: Start with a description of the basic dependent variable – the outcome of interest, and the way that the analysis is set up. Indicate the time-clock, whether you have time-varying covariates, and whether or not you have repeating events. Next, describe the kind of event history model you chose (Cox or various parametric options) and the justification for your decision. If plots or diagnostics were used to make your choice, include them in an appendix. Provide the relevant formula for the hazard rate. You may omit a description of the independent variables. Assume the reader is familiar with them. Also: Describe your efforts to address non-proportionality in the assets variable, and your findings regarding outliers. Indicate if any cases were removed from the analysis. Include the outlier plot as an appendix. (You may optionally include other diagnostics in appendices, if you wish.)
In the results section: Provide a table of results. You may use your discretion about how many models to present. A single model with all the variables (described above) is sufficient. I suggest presenting raw coefficients, but you can add hazard ratios if you wish. Describe your findings and indicate your answers to the arguments/hypotheses raised above. Be sure to provide clear interpretations of coefficients. For at least one independent variable I want you to go beyond merely interpreting the effect of a 1-unit change… For instance, you might discuss the impact on the hazard rate of moving from the bottom quartile in assets to the top quartile (or some other meaningful increment).
Finally, conclude by listing three ways to further improve your study. These could include additional variables to include in the analysis, other problems identified in the diagnostics, problems with model fit, measurement issues, etc. Just take a few minutes to show that you can think critically about the data and models that you are using.
I’m guessing you’ll have (roughly) a .5 page abstract, 1.5 pages of “Methods” and 2-3 pages of “Results.” Plus a table. Plus appendices with a hazard plot, a residual plot, and optionally some additional diagnostics. You may write more if needed, by try to keep things tight/focused.