JFK Case Study
In November 1963, just before President Kennedy's assassination, 57% of Americans approved of his performance. What drove that number — and how does the answer shift across region, age, and political alignment? Seven tools let you explore the data yourself.
Six Ways to Engage with the Data
Two simulators run on the published model. A stress test challenges the headline, and Model Checks validate it — a triangulation check re-derives the estimate a second, assumption-independent way, and a Bayesian key driver analysis separates the factors that move approval from those that only track it. An explorer and a model builder let anyone go further — investigate any of three outcomes in the data and build their own models, whether to challenge the published Approval account or to look at outcomes the published model doesn't address.
All-or-Nothing Simulator
Pin every respondent to one chosen response level per factor and see how Kennedy's 57% approval shifts. Runs on the published model.
Try itFine-Tuning Simulator
Same published model, but redistribute response shares gradually rather than pinning. Watch how small distributional changes move the approval needle.
Try itNon-Response Test
Specify a nonresponse pattern and see whether the 57% headline would survive it. A vulnerability check on the released score, separate from the explanatory model.
Try itModel Checks
Two independent checks on the model behind the headline. A triangulation check re-derives a predicted change a second, assumption-independent way; a Bayesian key driver analysis separates the factors that move approval from those that only track it.
Try itSurvey Explorer
Browse the raw responses. See how Americans answered each question, which questions moved together, and how one group compared to another. Frequencies, cross-tabs, and correlations — against any of the three outcomes.
Try itModel Builder
Pick any of three outcomes — Approval (a binary cut or the full ordered scale), Vote Intention (a Kennedy-vs-Goldwater head-to-head or the three-way leaned race), or Tax Cut Support — and refit with whichever predictors you choose. Add or remove survey questions, restrict the fit to a subgroup, or build a competing model from scratch. See where the published Approval account holds up — or model an outcome it doesn't cover.
Try itHistorical Context: November 1963
Key Events Timeline
November 1
South Vietnamese coup against Diem
November 18
JFK's final public speech in Tampa
November 22
Assassination in Dallas
Civil Rights
Civil Rights Act stalled in Congress
Vietnam
16,000 U.S. military advisors deployed
Cold War
Cuban Missile Crisis aftermath
Economy
5.5% unemployment, 4.4% GDP growth
The Original Survey
Louis Harris & Associates surveyed a nationally representative sample of likely voters for Newsweek just before JFK's assassination. Most reports based on this kind of survey stopped at the topline; this case study reopens it — refit on subgroups, swap predictors, stress the headline against nonresponse.
This dataset is the proof-of-concept for our paper, Beyond Isolated Headlines, currently under peer review.
Survey Topics Covered:
Beyond this case study
See how the same approach travels to other domains, or read how engagements are structured.