Case-crossover designs and overdispersion with application to air pollution epidemiology
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Over the last three decades, case-crossover designs have found many applications in health sciences, especially in air pollution epidemiology. They are typically used, in combination with partial likelihood techniques, to define a conditional logistic model for the responses, usually health outcomes, conditional on the exposures. Despite the fact that conditional logistic models have been shown equivalent, in typical air pollution epidemiology setups, to specific instances of the well-known Poisson time series model, it is often claimed that they cannot allow for overdispersion. This paper clarifies the relationship between case-crossover designs, the models that ensue from their use, and overdispersion. In particular, we propose to relax the assumption of independence between individuals traditionally made in case-crossover analyses, in order to explicitly introduce overdispersion in the conditional logistic model. As we show, the resulting overdispersed conditional logistic model coincides with the overdispersed, conditional Poisson model, in the sense that their likelihoods are simple re-expressions of one another. We further provide the technical details of a Bayesian implementation of the proposed case-crossover model, which we use to demonstrate, by means of a large simulation study, that standard case-crossover models can lead to dramatically underestimated coverage probabilities, while the proposed models do not. We also perform an illustrative analysis of the association between air pollution and morbidity in Toronto, Canada, which shows that the proposed models are more robust than standard ones to outliers such as those associated with public holidays.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it