Travel time estimation for ambulances using Bayesian data augmentation. Annals of Applied Statistics, to appear
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
Estimates of ambulance travel times on road networks are critical for effective ambulance base placement and real-time ambulance dispatching. We introduce new methods for estimat-ing the distribution of travel times on each road segment in a city, using Global Positioning System (GPS) data recorded during ambulance trips. Our preferred method uses a Bayesian model of the ambulance trips and GPS data. Due to sparseness and error in the GPS data, the exact ambulance paths and travel times on each road segment are unknown. To estimate the travel time distributions using the GPS data, we must also estimate each ambulance path. This is called the map-matching problem. We consider the unknown paths and travel times to be missing data, and simultaneously estimate them and the parameters of each road segment travel time distribution using Bayesian data augmentation. We also introduce two alternative estimation methods using GPS speed data that are simple to implement in practice. We test the predictive accuracy of the three methods on a subregion of Toronto, using simulated data and data from Toronto EMS. All three methods perform well. Point estimates of ambulance trip durations from the Bayesian method outperform estimates from the alterna-tive methods by roughly 5 % in root mean squared error. Interval estimates from the Bayesian method for the Toronto EMS data are substantially better than interval estimates from the alternative methods. Map-matching estimates from the Bayesian method are robust to large GPS location errors, and interpolate well between widely spaced GPS points.
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 | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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