THE RESULT
What the data shows
The largest computed metric is 3.733 for 19.0; the smallest is 0.7129 for 5.0. Metric: mean_co (CO reference concentration (source units)).
Each hour-of-day mean uses available reference readings only. This is not an exposure or compliance assessment.
| hour | observed hours | median co | mean co | p90 co |
|---|---|---|---|---|
| 0 | 329 | 1.6 | 1.786 | 2.8 |
| 1 | 323 | 1.3 | 1.468 | 2.4 |
| 2 | 320 | 0.9 | 1.099 | 2 |
| 3 | 312 | 0.7 | 0.8885 | 1.6 |
| 4 | 179 | 0.6 | 0.7587 | 1.32 |
| 5 | 317 | 0.6 | 0.7129 | 1.1 |
| 6 | 320 | 0.9 | 0.9216 | 1.5 |
| 7 | 321 | 1.5 | 1.811 | 3.6 |
| 8 | 320 | 2.85 | 2.824 | 4.8 |
| 9 | 327 | 2.9 | 2.972 | 5.2 |
| 10 | 327 | 2.4 | 2.566 | 4.4 |
| 11 | 325 | 2.1 | 2.261 | 3.7 |
THE METHOD
From source to answer
Hour-of-day reference summaries with paired observation counts and quantiles.
The Python source exposes this study’s transformations. The complete project download includes shared preparation and evaluation routines.
THE NEXT DECISION
What follows from the finding
Compare traffic and meteorology data before explaining a diurnal pattern.
Where the conclusion stops
The -200 sentinel is treated as missing. Reference instruments have incomplete coverage; comparisons use paired observations. Sensor calibration is retrospective, not a health or regulatory compliance assessment.
Related studies may reuse observations or holdouts. These are historical analyses; associations and backtests do not demonstrate commercial impact. Further model tuning needs new, untouched evaluation data.