Differences
This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision Last revision Both sides next revision | ||
|
kfv_._note [2016/06/30 01:28] nikolaj |
kfv_._note [2016/09/09 09:30] nikolaj |
||
|---|---|---|---|
| Line 20: | Line 20: | ||
| * $p^\mathrm{eff}(t) := \dfrac{ n_\mathrm{prev}(t) }{ n^\mathrm{max}(t) }$ ... (unknown) effective potential of the system. | * $p^\mathrm{eff}(t) := \dfrac{ n_\mathrm{prev}(t) }{ n^\mathrm{max}(t) }$ ... (unknown) effective potential of the system. | ||
| + | |||
| + | == note: Risk == | ||
| + | [Analysis Method for Accident and Injury Risk Studies]: | ||
| + | |||
| + | We know the number of accidents $n$ (terminated trips), but have not much information about the number of all car trips $t>>n$ taken (trips at risk). | ||
| + | |||
| + | The ratio $R=n/t$ is called accident "risk" and the potentials $p$ thus also quantifies ratios of risks. | ||
| + | |||
| + | Similar to potentials, accident risks may be partitioned according to causes. | ||
| + | |||
| + | In any case, as long as we don't have access to t, we can't quantify risks as such. | ||
| + | |||
| + | Neither do we have information of trip length, in time or space, at accidents ("densities"). | ||
| + | |||
| + | The ratio $n/(t-n)$, i.e. accidents vs. non-accidents of all trips, is called "odds". | ||
| + | |||
| + | Other ratios considered are e.g. n over population or n over cars in use. Those are all called "rate" of some form. | ||
| === Mitigation and Worsening === | === Mitigation and Worsening === | ||
| Line 252: | Line 269: | ||
| https://en.wikipedia.org/wiki/Ornstein%E2%80%93Uhlenbeck_process) | https://en.wikipedia.org/wiki/Ornstein%E2%80%93Uhlenbeck_process) | ||
| - | === Example: Prediction for the ESP system === | + | === Prediction for the ESP system === |
| + | ** Example ** | ||
| Here we have data for the **ESP** system, with a distribution of $x^{**}=0.68$ in the year 2014 and thus a slope $A\approx 0.0326$ according to the formula above. | Here we have data for the **ESP** system, with a distribution of $x^{**}=0.68$ in the year 2014 and thus a slope $A\approx 0.0326$ according to the formula above. | ||
