QuicksilverHelp
This page is considered to be a reference for key functionality of the Quicksilver application. As enhancements are brought forth to Quicksilver, any necessary reference information will be updated on this page.
Links to original Quicksilver use cases:
Modified EARS C2 algorithm used to determine if clinical effect counts are statistically significant where the expected value is based on a 28-day moving average:
- As with C2, the two days immediately preceding the index day (day for which an expected value is calculated) are skipped.
- The residual is the observed count minus the expected count.
- The standard deviation is calculated by the usual formula.
- If the standard deviation is less than 1.0, then 1.0 is used as the standard deviation.
- The C2 statistic equals the residual divided by the standard deviation.
We use an empiric method to find reasonable cutoff values for C2. Between 3-6 standard deviations above the mean are usually considered statistically significant. Currently any value that is > 4 SD units from the mean is flagged within Quicksilver as statistically significant. The data points themselves are highlighted in red when presented on the time series graph.
The Google Maps API is used to display all national, state, ZIP-3, and ZIP-5 geography within Quicksilver. Here is the link to the Google code page for the API: http://code.google.com/apis/maps/
All time series charting is handled by a Javascript plotting library for JQuery known as FLOT. Here is the link to the Google project page for FLOT: http://code.google.com/p/flot/