A field experiment was implemented to demonstrate the feasibility of quantifying the effect of future data on uncertainty reduction under real circumstances in a sequential way.
Lacking actual data on uncertainty in the parameter values, we could not express uncertainty in terms of statistical distributions, so we chose to use 1-way sensitivity analyses.
Parameters from clinical trial data were varied within the 95%% CIs and parameters for which data on uncertainty were not available were varied by ± 30%%.
Info-gap models of uncertainty are particularly useful when data on the uncertainties are quite limited.
The uncertainty of volumetric operations (volumetric flasks, pipettes) was calculated by using manufacturer data on calibration uncertainty (from certificates), the uncertainty associated with the use of glassware at a temperature different from that of calibration, and the repeatability of volumetric deliveries.
Data on the uncertainty contributed by sample collection, sample preservation/storage, and laboratory analysis in measured E. coli concentrations were compiled and analyzed, and differences in sampling method and data quality scenarios were compared.
We also thank Therese Sundell (Arbeids-og velferdsdirektoratet) for information on sick leave policy and Lars Rønningen at the Directorate of Health for data on the uncertainty of DRG costs.
Additionally, data on the uncertainty of the RR functions after 150 g/day were in most cases not available, and, thus, it was impossible to calculate the 95% confidence intervals for the burden of disease attributable to alcohol consumption.
However, the variance across replicate measurements often differs significantly between the biological samples and this data on measurement uncertainty is not retained by the summarization and consequently not considered in following statistical analyses.
The determining effect of the data lineage on uncertainty models will be described detail in the section of Construction of Uncertainty Models for Geospatial Utility Data.
