Sampling uncertainty
The uncertainty (precision component) due to sampling can be estimated according to Nordtest 604 by taking several duplicate samples. The approach uses repeated sampling and analysis, under various conditions, to quantify the effects caused by factors such as the heterogeneity of the analyte in the sampling target. The approach also includes variations in the application of the sampling protocols.
The experimental design shown in Figure below is repeated several times
The results are evaluated by ANOVA using the Excel add-in RANOVA from RSC in UK. An example of data input and the output from the software is shown below. The RANOVA can be downloaded from RSC here.
Input data from 8 duplicate samplings performed
Output from RANOVA showing a sampling uncertainty (U) of ca 30 %