GPro Talks - Comparing Data to Standards Using Statistics: Why and How
Many regulations compare a mean or percentile of observed data to a standard or guideline. If the mean exceeds the standard, the soil/water being sampled is out of compliance. If more than an allowed percentage (say 10%) of observations exceed the standard, the soil/water is out of compliance. Such comparisons lead to elevated false positives, false statements of non-compliance. The statistical approach compares a confidence limit on the mean or percentile rather than the parameter itself to the standard value. Why should a confidence limit be employed? What are the drawbacks to using the observed mean or percentile? After answering these questions, the method for comparing a confidence limit to a standard is illustrated.
Comparing Data to Standards Using Statistics: Why and How