Non-Parametric Tolerance Limit

 

See Also:

Parametric Tolerance Limit

Poisson Tolerance Limit

Non-Parametric Prediction Limit

 

Description:

 

The non-parametric tolerance limit is recommended in the 1992 guidance for samples sets where the assumptions of normality or transformed-normality can not be justified or when a significant portion ( > 25%) of the samples are non-detects. A very basic test, the non-parametric tolerance limit simply compares each individual down-gradient concentration to the maximum concentration in background samples. The only significant calculation is to determine the coverage or level of significance of the test. Both a minimum level of coverage and an average level of coverage are provided. The greater the number of background samples, the greater the level of coverage.

 

 

Use:

 

For comparison of individual compliance well samples to pooled background data where data do not follow a normal or transformed-normal distribution, and/or there is an abundance of non-detects.

 

The test is performed on all compliance wells for the specified parameter.

 

 

Remarks:

 

This method will tend to have a high rate of false negatives unless there is a sufficient number of samples available from background wells. As stated in the 1992 guidance document, at least 19 background samples are required for 95% coverage. Fewer background samples will result in a lower rate of coverage and a higher incidence of false negatives.

 

This method should give the exact same results for both original data or log data.