Outlier Test Analysis Object (Statistics Option)

09.03.2021

You can use this analysis object to test a sample originating from a normally distributed population for outliers.

The analysis object offers you two different tests:

Description

Procedure

David-Hartley-Pearson Test

The test checks whether the highest or lowest value in the sample is an outlier or not, depending on which value is furthest from the mean value. The sample size must be between 3 and 1000 values.

Grubbs-Beck Test

The test checks whether the highest and/or lowest value in the sample is an outlier or not. The sample size must be between 3 and 147 values.

Depending on the test procedure, the following results are possible:

a) David-Hartley-Pearson Test

Value

Interpretation

0

The hypothesis was rejected. The lowest or highest value is, with the error probability specified, an outlier.

1

The hypothesis was accepted. The lowest and highest values are, with the error probability specified, not outliers.

2

No result could be determined, since the sample size is outside the valid range.

b) Grubbs-Beck Test

Value

Interpretation

0

The lowest and highest values are, with the error probability specified, outliers.

1

The lowest value is, with the error probability specified, an outlier.

2

The highest value is, with the error probability specified, an outlier.

3

With the probability of error specified, there are no outliers in the sample.

4

No result could be determined, since the sample size is outside the valid range.

References

Hartung, Joachim (1993). Statistik (Statistics), 9th Edition. Oldenbourg Verlag GmbH, Munich. ISBN 3-486-22055-1. Starting on page 344.

FPScript Functions Used

DavidHartleyPearsonTest

GrubbsBeckTest

See Also

Statistics Option

Analysis Objects

Share article or send as email:

You might be interested in these articles