ST_strayarea

strayval = ST_strayarea(v, p)

Parameters

v:

vector of numerical values

p:

statistical confidence level (%) as a string or the level of significance (α) as a decimal value, "95%", "99%", "99.9%" or 0.05, 0.01, 0.001 resp (see examples).

strayval:

historical stray area (Streubereich), calculated as s*t.

Description

"ST_strayarea" calculates the historical stray area (German: Streubereich) according to Kaiser/Gottschalk as

T: stray area of values; s: sample standard deviation; t: student factor (dependent on statistical confidence level P% and degree of freedom f=n-1 with n: number of values)

It defines the range around the mean within which the values may vary at a given significance level.

This quantity must not be confused with a modern prediction interval for a future individual observation, which is defined differently.

E.g. if strayval = 1.4 at p = 95% and mean(v) = 10.0, the historical Kaiser/Gottschalk stray area is reported as approximately 10.0 +/- 1.4.

Examples

See also

• ST_trustarea — Determines the range of dispersion of the mean.
• ST_studentfactor — Determine the student factor
• ST_grubbs — Classical non-iterative Grubbs test for a single outlier
• ST_esd — Generalized Extreme Studentized Deviate test according to Rosner
• ST_outlier — Basic outlier tests with standard deviation or quantile
• ST_deandixon — Basic Dean-Dixon outlier test
• ST_pearsonhartley — Pearson-Hartley outlier test
• ST_shapirowilk — Shapiro-Wilk test of normality
• ST_ivplot — Individual value plot for one or more data sets.

Authors

• Hani A. Ibrahim - hani.ibrahim@gmx.de

Bibliography

R. Kaiser, G. Gottschalk; "Elementare Tests zur Beurteilung von Meßdaten", BI Hochschultaschenbücher, Bd. 774, Mannheim 1972.