Corrigendum to Critical values for 22 discordancy test variants for outliers in normal samples up to sizes 100, and applications in science and engineering [Rev. Mex. Cienc. Geol., 23 (2006), 302–319]ª
Surendra P. Verma* and Alfredo Quiroz–Ruiz
Centro de Investigación en Energía, Universidad Nacional Autónoma de México, Priv. Xochicalco s/no., Col Centro, Apartado Postal 34, 62580 Temixco, Morelos, Mexico. * spv@cie.unam.mx
We had not clarified that in the above mentioned paper as well as two later papers [Rev. Mex. Cienc. Geol. 25 (2008): 82–96 and 369–381], the critical values reported for test N14 (skewness or third moment test) were of the one–sided type. They were simulated from the actual value of the statistic TN14 and repetitions of 100,000 in 2006 or 1,000,000 in 2008.
]]> Using the absolute value of the statistic TN14, we have recently simulated more precise and accurate two–sided critical values (2,000,000 repetitions) for confidence levels of 70%, 80%, 90%, 95%, 98%, 99%, and 99.5% (or equivalently, significance level a of 0.30, 0.20, 0.10, 0.05, 0.02, 0.01, and 0.005, as well as for sample sizes of 5(1)100(5)200(10)500(20)1000(50)1500(100)2000(500)5000(1000)10000(5000)30000.These two–sided critical values are available along with their individual error estimates as txt or Excel files, to anyone interested on request to any of the authors.
ª Artículo original http://satori.geociencias.unam.mx/23–3/(5)Verma.pdf
]]>