Alternative to Tukey test

In order to search for an ideal test for multiple comparison procedures, this study aimed to develop two tests, similar to the Tukey and SNK tests, based on the distribution of the externally studentized amplitude. The test names are Tukey Midrange (TM) and SNK Midrange (SNKM). The tests were evaluated based on the experimentwise error rate and power, using Monte Carlo simulation. The results showed that the TM test could be an alternative to the Tukey test, since it presented superior performances in some simulated scenarios. On the other hand, the SNKM test performed less than the SNK test.

Index terms:
Type I error rate; simulation; range; midrange; midrangeMCP package.

Authorship

Ben Dêivide de Oliveira Batista ^**Corresponding author: ben.deivide@ufsj.edu.br

Universidade Federal de São João del-Rei/UFSJ, Departamento de Estatística, Física e Matemática, São João del-Rei, MG, BrasilUniversidade Federal de São João del-Rei/UFSJBrazilSão João del-Rei, MG, BrazilUniversidade Federal de São João del-Rei/UFSJ, Departamento de Estatística, Física e Matemática, São João del-Rei, MG, Brasil

http://orcid.org/0000-0001-7019-8794

Daniel Furtado Ferreira

Universidade Federal de Lavras/UFLA, Departamento de Estatística/DES, Lavras, MG, BrasilUniversidade Federal de Lavras/UFLABrazilLavras, MG, BrazilUniversidade Federal de Lavras/UFLA, Departamento de Estatística/DES, Lavras, MG, Brasil

http://orcid.org/0000-0002-4371-5239

^*Corresponding author: ben.deivide@ufsj.edu.br

SCIMAGO INSTITUTIONS RANKINGS

Figures | Tables | Formulas

Figures (4)
Tables (1)
Formulas (22)

Replicates	Treatments	Tests
Replicates	Treatments	Tukey	SNK	TM	SNKM
4	5	5.240	5.240	3.680^--	3.680^--
	10	5.660	5.660	4.720	4.720
	20	5.080	5.080	5.060	5.060
	30	4.960	4.960	4.340	4.340
	40	4.980	4.980	3.980^--	3.980^--
	100	4.680	4.680	3.340^--	3.340^--
10	5	4.940	4.940	3.860^--	3.860^--
	10	5.060	5.060	4.820	4.820
	20	5.240	5.240	5.140	5.140
	30	4.840	4.840	4.160^--	4.160^--
	40	4.620	4.620	4.020^--	4.020^--
	100	5.140	5.140	3.700^--	3.700^--
20	5	4.880	4.880	2.540^--	2.540^--
	10	5.060	5.060	4.440	4.440
	20	4.940	4.940	4.760	4.760
	30	4.960	4.960	4.120^--	4.120^--
	40	5.020	5.020	4.180^--	4.180^--
	100	4.820	4.820	3.720^--	3.720^--