Evaluation of normality, validity of mean tests and non-parametric options: contributions to a necessary debate

Authors

DOI:

https://doi.org/10.5902/2179460X67509

Keywords:

ANOVA assumptions, Multiple comparison tests, GLzM

Abstract

Experimentation is an important methodological basis for innovations in the agricultural sector. Nevertheless, several aspects can be improved in the classical statistical analysis used in agricultural research. The objective of this review was to discuss a few conceptual elements and research results about the validity of statistical tests usually applied in experimentation and present some recommendations that can improve the quality of the analyzes commonly used in the scope of fixed models. Useful elements for the discussion of tests of means, assessment of the condition of normality, and non-parametric analysis options are presented. Understanding the statistical hypotheses and Type I error subtypes, for example, can help in better result interpretation and choice of means test. Some doubts about the evaluation of the normality requirement of the residues explored here can also help researchers better use parametric statistical tools. Finally, we present a general decision flowchart and a brief exemplified discussion of some non-parametric analysis options with emphasis on the differences between classical methods and methods based on generalized models.

Downloads

Download data is not yet available.

Author Biographies

André Mundstock Xavier de Carvalho, Universidade Federal de Viçosa

PhD in Soils from the UFV, professor in the postgraduate disciplines “Research Methodology”, in the theme of experimental statistics and “Experimental and Observational Statistics Applied to Agroecology” in multicampus modality. Author of the book “Experimental and Observational Statistics – a new approach” by Editora da UFV (in press) and main author of the basic statistics software “SPEED Stat”.

Éder Matsuo, Universidade Federal de Viçosa

PhD in Genetics and Breeding from UFV, professor in the disciplines of “Introduction to Statistics” and “Notions of Biostatistics”.

Marcelo da Silva Maia, Universidade Federal de Viçosa

Agronomist from UFV, specialist in Plant Protection from UFV – Viçosa campus and currently studying for a master's degree in Agronomy from UFV – Campus Rio Paranaíba.

References

ALVAREZ, V. H.; ALVAREZ, G. A. M. Reflexões sobre a utilização de estatística para pesquisa em ciência do solo. Boletim Informativo da Sociedade Brasileira de Ciência do Solo, v. 38, n. 1, 28-35, 2013.

BANZATTO, D. A.; KRONKA, S. N. Experimentação agrícola. 4. ed. Jaboticabal: Funep, 2006.

BIRD, K.D.; HADZI-PAVLOVIC, D. Controlling the maximum familywise Type I error rate in analyses of multivariate experiments. Psychological Methods, v. 19, n. 2, 265–280, 2014. DOI: https://doi.org/10.1037/a0033806

BORGES, L. C.; FERREIRA, D. F. Power and type I error rates of Scott-Knott, Tukey and Student-Newman-Keuls’s tests under residual normal and non-normal distributions. Revista Matemática e Estatística, v. 21, n. 2, 67-83, 2003.

BOX, G. E. P.; COX, D. R. An Analysis of Transformations. Journal of the Royal Statistical Society. Series B (Methodological), v. 26, n. 2, 211-252, 1964. DOI: https://doi.org/10.1111/j.2517-6161.1964.tb00553.x

CANDIOTI, L. V.; ZAN, M. M.; CAMARA, M. S.; GOICOECHEA, H. C. Experimental design and multiple response optimization - using the desirability function in analytical methods development. Talanta, v. 124, n. 2, 123-138, 2014. DOI: https://doi.org/10.1016/j.talanta.2014.01.034

CARGNELUTTI FILHO, A.; SOUZA, J. M.; PEZZINI, R. V.; NEU, I. M. M.; SILVEIRA, D. L.; PROCEDI, A. Optimal plot size for experiments with black oats and the common vetch. Ciência Rural, v. 50, e20190123, 2020. DOI: https://doi.org/10.1590/0103-8478cr20190123

CARVALHO, A.M.X. Estatística Experimental e Observacional: uma nova abordagem sobre os métodos clássicos. Rio Paranaíba: UFV-CRP, in press, 2023.

CARVALHO, A.M.X.; MENDES, F.Q.; BORGES, P.H.C.; KRAMER, M. A brief review of the classic methods of experimental statistics. Acta Scientiarum - Agronomy, v. 45, e56882, 2023a. DOI: https://doi.org/10.4025/actasciagron.v45i1.56882

CARVALHO, F. J. Modelos lineares generalizados na agronomia: análise de dados binomiais e de contagem, zeros inflacionados e enfoque bayesiano. Tese (Doutorado em Fitotecnia). Universidade Federal de Uberlândia, Uberlândia, 2019.

CARVALHO, A.M.X.; SOUZA, M.R.; MARQUES, T.B.; SOUZA, D.L.; SOUZA, E.F.M. Familywise type I error of ANOVA and ANOVA on ranks in factorial experiments. Ciência Rural, v. 53, n. 7, e20220146, 2023b. DOI: https://doi.org/10.1590/0103-8478cr20220146

CECON, P. R.; SILVA, A. R.; NASCIMENTO, M.; FERREIRA, A. Métodos estatísticos. Viçosa: Editora da UFV, 2012.

CONAGIN, A. Tables for the calculation of the probability to be used in the modified bonferroni's test. Brazilian Journal of Agriculture, v. 76, 71-83, 2001. DOI: https://doi.org/10.37856/bja.v76i1.3987

CONAGIN, A.; PIMENTEL-GOMES, F. Escolha adequada dos testes estatísticos para comparações múltiplas. Brazilian Journal of Agriculture, v. 79, 288-295, 2004. DOI: https://doi.org/10.37856/bja.v79i3.1392

CONAGIN, A.; BARBIN, D.; DEMÉTRIO, C. G. B. Modifications for the Tukey test procedure and evaluation of the power and efficiency of multiple comparison procedures. Scientia Agricola, v. 65, n. 4, 428-432, 2008. DOI: https://doi.org/10.1590/S0103-90162008000400016

CONOVER, W. J. Practical Nonparametric Statistics. 3.. ed. John Wiley & Sons, 1999.

CONOVER, W. J. The rank transformation - an easy and intuitive way to connect many nonparametric methods to their parametric counterparts for seamless teaching introductory statistics courses. WIREs Computational Statistics, v. 4, 432-438, 2012. DOI: https://doi.org/10.1002/wics.1216

CONOVER, W. J.; IMAN, R.L. Rank transformation as a bridge betwen parametric and nonparametric statistics. The American Statistician, v. 35, n. 3, 124-134, 1981. DOI: https://doi.org/10.2307/2683975

CONRADO, T. V.; FERREIRA, D. F.; SCAPIM, C. A.; MALUF, W. R. Adjusting the Scott-Knott cluster analyses for unbalanced designs. Crop Breeding and Applied Biotechnology, v. 17, 1-9, 2017. DOI: https://doi.org/10.1590/1984-70332017v17n1a1

COUTO, M. R. M.; JACOBI, L. F.; MACHADO, G. S. Analise de variância multivariada aplicada a dados com medidas repetidas. Ciência & Natura, Santa Maria, v. 42, e01, 2020. DOI: https://doi.org/10.5902/2179460X39870

DANCEY, C. P.; REIDY, J. G.; ROWE, R. Estatística sem matemática para as ciências da saúde. Porto Alegre: Penso, 2017.

DI RIENZO, J. A.; GUZMÁN, A. W.; CASANOVES, F. A multiple-comparisons method based on the distribution of the root node distance of a binary tree. Journal of Agricultural, Biological, and Environmental Statistics, v. 7, 129-142, 2002. DOI: https://doi.org/10.1198/10857110260141193

DUTCOSKY, S. D. Análise sensorial de alimentos. 4. ed. Curitiba: Champagnat – PUCPress; 2013.

FERREIRA, D. F. SISVAR: A Guide for Its Bootstrap Procedures in Multiple Comparisons. Ciência & Agrotecnologia, v. 38, n. 2, 109-112, 2014. DOI: https://doi.org/10.1590/S1413-70542014000200001

GARCIA-MARQUES, T.; AZEVEDO, M. A inferência estatística múltipla e o problema da inflação do nível de alfa: a ANOVA como exemplo. Psicologia, v. 10, n. 1, 195-220, 1995.

GIRARDI, L. H.; CARGNELUTTI FILHO, A.; STORCK, L. Erro tipo I e poder de cinco testes de comparação múltipla de médias. Revista Brasileira de Biometria, v. 27, n. 1, 23-36, 2009.

GONÇALVES JÚNIOR, F. A.; CORRÊA, T. C. Reflexões sobre a hiperspecialização científica e suas conseqüências para a geografia. Geografia, Ensino & Pesquisa, v. 21, n. 3, 87-96, 2017. DOI: https://doi.org/10.5902/2236499425828

GONÇALVES, B. O.; RAMOS, P. S.; AVELAR, F. G. Teste de Student-Newman-Keuls Bootstrap: proposta, avaliação e aplicação em dados de produtividade de graviola. Revista Brasileira de Biometria, v. 33, 445-470, 2015.

GOTELLI, N. J.; ELLISON, A. M. Princípios de estatística em ecologia. Porto Alegre: Artmed, 2011.

HINES, W. G. S.; O’HARA-HINES, R. Increased power with modified forms of the Levene (Med) test for heterogeneity of variance. Biometrics, v. 56, n. 2, 451-454, 2000. DOI: https://doi.org/10.1111/j.0006-341X.2000.00451.x

KESELMAN, H. J. Per Family or Familywise Type I Error Control: "Eether, Eyether, Neether, Nyther, Let's Call the Whole Thing Off!". Journal of Modern Applied Statistical Methods, v. 14, n. 1, 24-37, 2015. DOI: https://doi.org/10.22237/jmasm/1430453100

KRAMER, M. H.; PAPAROZZI, E. T.; STROUP, W. W. Best Practices for Presenting Statistical Information in a Research Article. HortScience, v. 54, n. 9, 1605-1609, 2019. DOI: https://doi.org/10.21273/HORTSCI13952-19

LITTLE, R. J. In praise of simplicity not mathematistry! Ten simple powerful ideas for the statistical scientist. Journal of the American Statistical Association, v. 108, n. 502, 359-369, 2013. DOI: https://doi.org/10.1080/01621459.2013.787932

LOUREIRO, L. M. J.; GAMEIRO, M. G. H. Interpretação crítica dos resultados estatísticos: para lá da significância estatística. Revista de Enfermagem Referência, v. 3, n. 3, 151-162, 2011. DOI: https://doi.org/10.12707/RIII1009

LÚCIO, A. D.; SARI, B. G. Planning and implementing experiments and analyzing experimental data in vegetable crops: problems and solutions. Horticultura Brasileira, v. 35, 316-327, 2017. DOI: https://doi.org/10.1590/s0102-053620170302

MANLY, B. F. J. Multivariate statistical methods – a primer. 2. ed. London: Chapman & Hall, 1995.

MANN, P. S. Introdução à estatística. 8ª Ed. Rio de Janeiro: LTC, 2015.

MONTGOMERY, D. C. Design and Analysis of Experiments. 9. ed. Wiley, Danvers, 2017.

NUNES, R. P. Métodos para a pesquisa agronômica. Fortaleza: Ed. UFC, 1998.

PATRIOTA, A. G. Uma medida de evidência alternativa para testar hipóteses gerais. Ciência & Natura, Santa Maria, v. 36, 14-22, 2014. DOI: https://doi.org/10.5902/2179460X13195

PERECIN, D.; BARBOSA, J. C. Uma avaliação de seis procedimentos para comparações múltiplas. Revista de Matemática e Estatística, v. 6, n. 1, 95-104, 1988.

PERECIN, D.; CARGNELUTTI FILHO, A. Efeitos por comparações e por experimento em interações de experimentos fatoriais. Ciência e Agrotecnologia, v. 32, n. 1, p. 68-72, 2008. DOI: https://doi.org/10.1590/S1413-70542008000100010

PIEPHO, H. P.; EDMONDSON, R. N. A tutorial on the statistical analysis of factorial experiments with qualitative and quantitative treatment factor levels. Journal of Agronomy and Crop Science, v. 204, n. 5, 429-455, 2018. DOI: https://doi.org/10.1111/jac.12267

PIMENTEL-GOMES, F. Curso de estatística experimental. Piracicaba: FEALQ, 2009.

POSSATTO JUNIOR, O.; BERTAGNA, F. A. B.; PETERLINI, E.; BALERONI, A. G.; ROSSI, R. M.; ZENI NETO, H. Survey of statistical methods applied in articles published in Acta Scientiarum. Agronomy from 1998 to 2016. Acta Scientiarum - Agronomy, v. 41, e42641, 2019. DOI: https://doi.org/10.4025/actasciagron.v41i1.42641

PRIMPAS, I.; TSIRTSIS, G.; KARYDIS, M.; KOKKORIS, G. D. Principal component analysis: Development of a multivariate index for assessing eutrophication according to the European water framework directive. Ecological Indicators, v. 10, 178-183, 2010. DOI: https://doi.org/10.1016/j.ecolind.2009.04.007

SALTER, K. C.; FAWCET, R. F. The art test of interaction: a robust and powerful rank test of interaction in factorial models. Communications in Statistics - Simulation and Computation, v. 22, 137-153, 1993. DOI: https://doi.org/10.1080/03610919308813085

SAWILOWSKY, S. S.; BLAIR, R. C. A more realistic look at the robustness and Type II error properties of the t test to departures from population normality. Psychological Bulletin, v. 111, n. 2, 352–360, 1992. DOI: https://doi.org/10.1037/0033-2909.111.2.352

SCHMIDER, E.; ZIEGLER, M.; DANAY, E.; BEYER, L.; BÜHNER, M. Is it really robust? Reinvestigating the robustness of ANOVA against violations of the normal distribution assumption. Methodology: European Journal of Research Methods for the Behavioral and Social Sciences, v. 6, n. 4, 147–151, 2010. DOI: https://doi.org/10.1027/1614-2241/a000016

SNEDECOR, G. W.; COCHRAN, W. G. Statistical Methods. 8. ed. Iowa: ISU Press. 1989.

SOUSA, C. A. D.; LIRA JUNIOR, M. A.; & FERREIRA, R. L. C. Avaliação de testes estatísticos de comparações múltiplas de médias. Revista Ceres, v. 59, n. 3, 350-354, 2012. DOI: https://doi.org/10.1590/S0034-737X2012000300008

STORCK, L.; GARCIA, D. C.; LOPES, S. J.; ESTEFANEL, V. Experimentação Vegetal. 3. Ed. Santa Maria: Ed UFSM, 2016.

STROUP, W. W. Rethinking the Analysis of Non-Normal Data in Plant and Soil Science. Agronomy Journal, v. 107, n. 2, 811-827, 2015. DOI: https://doi.org/10.2134/agronj2013.0342

TAVARES, L. F.; CARVALHO, A. M. X.; MACHADO, L. G. An evaluation of the use of statistical procedures in soil science. Revista Brasileira de Ciência do Solo, v. 40: e0150246, 2016. DOI: https://doi.org/10.1590/18069657rbcs20150246

TORMAN, V. B. L.; COSTER, R.; RIBOLDI, J. Normalidade de variáveis: métodos de verificação e comparação de alguns testes não-paramétricos por simulação. Revista HCPA, v. 32, n. 2, 227-235. 2012.

WOBBROCK, J. O.; FINDLATER, L.; GERGLE, D.; HIGGINS, J. J. The aligned rank transform for nonparametric factorial analyses using only ANOVA procedures. In J. J. HIGGINS (Ed) Proceedings of the ACM Conference on Human Factors in Computing Systems. Vancouver, ACM Press New York, 2011, p. 143-146. DOI: https://doi.org/10.1145/1978942.1978963

ZHIYUAN, W.; WANG, D.; ZHOU, H.; QI, Z. Assessment of soil heavy metal pollution with principal component analysis and Geoaccumulation Index. Procedia Environmental Sciences, v. 10, 1946–1952, 2011. DOI: https://doi.org/10.1016/j.proenv.2011.09.305

ZIMMERMANN, F. J. P. Estatística Aplicada à Pesquisa Agrícola. Santo Antônio de Goiás: Embrapa Arroz e Feijão, 2004.

ZIMMERMAN, D. W. A note on consistency of non‐parametric rank tests and related rank transformations. British Journal of Mathematical and Statistical Psychology, v. 65, n. 1, 122-144, 2012. DOI: https://doi.org/10.1111/j.2044-8317.2011.02017.x

Published

2023-06-22

How to Cite

Carvalho, A. M. X. de, Matsuo, Éder, & Maia, M. da S. (2023). Evaluation of normality, validity of mean tests and non-parametric options: contributions to a necessary debate. Ciência E Natura, 45, e9. https://doi.org/10.5902/2179460X67509