p < 0,05, ¿Criterio mágico para resolver cualquier problema o leyenda urbana? / p <0.05, A magic criterion to solve any problem or an urban legend? / p <0,05, Critério mágico para resolver qualquer problema ou lenda urbana?

Las Pruebas de Hipótesis son el procedimiento de análisis más conocido por los investigadores y utilizado en las revistas científicaspero, a su vez, ellas han sido fuertemente criticadas, su uso ha sido cuestionado y restringido en algunos casos por las inconsistenciasobservadas en su aplicación. Este problema se analiza, en este artículo, tomando como punto de partida los Fundamentos de laMetodología Estadística y los diferentes enfoques que históricamente se han desarrollado para abordar el problema del análisis delas Hipótesis Estadísticas. Resaltándose un punto poco conocido por algunos: el carácter aleatorio de los valores P. Se presentanlos fundamentos de las soluciones de Fisher, Neyman-Pearson y Bayesiana y a partir de ellas se identifican las inconsistenciasdel procedimiento de conducta que indica identificar un valor P, compararlo con el valor del error de tipo I –que usualmente esconsiderado como 0,05- y a partir de ahí decidir las conclusiones del análisis. Adicionalmente se identifican recomendaciones sobrecómo proceder en un problema, así como los retos a enfrentar, en lo docente y en lo metodológico, para analizar correctamente losdatos y determinar la validez de las hipótesis de interés...

Hypothesis testing is a well-known procedure for data analysiswidely used in scientific papers but, at the same time, strongly criticized and its use questioned and restricted in some cases due toinconsistencies observed from their application. This issue is analyzed in this paper on the basis of the fundamentals of the statisticalmethodology and the different approaches that have been historically developed to solve the problem of statistical hypothesis analysishighlighting a not well known point: the P value is a random variable. The fundamentals of Fisher´s, Neyman-Pearson´s and Bayesian´ssolutions are analyzed and based on them, the inconsistency of the commonly used procedure of determining a p value, compare it toa type I error value (usually 0.05) and get a conclusion is discussed and, on their basis, inconsistencies of the data analysis procedureare identified, procedure consisting in the identification of a P value, the comparison of the P-value with a type-I error value –whichis usually considered to be 0.05– and upon this the decision on the conclusions of the analysis. Additionally, recommendations on thebest way to proceed when solving a problem are presented, as well as the methodological and teaching challenges to be faced whenanalyzing correctly the data and determining the validity of the hypotheses...

Os testes de hipóteses são o método de análisemelhor conhecido por pesquisadores e utilizado em revistas científicas; mas por sua vez, têm sido fortemente criticados, seu uso temsido questionado e, em alguns casos restritos pelas inconsistências observadas na sua aplicação. Esse problema é discutido neste artigo,tendo como ponto de partida os Fundamentos da Metodologia Estatística e as diferentes abordagens que historicamente têm sidodesenvolvidas para resolver o problema da analise das Hipóteses Estatísticas. Destacando-se um ponto pouco conhecido por alguns: ocaráter aleatório do p-valor. Apresentam-se os fundamentos das soluções de Fisher, Neyman-Pearson e Bayesiana e delas são identificadasas inconsistências do procedimento de conduta que orienta identificar um p-valor para compará-lo com o valor do erro de tipo I, queé geralmente considerado como 0,05 - e, posteriormente, decidir as conclusões da análise. Além disso, se identificam recomendaçõessobre como proceder num problema, e os desafios a serem enfrentados no ensino e no metodológico, para analisar corretamente osdados e determinar a validade das hipóteses de interesse...

A straightforward multiallelic significance test for the Hardy-Weinberg equilibrium law

Much forensic inference based upon DNA evidence is made assuming Hardy-Weinberg Equilibrium (HWE) for the genetic loci being used. Several statistical tests to detect and measure deviation from HWE have been devised, and their limitations become more obvious when testing for deviation within multiallelic DNA loci. The most popular methods-Chi-square and Likelihood-ratio tests-are based on asymptotic results and cannot guarantee a good performance in the presence of low frequency genotypes. Since the parameter space dimension increases at a quadratic rate on the number of alleles, some authors suggest applying sequential methods, where the multiallelic case is reformulated as a sequence of "biallelic" tests. However, in this approach it is not obvious how to assess the general evidence of the original hypothesis; nor is it clear how to establish the significance level for its acceptance/rejection. In this work, we introduce a straightforward method for the multiallelic HWE test, which overcomes the aforementioned issues of sequential methods. The core theory for the proposed method is given by the Full Bayesian Significance Test (FBST), an intuitive Bayesian approach which does not assign positive probabilities to zero measure sets when testing sharp hypotheses. We compare FBST performance to Chi-square, Likelihood-ratio and Markov chain tests, in three numerical experiments. The results suggest that FBST is a robust and high performance method for the HWE test, even in the presence of several alleles and small sample sizes.