Comprehensive study of tests for normality and symmetry: extending the Spiegelhalter test

Farrell, Patrick J.; Rogers‐Stewart, Katrina

doi:10.1080/10629360500109023

Cited by 91 publications

(66 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Also, according to the test performed in Engmann & Darling (2011) who compared the AD test with the KS test, the former also requires smaller sample sizes achieving the same prediction power as the latter, concluding that "the AD test is more powerful than the KS test in detecting any kind of difference between samples from two different distributions". The third frequently used test (also nonparametric and distribution-free) is the CvM test (Anderson 1962) 14 , but it gives less weight to the tails of the distribution (Farrell & Rogers-Stewart 2006). Nevertheless, this test was also carried out and is in good agreement with the other two tests.…”

Section: Statistical Testsmentioning

confidence: 48%

Full stellar kinematical profiles of central parts of nearby galaxies

Vudragović

Samurovic

Jovanović

2016

A&A

View full text Add to dashboard Cite

Context. We present the largest catalog of detailed stellar kinematics of the central parts of nearby galaxies, which includes higher moments of the line-of-sight velocity distribution (LOSVD) function represented by the Gauss-Hermite series. The kinematics is measured on a sample of galaxies selected from the Arecibo Legacy Fast ALFA (Alfalfa) survey using spectroscopy from the Sloan Digital Sky Survey (SDSS DR7). Aims. The SDSS DR7 offers measurements of the LOSVD based on the assumption of a pure Gaussian shape of the broadening function caused by the combination of rotational and random motion of the stars in galaxies. We discuss the consequences of this oversimplification since the velocity dispersion, one of the measured quantities, often serves as the proxy to important modeling parameters such as the black-hole mass and the virial mass of galaxies. Methods. The publicly available pPXF code is used to calculate the full kinematical profile for the sample galaxies including higher moments of their LOSVD. Both observed and synthetic stellar libraries were used and the related template mismatch problem is discussed. Results. For the whole sample of 2180 nearby galaxies reflecting morphological distribution characteristic for the local Universe, we successfully recovered stellar kinematics of their central parts, including higher order moments of the LOSVD function, for signal-to-noise above 50. Conclusions. We show the consequences of the oversimplification of the LOSVD function with Gaussian function on the velocity dispersion for the empirical and the synthetic stellar library. For the empirical stellar library, this approximation leads to an increase in the virial mass of 13% on average, while for the synthetic library the effect is weaker, with an increase of 9% on average. Systematic erroneous estimates of the velocity dispersion comes from the use of the synthetic stellar library instead of the empirical one and is much larger than the value imposed by the use of the Gaussian function. Only after a careful analysis of the template mismatch problem does one need to address the issue of the deviation of the LOSVD from the Gaussian function. We also show that the kurtotic parameter describing symmetrical departures from the Gaussian seems to increase along the continuous morphological sequence from late-to early-type galaxies.

show abstract

Section: Statistical Testsmentioning

confidence: 48%

Full stellar kinematical profiles of central parts of nearby galaxies

Vudragović

Samurovic

Jovanović

2016

A&A

View full text Add to dashboard Cite

show abstract

“…Some of these tests are constructed to be applied under certain conditions or assumptions. Extensive studies on the Type I error rate and power of these normality tests have been discussed in [1][2][3][4][5][6][7][8][9]. Most of these comparisons were carried out using selected normality tests and selected small sample sizes.…”

Section: Introductionmentioning

confidence: 99%

Comparisons of various types of normality tests

Wah

Sim

2011

Journal of Statistical Computation and Simulation

637

321

View full text Add to dashboard Cite

Normality tests can be classified into tests based on chi-squared, moments, empirical distribution, spacings, regression and correlation and other special tests. This paper studies and compares the power of eight selected normality tests: the Shapiro-Wilk test, the Kolmogorov-Smirnov test, the Lilliefors test, the Cramer-von Mises test, the Anderson-Darling test, the D'Agostino-Pearson test, the Jarque-Bera test and chi-squared test. Power comparisons of these eight tests were obtained via the Monte Carlo simulation of sample data generated from alternative distributions that follow symmetric short-tailed, symmetric long-tailed and asymmetric distributions. Our simulation results show that for symmetric short-tailed distributions, D'Agostino and Shapiro-Wilk tests have better power. For symmetric long-tailed distributions, the power of Jarque-Bera and D'Agostino tests is quite comparable with the Shapiro-Wilk test. As for asymmetric distributions, the Shapiro-Wilk test is the most powerful test followed by the Anderson-Darling test.

show abstract

“…Figura 2 -Sequência de desenvolvimento para análise O teste de Shapiro-Wilk averigua os desvios acerca de uma população de dados e o resultado do teste aponta se os dados apresentam ou não distribuição normal (FARREL; STEWART, 2006). Se a hipótese nula de que os dados provêm de uma população normal for rejeitada, tem-se que os dados futuros desta série estarão fora dos limites já preestabelecidos na série.…”

Section: Descrição Do Modelounclassified

Planejamento da safra de soja no Oeste do Paraná

Arthus

Camatti

Bortoletto

et al. 2017

P&P

View full text Add to dashboard Cite

Planejamento da safra de soja no Oeste do Paraná RESUMOA soja é o grão mais produzido no Brasil e tem dado ao país o título de maior exportador desta commodity. A pouca quantidade de produto disponível internamente e a alta do dólar tem elevado o seu preço a valores recorde, com desdobramentos na área de cultivo, que vem aumentando com o passar dos anos. Este artigo tem o objetivo de aplicar modelos de previsão de demanda para o cenário de rendimento de soja no Oeste do Paraná e discutir os seus resultados quanto aos erros em relação aos valores reais. Dados referentes ao rendimento do grão por hectare no Oeste do Paraná, entre os anos de 1980 e 2014, foram coletados e submetidos a quatro testes de hipóteses para determinar os modelos de previsão mais adequados para comparação. Os resultados obtidos validaram a modelagem, que pode servir de base para o planejamento dos produtores rurais em relação às estimativas de rendimento de soja no curto prazo.Palavras-chave: Soja, previsão de demanda, séries temporais. 81 ABSTRACTSoybean is the most produced grain in Brazil and has given the country the title of largest exporter of this commodity. The small amount of internally available product and the Dollar high exchange rates have raised its the price to record levels, with extensions in the harvesting area, which has been increasing over the years. This article aims to apply forecasting methods for soybean yield scenario in western Parana and to discuss the results of the errors against the original values. Data on the grain hectare yield in the west of Parana were collected, between the years of 1980 and 2014, and four tests of hypotheses were applied to point out the most appropriate forecasting methods for comparison. The results validated the model, which may become the basis for the farmers' crop planning regarding soybean yield in the short-term period.

show abstract

Comprehensive study of tests for normality and symmetry: extending the Spiegelhalter test

Cited by 91 publications

References 16 publications

Full stellar kinematical profiles of central parts of nearby galaxies

Full stellar kinematical profiles of central parts of nearby galaxies

Comparisons of various types of normality tests

Planejamento da safra de soja no Oeste do Paraná

Contact Info

Product

Resources

About