On quantile residuals in beta regression

Pereira, Gustavo H. A.

doi:10.1080/03610918.2017.1381740

Cited by 31 publications

(23 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additionally, some residual diagnostics are provided in the Appendix using the quantile residuals (Pereira, 2019). These are showing (Figure ) that the model is valid.…”

Section: Resultsmentioning

confidence: 99%

Quantitative estimation of water status in field‐grown wheat using beta mixed regression modelling based on fast chlorophyll fluorescence transients: A method for drought tolerance estimation

Rybka

Maldonado-Rodríguez

Stefański³

et al. 2021

J Agronomy Crop Science

View full text Add to dashboard Cite

Wheat (Triticum aestivum L.) along with rice and maize belongs to the staple crops essential for feeding the world's population. It is cultivated on fields of a total area bigger than 220 million hectares (about 1.5% of earth land area) providing about 19% of food calories, the same as rice and fourfold more than maize. It has been estimatedthat the global wheat yield should increase by 2% yearly to satisfy food needs (FAO, 2014). Its production is strongly dependent on climatic conditions (Ahmadi & Baker, 2001;Groisman et al., 2005) and needs as much as 500-600 litres of water for 1 kg of crop dry matter. In the case of Poland (Central Europe), the optimal sum of

show abstract

“…Additionally, some residual diagnostics are provided in the Appendix using the quantile residuals (Pereira, 2019). These are showing (Figure ) that the model is valid.…”

Section: Resultsmentioning

confidence: 99%

Quantitative estimation of water status in field‐grown wheat using beta mixed regression modelling based on fast chlorophyll fluorescence transients: A method for drought tolerance estimation

Rybka

Maldonado-Rodríguez

Stefański³

et al. 2021

J Agronomy Crop Science

View full text Add to dashboard Cite

show abstract

“…In the case of a non-normal regression model for modeling a highly skewed and continuous outcome variable, Scudilio and Pereira (2020) [14] proposed an adjusted quantile residual to diagnose inverse Gaussian or Gamma regression models, which was shown to be a better choice to perform diagnostic analysis compared to traditional residuals. Pereira (2019) [12] and Arenas (2019) [13] investigated the properties of the quantile residual in the beta regression and generalized Johnson S B regression models, respectively. Their results showed that the quantile residual is well approximated by a standard normal distribution.…”

Section: Randomized Quantile Residual Definition Of Randomized Quantimentioning

confidence: 99%

“…For modeling non-normal and continuous outcome data, several studies have investigated the properties of quantile residuals for checking the model fit. For example, Pereira (2019) [12] investigated the properties of the quantile residual in the beta regression model and demonstrated that the distribution of the quantile residual is better approximated by the standard normal distribution than that of the other residuals in most scenarios. Lemonte and Moreno-Arenas (2019) [13] proposed the normalized quantile residual to check the adequacy of the generalized Johnson S B (GJS) regression model, which were shown as a better choice to identify departures from the model assumptions and to assess the overall goodness-of-fit than the deviance residual.…”

Section: Introductionmentioning

confidence: 99%

A comparison of residual diagnosis tools for diagnosing regression models for count data

Feng

Sadeghpour

2020

BMC Med Res Methodol

View full text Add to dashboard Cite

Background: Examining residuals is a crucial step in statistical analysis to identify the discrepancies between models and data, and assess the overall model goodness-of-fit. In diagnosing normal linear regression models, both Pearson and deviance residuals are often used, which are equivalently and approximately standard normally distributed when the model fits the data adequately. However, when the response vari*able is discrete, these residuals are distributed far from normality and have nearly parallel curves according to the distinct discrete response values, imposing great challenges for visual inspection. Methods: Randomized quantile residuals (RQRs) were proposed in the literature by Dunn and Smyth (1996) to circumvent the problems in traditional residuals. However, this approach has not gained popularity partly due to the lack of investigation of its performance for count regression including zero-inflated models through simulation studies. Therefore, we assessed the normality of the RQRs and compared their performance with traditional residuals for diagnosing count regression models through a series of simulation studies. A real data analysis in health care utilization study for modeling the number of repeated emergency department visits was also presented. Results: Our results of the simulation studies demonstrated that RQRs have low type I error and great statistical power in comparisons to other residuals for detecting many forms of model misspecification for count regression models (non-linearity in covariate effect, over-dispersion, and zero inflation). Our real data analysis also showed that RQRs are effective in detecting misspecified distributional assumptions for count regression models. Conclusions: Our results for evaluating RQRs in comparison with traditional residuals provide further evidence on its advantages for diagnosing count regression models.

show abstract

“…Por se tratar de um método informal para verificar a distribuição da variável resposta, uma grande dificuldade dos gráficos de probabilidade normal e meio normal está em avaliar até que ponto certas irregularidades no padrão linear dos resíduos podem ser consideradas naturais. Além disso, mesmo que o modelo seja correto, os resíduos não são independentes e nem possuem distribuição exatamente normal padrão em amostras finitas (Pereira, 2017).…”

Section: Gráficos De Probabilidadeunclassified

Contribuições sobre o envelope simulado na análise de diagnóstico em modelos de regressão

Fernandes¹

View full text Add to dashboard Cite

Agradeço primeiramente a Deus, pelo dom da vida. Agradeço aos meus familiares, em especial, meus pais, Hélio e Rose, e meus avós, Adão e Dirce, por todo o apoio e incentivo. Agradeço ao meu orientador, Gustavo, pela atenção dedicada ao longo desses anos e por todo o aprendizado. Agradeço aos meus grandes amigos, Dani, Ana Carolina e Paulo, por sempre estarem presentes e torcerem por mim. Por fim, agradeço também aos meus amigos de mestrado, Lucas Cavalaro, Milene, Gabi, Polo, Luiz, Fabi, Juliana, Alex e Lucas Lopes, pelo companheirismo e momentos de estudo. Esta experiência foi incrível! O presente trabalho foi realizado com apoio da Coordenação de Aperfeiçoamento de Pessoal de Nível Superior-Brasil (CAPES/DS-Demanda Social). Além disso, esta pesquisa foi desenvolvida com o auxílio dos recursos de HPC disponibilizados pela Superintendência de Tecnologia da Informação da Universidade de São Paulo. i RESUMO Fernandes, V. V. Contribuições sobre o envelope simulado na análise de diagnóstico em modelos de regressão. 2019. 66 p. Dissertação (Mestrado em Estatística

show abstract

On quantile residuals in beta regression

Cited by 31 publications

References 22 publications

Quantitative estimation of water status in field‐grown wheat using beta mixed regression modelling based on fast chlorophyll fluorescence transients: A method for drought tolerance estimation

Quantitative estimation of water status in field‐grown wheat using beta mixed regression modelling based on fast chlorophyll fluorescence transients: A method for drought tolerance estimation

A comparison of residual diagnosis tools for diagnosing regression models for count data

Contribuições sobre o envelope simulado na análise de diagnóstico em modelos de regressão

Contact Info

Product

Resources

About