Robust Wild Bootstrap for Stabilizing the Variance of Parameter Estimates in Heteroscedastic Regression Models in the Presence of Outliers

Rana, Sohel; Midi, Habshah; Imon, A. H. M. Rahmatullah

doi:10.1155/2012/730328

Cited by 20 publications

(23 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For detailed explanations we refer to [23]. Similar Wild-Bootstrap methods have been used in several inference methods and disciplines, see, e.g., [31,32,33,34,35,36,37,38,39,40,41].…”

mentioning

confidence: 99%

The Behrens–Fisher problem with covariates and baseline adjustments

Cao

Pauly

Konietschke

2019

Metrika

View full text Add to dashboard Cite

The Welch-Satterthwaite t-test is one of the most prominent and often used statistical inference method in applications. The method is, however, not flexible with respect to adjustments for baseline values or other covariates, which may impact the response variable. Existing analysis of covariance methods are typically based on the assumption of equal variances across the groups. This assumption is hard to justify in real data applications and the methods tend to not control the type-1 error rate satisfactorily under variance heteroscedasticity. In the present paper, we tackle this problem and develop unbiased variance estimators of group specific variances, and especially of the variance of the estimated adjusted treatment effect in a general analysis of covariance model. These results are used to generalize the Welch-Satterthwaite t-test to covariates adjustments. Extensive simulation studies show that the method accurately controls the nominal type-1 error rate, even for very small sample sizes, moderately skewed distributions and under variance heteroscedasticity. A real data set motivates and illustrates the application of the proposed methods.

show abstract

“…For detailed explanations we refer to [23]. Similar Wild-Bootstrap methods have been used in several inference methods and disciplines, see, e.g., [31,32,33,34,35,36,37,38,39,40,41].…”

mentioning

confidence: 99%

The Behrens–Fisher problem with covariates and baseline adjustments

Cao

Pauly

Konietschke

2019

Metrika

View full text Add to dashboard Cite

show abstract

“…Mediante simulaciones Bootstrap (Rana, Midi e Imon, [26]), se obtienen los intervalos de confianza para el vector de parámetros local dados en la Tabla (6):…”

Section: Distribuciones a Priori Continuasunclassified

Diseños Dπ-óptimos para modelos no lineales heteroscedásticos: un estudio de robustez

Patiño-Bustamante

López-Ríos

2020

ing.cienc

View full text Add to dashboard Cite

Los diseños óptimos son utilizados para determinar las mejores condiciones donde se debe realizar un experimento para obtener ciertas propiedades estadísticas. En los modelos no lineales heteroscedásticos donde la varianza es una función de la media, el criterio de optimalidad depende de la elección de un valor local para los parámetros del modelo. Una forma de evitar esta dependencia es considerar una distribución a priori para el vector de parámetros del modelo e incorporarla en el criterio de optimalidad que se va a optimizar. En este artículo se consideran diseños D-óptimos en modelos no lineales heteroscedásticos cuando se incorpora una distribución a priori asociada a los parámetros del modelo. Se extiende el teorema de equivalencia al considerar el efecto de la distribución a priori. Se propone una metodología para la construcción de distribuciones a priori discretas y continuas. Se muestra, con un ejemplo, cómo a partir de las distribuciones construidas se pueden encontrar diseños óptimos con mayor número de puntos experimentales que los obtenidos con un valor local. La eficiencia de los diseños hallados es muy competitiva comparada con los diseños óptimos locales. Adicionalmente se consideran distribuciones a priori de una familia de escala, y se muestra que los diseños hallados son robustos a la elección de la distribución a priori elegida de esta familia.

show abstract

“…( 3) The weighted bootstrap can be found in many recent applications: Bücher and Dette (2010) approximated the empirical copula process with it; Davidson and Flachaire (2008), Feng et al (2011) and Rana et al (2012) exploited weighted bootstrap in regression analysis.…”

Section: Weighted Bootstrapmentioning

confidence: 99%

Applications of threshold models and the weighted bootstrap for Hungarian precipitation data

Varga

Rakonczai

Zempléni

2015

Theor Appl Climatol

View full text Add to dashboard Cite

This paper presents applications of the peaks-over threshold methodology for both the univariate and the recently introduced bivariate case, combined with a novel bootstrap approach. We compare the proposed bootstrap methods to the more traditional profile likelihood.We have investigated 63 years of the European Climate Assessment daily precipitation data for five Hungarian grid points, first separately for the summer and winter months, then aiming at the detection of possible changes by investigating 20 years moving windows. We show that significant changes can be observed both in the univariate and the bivariate cases, the most recent period being the most dangerous, as the return levels here are the highest. We illustrate these effects by bivariate coverage regions.Keywords daily precipitation data · moving window · profile likelihood · return level · univariate and bivariate generalized Pareto distribution · weighted bootstrap 1 IntroductionDetection of signs for climate changes are in the focus of recent climatology. There is an abundance of publications in the area of temperature changes. Precipitation is equally important, if we consider its economic effect -here the extremes play an especially important role, since these are in

show abstract

Robust Wild Bootstrap for Stabilizing the Variance of Parameter Estimates in Heteroscedastic Regression Models in the Presence of Outliers

Cited by 20 publications

References 22 publications

The Behrens–Fisher problem with covariates and baseline adjustments

The Behrens–Fisher problem with covariates and baseline adjustments

Diseños Dπ-óptimos para modelos no lineales heteroscedásticos: un estudio de robustez

Applications of threshold models and the weighted bootstrap for Hungarian precipitation data

Contact Info

Product

Resources

About