Simple resampling methods for censored regression quantiles

Bilias, Yannis; Chen, Songnian; Ying, Zhiliang

doi:10.1016/s0304-4076(00)00042-7

Cited by 68 publications

(47 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…REML is believed to be a proper method when the sample size is small. To see this, a simulation study has been done on the study design used in Bilias et al (2000) and Yu and Stander (2007). That is, for a Tobit regression model, the latent variable was generated according to Regressors x 1 and x 2 are generated by a Bernoulli random number taking −1 and 1 each with probability 1/2, and a standard normal random number, respectively.…”

Section: Simulation Study and Conclusionmentioning

confidence: 99%

The restricted maximum likelihood estimation of a censored regression model

Lee

2017

CSAM

View full text Add to dashboard Cite

It is well known in a small sample that the maximum likelihood (ML) approach for variance components in the general linear model yields estimates that are biased downward. The ML estimate of residual variance tends to be downwardly biased. The underestimation of residual variance, which has implications for the estimation of marginal effects and asymptotic standard error of estimates, seems to be more serious in some limited dependent variable models, as shown by some researchers. An alternative frequentist's approach may be restricted or residual maximum likelihood (REML), which accounts for the loss in degrees of freedom and gives an unbiased estimate of residual variance. In this situation, the REML estimator is derived in a censored regression model. A small sample the REML is shown to provide proper inference on regression coefficients.

show abstract

Section: Simulation Study and Conclusionmentioning

confidence: 99%

The restricted maximum likelihood estimation of a censored regression model

Lee

2017

CSAM

View full text Add to dashboard Cite

show abstract

“…These approaches were compared with the standard Tobit QReg approach (crq) employing Powell's method (Koenker, 2011). The simulation design follows the setting of Bilias et al (2000) and Yu and Stander (2007). Data are simulated from the model The simulation results for β 0 , β 1 and β 2 are summarized in Table (1).…”

Section: Examplementioning

confidence: 99%

“…The Tobit QReg model provides an efficient way of coping with left-censored data, and can be viewed as a linear QReg model where only the data on the dependent variable is incompletely observed. A great body of work exists on Tobit QReg methods and we refer to Powell (1986), Hahn (1995), Buchinsky and Hahn (1998), Bilias et al (2000), Yu and Stander (2007) and Wang and Fygenson (2009) for an overview.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Tobit quantile regression usingg-prior distribution with ridge parameter

Alhamzawi

2014

Journal of Statistical Computation and Simulation

View full text Add to dashboard Cite

A Bayesian approach is proposed for coefficient estimation in Tobit quantile regression model. The proposed approach is based on placing a g-prior distribution depends on the quantile level on the regression coefficients. The prior is generalized by introducing a ridge parameter to address important challenges that may arise with censored data, such as multicollinearity and overfitting problems. Then, a stochastic search variable selection approach is proposed for Tobit quantile regression model based on g-prior. An expression for the hyperparameter g is proposed to calibrate the modified g-prior with a ridge parameter to the corresponding g-prior. Some possible extensions of the proposed approach are discussed, including the continuous and binary responses in quantile regression. The methods are illustrated using several simulation studies and a microarray study. The simulation studies and the microarray study indicate that the proposed approach performs well.

show abstract

“…The variances of parameter estimates typically depend on the unknown error distribution. To this end, a variety of resampling approaches have been proposed to estimate them [21,3,1]. However, intensive resamplings add computational burdens, while with very small number of resamplings, the estimating function may not be jittered enough to yield good estimates [28].…”

Section: Introductionmentioning

confidence: 99%

“…Because a Gaussian copula has a correlation structure and can handle general serial dependence, we utilize the Gaussian copula to explore the correlations in quantile regression with longitudinal data. We construct multiple unbiased estimating functions based on the working correlation matrices derived via the Gaussian copula with different correlation matrices, such as: exchangeable and AR (1). Furthermore, we combine these multiple estimating functions by the empirical likelihood method [22,20,18].…”

Section: Introductionmentioning

confidence: 99%

Efficient parameter estimation via Gaussian copulas for quantile regression with longitudinal data

Wang

2016

Journal of Multivariate Analysis

View full text Add to dashboard Cite

Simple resampling methods for censored regression quantiles

Cited by 68 publications

References 26 publications

The restricted maximum likelihood estimation of a censored regression model

The restricted maximum likelihood estimation of a censored regression model

Bayesian Tobit quantile regression usingg-prior distribution with ridge parameter

Efficient parameter estimation via Gaussian copulas for quantile regression with longitudinal data

Contact Info

Product

Resources

About