Censored Regression Quantiles

By Stephen Portnoy. 2003

832 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/d0bbeeba01481b12a805bb2c23c2c462f7188ebb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

Estimation of Censored Quantile Regression for Panel Data With Fixed Effects (2013, background): “…1997; Buchinsky and Hahn 1998; Bilias, Chen, and Ying 2000; Khan and Powell 2001; Chernozhukov and Hong 2002; Honoré, Khan, and Powell 2002; Portnoy 2003; Peng and Huang 2008; Lin, He, and Portnoy 2012; Tang et al. 2012), the literature on censored QR for panel data is still very limited.”
Quantile Regression: Overview and Selected Applications ∗ (2004, background): “Powell (1986) made the crucial observation that linear conditional quantile models can solve the fixed censoring issue by a simple nonlinear modification of the response function.”
Unconditional Quantile Regression for Panel Data with Exogenous or Endogenous Regressors (2010, positive): “I apply the estimator to the analysis of Rouse [1998]. Importantly, the conclusions drawn from this analysis are very different from the conclusions found in Harding and Lamarche [2009] which uses conditional quantiles.”
Quantile Regression with Clustered Data (2015, methodology): “Following Powell (1984, 1986) and Kim and White (2003), we consider the estimator 1 1 1ˆ ˆˆB I[| | ] , ˆ2 G n gi G gi gig i G u c x x c G = = = ≤ ′∑ ∑ 5 Related estimators of this covariance matrix have recently been used in empirical applications by Penner (2008) and by Fitzenberger, Kohn, and…”
SEMIPARAMETRIC ESTIMATION OF A PARTIALLY LINEAR CENSORED REGRESSION MODEL (2001, background): “This is to be expected because the full rank condition for the uncensored partially linear model fails also in this case, as discussed in Robinson (1988). Furthermore, the condition also fails if coij = 0 with high probability.”
Conditional quantile screening in ultrahigh-dimensional heterogeneous data (2015, neutral): “…a weight-adjusted version of dk(t), rk(t) = E { [τ − ω(F)I {X < Qτ (Y )}] I (Zk < t) } , where F(y) = pr(Y y) and the weight function ω(F) = ⎧⎨ ⎩ 1, = 1 or F(C) > τ, τ − F(C) 1 − F(C) , = 0, F(C) τ redistributes the masses of censored observations to the right (Portnoy, 2003; Wang & Wang, 2009).”
Censored Quantile Regression Redux (2008, methodology): “As was immediately apparent from the work of Powell (1984, 1986) quantile regression oers some distinct advantages over mean regression methods when there is censoring; departures from Gaussian conditions, or any deviation from identically distributed error, induce bias for leastsquares based esti”
A quantile regression estimator for censored data (2013, methodology): “…simulation study, we compare the estimator of Ying et al. (YJW), the proposed estimator (CQR), the locally weighted censored quantile regression estimator (Lcrq) in Wang and Wang [22], the estimator in Portnoy [17], abbreviated as Port, and the estimator by Peng and Huang [16], abbreviated as PH.”
Estimating Structural Changes in Regression Quantiles (2011, methodology): “To address the rst issue, we apply the censored quantile regression of Powell (1996) conditioning”
Partial rank estimation of duration models with general forms of censoring (2007, neutral): “…estimators for b0-examples include Buckley and James (1979), Koul, Susarla and Van Ryzin (1981), Tsiatis (1990), Ying, Jung and Wei (1995), Yang (1999), Honoré, Khan and Powel (2002) and Portnoy (2003), some of which allow for the distribution of the censoring variable to depend on the covariates.”
Life Cycle and Cohort Productivity in Economic Research: The Case of Germany (2008, positive): “We used the SAS estimation procedure TRAJ, which maximizes the joint likelihood of the mixture model.”
Inference on endogenously censored regression models using conditional moment inequalities (2009, background): “On the other hand, statistical independence between ǫi and (xi, ci) is imposed in Buckley and James (1979) and Yang (1999), Portnoy (2003). Independence between ci and (xi, ǫi) was imposed in Ying, Jung, and Wei (1995), and Honoré, Khan, and Powell (2002) (8). This is important in competing risks se”
A Test of the Conditional Independence Assumption in Sample Selection Models: A TEST OF THE CONDITIONAL INDEPENDENCE ASSUMPTION (2012, neutral): “In particular, we estimate the densities using 11 the kernel method as in Powell (1986), Buchinsky (1998a), and Lee (2007): ^̀ i ( ) = ( 1 yi < x 0 2î ( ) + J (x 0 1î) ̂ ( ) )m̂i; ̂b; = (nhn) 1 nX i=1 t̂i "̂i ( ) hn m̂im̂ 0 i; ̂ = (nhn) 1 nX i=1 t̂i "̂i ( ) hn d J (x 0 1î) d m̂i; "̂ ( ) = yi…”
Quantile-adaptive model-free variable screening for high-dimensional heterogeneous data (2013, methodology): “As a powerful alternative to the classical Cox model, quantile regression has recently emerged as a useful tool for analyzing censored data, see Ying, Jung and Wei (1995), McKeague, Subramanian and Sun (2001), Portnoy (2003), Peng and Huang (2008), Wang and Wang (2009), among others.”
Gibbs sampling methods for Bayesian quantile regression (2011, methodology): “For comparison, we also considered the Powell [21] estimator, which is commonly used in practice and can be implemented by the function crq in the quantreg package.”
QUANTILE AND PROBABILITY CURVES WITHOUT CROSSING (2007, methodology): “Another manifestation of this issue, known as 4See Koenker and Bassett (1978), Powell (1986), Chaudhuri (1991), Buchinsky and Hahn (1998), Yu and Jones (1998), Abadie et al. (2002), Honoré et al. (2002), and Chernozhukov and Hansen (2006), among others, for examples of exogenous, censored,…”
Unconditional Quantile Treatment Effects Under Endogeneity (2007, neutral): “…heterogeneous effects, its theoretical properties have been studied extensively and it has been used in many empirical studies; see, for example, Powell (1986), Guntenbrunner and Jurečková (1992), Buchinsky (1994), Koenker and Xiao (2002), and Angrist, Chernozhukov, and Fernández-Val (2006).”