Marginal nonparametric kernel regression accounting for within‐subject correlation

By Naisyin Wang. 2003

219 citations recorded by the source corpus.

Subfields: Genetics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/21cb3ae2846e085835165fcd0ab45de9e1114eda

How researchers see this paper

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

In Genetics

In Statistics and Probability

Citations in the corpus

Simultaneous variable selection and estimation in semiparametric modeling of longitudinal/clustered data (2013, background): “This is challenging due to the issue of “curse of dimensionality” and the additional complexity of the correlation structures (Wang [34]) introduced by repeated measurements.”
Estimation of the covariance matrix of random effects in longitudinal studies (2007, background): “Wang [ 25 ] provides an innovative kernel smoothing and demonstrates that, when the true correlation is available, her estimator is more efficient than the most efficient estimator that is obtained by adopting a working independence approach.”
Robust Estimation in Generalized Partial Linear Models for Clustered Data (2005, result): “These asymptotic properties are in sharp contrast to those of the profile-kernel estimators, where semiparametric efficient scores are highly complicated (see, e.g., Wang 2003).”
FUNCTIONAL RESPONSE MODELS (2004, methodology): “In this paper, we introduce a general model which extends the approaches considered previously in Chiou, Müller, Wang (2003) and Chiou, Müller, Wang and Carey (2003).”
Smoothing spline estimation in varying‐coefficient models (2004, methodology): “This approach has been shown to be inefficient in the presence of within-subject correlation by Wang (2003) who proposed a one-step update estimator which resolves this problem. The basic idea is to use the original responses, the initial estimates of the conditional means and the covariance matrix ”
Semiparametric estimation in general repeated measures problems (2006, methodology): “Following Wang (2003), we propose to solve the kernel estimating equation (4) for θ̂.z/ in the following iterative fashion.”
Consistent Model Selection for Marginal Generalized Additive Model for Correlated Data (2010, background): “In addition, for smoothing spline and seemingly unrelated kernel approaches (Wang, 2003), ignoring the correlation could also lead to biased estimation (Zhu, Fung and He, 2008).”
Efficient Semiparametric Marginal Estimation for Longitudinal/Clustered Data (2005, methodology): “For the first 50 datasets, we estimated the bandwidth using a method mimicking the idea of the empirical bias bandwidth selection method (Ruppert 1997; Wang 2003) and the leave-one-subjectout cross-validation methods in nonparametric estimation with the WI and the proposed θ̂ .”
Asymptotic optimality and efficient computation of the leave-subject-out cross-validation (2012, background): “…et al. (1998), Lin and Ying (2001), Wang, Carroll and Lin (2005)] and nonparametric [e.g., Fan and Zhang (2000), Lin and Carroll (2000), Rice and Silverman (1991), Wang (1998, 2003), Welsh, Lin and Carroll (2002), Zhu, Fung and He (2008)] models have been proposed and studied in the literature.”
Statistical Methods with Varying Coefficient Models. (2008, methodology): “An innovative kernel method is proposed by Wang (2003), which incorporates the true covariance structure.”
Nonparametric Regression Analysis of Longitudinal Data (2005, methodology): “Another framework mimicking the marginal approach of GEE (Generalized Estimating Equations) can be found in [14], [26], [27] and”
Semiparametric Mean–Covariance Regression Analysis for Longitudinal Data (2009, unknown): “See, for example, the kernel and spline approaches in Lin and Carroll (2001), Welch, Lin, and Carroll (2002), He, Zhu, and Fung (2002), Wang (2003), Wang, Carroll, and Lin (2005), He, Fung, and Zhu (2005), and Lin and Carroll (2006).”
Estimation and model selection in generalized additive partial linear models for correlated data with diverging number of covariates (2014, background): “Moreover, [28] and [36] indicate that in nonparametric settings ignoring the correlation could also result in biased estimation since the selection process is rather sensitive to small departures from the true correlation structure, and likely to cause overfitting of the nonparametric estimator to c”
Profile‐kernel versus backfitting in the partially linear models for longitudinal/clustered data (2004, background): “In Lemma 1 of Wang, Carroll and Lin’s report, it is shown that the nonparametric smoother of Wang (2003) possesses such a property.”