Marginal nonparametric kernel regression accounting for within-subject correlation

Wang, Naisyin

doi:10.1093/biomet/90.1.43

Cited by 174 publications

(173 citation statements)

References 11 publications

Supporting

Mentioning

168

Contrasting

Order By: Relevance

“…Our estimation procedure is based on profile-kernel estimating equations, where θ(t) is estimated using a kernel GEE estimator accounting for correlations proposed by Wang (2003) and β is estimated using a profile-type estimating equation. The proposed method differs from those proposed by Severini andStaniswalis (1994) andLC (2001a) only in the way in which θ(t, β), the estimated θ(t) for a given β, is constructed.…”

Section: The Estimation Proceduresmentioning

confidence: 99%

Efficient Semiparametric Marginal Estimation for Longitudinal/Clustered Data

Wang

Carroll

Lin

2005

Journal of the American Statistical Association

166

198

View full text Add to dashboard Cite

We consider marginal generalized semiparametric partially linear models for clustered data. Lin and Carroll derived the semiparametric efficient score function for this problem in the multivariate Gaussian case, but they were unable to construct a semiparametric efficient estimator that actually achieved the semiparametric information bound. Here we propose such an estimator and generalize the work to marginal generalized partially linear models. We investigate asymptotic relative efficiencies of the estimators that ignore the within-cluster correlation structure either in nonparametric curve estimation or throughout. We evaluate the finite-sample performance of these estimators through simulations and illustrate it using a longitudinal CD4 cell count dataset. Both theoretical and numerical results indicate that properly taking into account the within-subject correlation among the responses can substantially improve efficiency.

show abstract

Section: The Estimation Proceduresmentioning

confidence: 99%

Efficient Semiparametric Marginal Estimation for Longitudinal/Clustered Data

Wang

Carroll

Lin

2005

Journal of the American Statistical Association

166

198

View full text Add to dashboard Cite

show abstract

“…In case of lack of independence, Robinson (2008Robinson ( , 2011 derives consistency and asymptotic distribution theory for the local constant regression estimator in relation to various kinds of spatial data. Other authors (for example, Xiao et al, 2003;Lin and Carroll, 2000;Ruckstuhl et al, 2000;Wang, 2003) study possible extensions of the nonparametric regression to a non i.i.d. errors setting, where errors can be correlated and heteroschedastic.…”

Section: Nonparametric Regression With Dependent Errorsmentioning

confidence: 99%

Distribution Dynamics in the US. A Spatial Perspective

Gerolimetto

Magrini

2016

SSRN Journal

View full text Add to dashboard Cite

It is quite common in cross-sectional convergence analyses that data exhibit strong spatial dependence. While the literature adopting the regression approach is now fully aware that neglecting this feature may lead to inaccurate results and has therefore suggested a number of statistical tools for addressing the issue, research is only at a very initial stage within the distribution dynamics approach. In particular, in the continuous state-space framework, a few authors opted for spatial pre-filtering the data in order to guarantee the statistical properties of the estimates. In this paper, we follow an alternative route that starts from the idea that spatial dependence is not just noise but can be a substantive element of the data generating process. In particular, we develop a tool that, building on a mean-bias adjustment procedure established in the literature, explicitly allows for spatial dependence in distribution dynamics analysis thus eliminating the need for pre-filtering. Using this tool, we then reconsider the evidence on convergence across US states. It is quite common in cross-sectional convergence analyses that data exhibit strong spatial dependence. While the literature adopting the regression approach is now fully aware that neglecting this feature may lead to inaccurate results and has therefore suggested a number of statistical tools for addressing the issue, research is only at a very initial stage within the distribution dynamics approach. In particular, in the continuous state-space framework, a few authors opted for spatial pre-filtering the data in order to guarantee the statistical properties of the estimates. In this paper we follow an alternative route that starts from the idea that spatial dependence is not just noise but can be a substantive element of the data generating process. In particular, we develop a tool that, building on a mean-bias adjustment procedure established in the literature, explicitly allows for spatial dependence in distribution dynamics analysis thus eliminating the need for pre-filtering. Using this tool, we then reconsider the evidence on convergence across US states. Keywords

show abstract

“…For simplicity, we ignore the dependence of repeated measurements coming from the same subject; it was demonstrated in Welsh, Lin and Carroll (2002) and Wang (2003) that adjusting to a given dependence structure can lead to substantial efficiency gains. Whether these gains hold up when the correlations need to be estimated remains an open question.…”

Section: Fitting Functional Response Modelsmentioning

confidence: 99%

Functional Response Models

Kowalski

2007

Modern Applied U‐Statistics

View full text Add to dashboard Cite

We review functional regression models and discuss in more detail the situation where the predictor is a vector or scalar such as a dose and the response is a random trajectory. These models incorporate the influence of the predictor either through the mean response function, through the random components of a Karhunen-Loève or functional principal components expansion, or by means of a combination of both. In a case study, we analyze dose-response data with functional responses from an experiment on the age-specific reproduction of medflies. Daily egg-laying was recorded for a sample of 874 medflies in response to dietary dose provided to the flies. We compare several functional response models for these data. A useful criterion to evaluate models is a model's ability to predict the response at a new dose. We quantify this notion by means of a conditional prediction error that is obtained through a leave-one-dose-out technique.

show abstract

Marginal nonparametric kernel regression accounting for within-subject correlation

Cited by 174 publications

References 11 publications

Efficient Semiparametric Marginal Estimation for Longitudinal/Clustered Data

Efficient Semiparametric Marginal Estimation for Longitudinal/Clustered Data

Distribution Dynamics in the US. A Spatial Perspective

Functional Response Models

Contact Info

Product

Resources

About