schliessen

Filtern

 

Bibliotheken

Weighted profile least squares estimation for a panel data varying-coefficient partially linear model

This paper is concerned with inference of panel data varying-coefficient partially linear models with a one-way error structure. The model is a natural extension of the well-known panel data linear model (due to Baltagi 1995) to the setting of semiparametric regressions. The authors propose a weight... Full description

Journal Title: Chinese Annals of Mathematics Series B, 2010, Vol.31(2), pp.247-272
Main Author: Zhou, Bin
Other Authors: You, Jinhong , Xu, Qinfeng , Chen, Gemai
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: ISSN: 0252-9599 ; E-ISSN: 1860-6261 ; DOI: 10.1007/s11401-008-0153-3
Link: http://dx.doi.org/10.1007/s11401-008-0153-3
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: springer_jour10.1007/s11401-008-0153-3
title: Weighted profile least squares estimation for a panel data varying-coefficient partially linear model
format: Article
creator:
  • Zhou, Bin
  • You, Jinhong
  • Xu, Qinfeng
  • Chen, Gemai
subjects:
  • Semiparametric
  • Panel data
  • Local polynomial
  • Weighted estimation
  • Block bootstrap
ispartof: Chinese Annals of Mathematics, Series B, 2010, Vol.31(2), pp.247-272
description: This paper is concerned with inference of panel data varying-coefficient partially linear models with a one-way error structure. The model is a natural extension of the well-known panel data linear model (due to Baltagi 1995) to the setting of semiparametric regressions. The authors propose a weighted profile least squares estimator (WPLSE) and a weighted local polynomial estimator (WLPE) for the parametric and nonparametric components, respectively. It is shown that the WPLSE is asymptotically more efficient than the usual profile least squares estimator (PLSE), and that the WLPE is also asymptotically more efficient than the usual local polynomial estimator (LPE). The latter is an interesting result. According to Ruckstuhl, Welsh and Carroll (2000) and Lin and Carroll (2000), ignoring the correlation structure entirely and “pretending” that the data are really independent will result in more efficient estimators when estimating nonparametric regression with longitudinal or panel data. The result in this paper shows that this is not true when the design points of the nonparametric component have a closeness property within groups. The asymptotic properties of the proposed weighted estimators are derived. In addition, a block bootstrap test is proposed for the goodness of fit of models, which can accommodate the correlations within groups. Some simulation studies are conducted to illustrate the finite sample performances of the proposed procedures.
language: eng
source:
identifier: ISSN: 0252-9599 ; E-ISSN: 1860-6261 ; DOI: 10.1007/s11401-008-0153-3
fulltext: fulltext
issn:
  • 1860-6261
  • 18606261
  • 0252-9599
  • 02529599
url: Link


@attributes
ID676227851
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid10.1007/s11401-008-0153-3
sourceidspringer_jour
recordidTN_springer_jour10.1007/s11401-008-0153-3
sourcesystemPC
galeid229537760
display
typearticle
titleWeighted profile least squares estimation for a panel data varying-coefficient partially linear model
creatorZhou, Bin ; You, Jinhong ; Xu, Qinfeng ; Chen, Gemai
ispartofChinese Annals of Mathematics, Series B, 2010, Vol.31(2), pp.247-272
identifier
subjectSemiparametric ; Panel data ; Local polynomial ; Weighted estimation ; Block bootstrap
descriptionThis paper is concerned with inference of panel data varying-coefficient partially linear models with a one-way error structure. The model is a natural extension of the well-known panel data linear model (due to Baltagi 1995) to the setting of semiparametric regressions. The authors propose a weighted profile least squares estimator (WPLSE) and a weighted local polynomial estimator (WLPE) for the parametric and nonparametric components, respectively. It is shown that the WPLSE is asymptotically more efficient than the usual profile least squares estimator (PLSE), and that the WLPE is also asymptotically more efficient than the usual local polynomial estimator (LPE). The latter is an interesting result. According to Ruckstuhl, Welsh and Carroll (2000) and Lin and Carroll (2000), ignoring the correlation structure entirely and “pretending” that the data are really independent will result in more efficient estimators when estimating nonparametric regression with longitudinal or panel data. The result in this paper shows that this is not true when the design points of the nonparametric component have a closeness property within groups. The asymptotic properties of the proposed weighted estimators are derived. In addition, a block bootstrap test is proposed for the goodness of fit of models, which can accommodate the correlations within groups. Some simulation studies are conducted to illustrate the finite sample performances of the proposed procedures.
languageeng
source
version4
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
backlink$$Uhttp://dx.doi.org/10.1007/s11401-008-0153-3$$EView_full_text_in_Springer_(Subscribers_only)
search
creatorcontrib
0Zhou, Bin
1You, Jinhong
2Xu, Qinfeng
3Chen, Gemai
titleWeighted profile least squares estimation for a panel data varying-coefficient partially linear model
descriptionThis paper is concerned with inference of panel data varying-coefficient partially linear models with a one-way error structure. The model is a natural extension of the well-known panel data linear model (due to Baltagi 1995) to the setting of semiparametric regressions. The authors propose a weighted profile least squares estimator (WPLSE) and a weighted local polynomial estimator (WLPE) for the parametric and nonparametric components, respectively. It is shown that the WPLSE is asymptotically more efficient than the usual profile least squares estimator (PLSE), and that the WLPE is also asymptotically more efficient than the usual local polynomial estimator (LPE). The latter is an interesting result. According to Ruckstuhl, Welsh and Carroll (2000) and Lin and Carroll (2000), ignoring the correlation structure entirely and “pretending” that the data are really independent will result in more efficient estimators when estimating nonparametric regression with longitudinal or panel data. The result in this paper shows that this is not true when the design points of the nonparametric component have a closeness property within groups. The asymptotic properties of the proposed weighted estimators are derived. In addition, a block bootstrap test is proposed for the goodness of fit of models, which can accommodate the correlations within groups. Some simulation studies are conducted to illustrate the finite sample performances of the proposed procedures.
subject
0Semiparametric
1Panel data
2Local polynomial
3Weighted estimation
4Block bootstrap
general
010.1007/s11401-008-0153-3
1English
2Springer Science & Business Media B.V.
3SpringerLink
sourceidspringer_jour
recordidspringer_jour10.1007/s11401-008-0153-3
issn
01860-6261
118606261
20252-9599
302529599
rsrctypearticle
creationdate2010
addtitle
0Chinese Annals of Mathematics, Series B
1Chin. Ann. Math. Ser. B
searchscopespringer_journals_complete
scopespringer_journals_complete
lsr30VSR-Enriched:[galeid, pages]
sort
titleWeighted profile least squares estimation for a panel data varying-coefficient partially linear model
authorZhou, Bin ; You, Jinhong ; Xu, Qinfeng ; Chen, Gemai
creationdate20100300
facets
frbrgroupid8659497444607770204
frbrtype5
languageeng
creationdate2010
topic
0Semiparametric
1Panel Data
2Local Polynomial
3Weighted Estimation
4Block Bootstrap
collectionSpringerLink
prefilterarticles
rsrctypearticles
creatorcontrib
0Zhou, Bin
1You, Jinhong
2Xu, Qinfeng
3Chen, Gemai
jtitleChinese Annals Of Mathematics, Series B
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Zhou
1You
2Xu
3Chen
aufirst
0Bin
1Jinhong
2Qinfeng
3Gemai
au
0Zhou, Bin
1You, Jinhong
2Xu, Qinfeng
3Chen, Gemai
atitleWeighted profile least squares estimation for a panel data varying-coefficient partially linear model
jtitleChinese Annals of Mathematics, Series B
stitleChin. Ann. Math. Ser. B
addtitleChinese Annals of Mathematics, Series B
risdate201003
volume31
issue2
spage247
epage272
issn0252-9599
eissn1860-6261
genrearticle
ristypeJOUR
abstractThis paper is concerned with inference of panel data varying-coefficient partially linear models with a one-way error structure. The model is a natural extension of the well-known panel data linear model (due to Baltagi 1995) to the setting of semiparametric regressions. The authors propose a weighted profile least squares estimator (WPLSE) and a weighted local polynomial estimator (WLPE) for the parametric and nonparametric components, respectively. It is shown that the WPLSE is asymptotically more efficient than the usual profile least squares estimator (PLSE), and that the WLPE is also asymptotically more efficient than the usual local polynomial estimator (LPE). The latter is an interesting result. According to Ruckstuhl, Welsh and Carroll (2000) and Lin and Carroll (2000), ignoring the correlation structure entirely and “pretending” that the data are really independent will result in more efficient estimators when estimating nonparametric regression with longitudinal or panel data. The result in this paper shows that this is not true when the design points of the nonparametric component have a closeness property within groups. The asymptotic properties of the proposed weighted estimators are derived. In addition, a block bootstrap test is proposed for the goodness of fit of models, which can accommodate the correlations within groups. Some simulation studies are conducted to illustrate the finite sample performances of the proposed procedures.
copBerlin/Heidelberg
pubSpringer-Verlag
doi10.1007/s11401-008-0153-3
pages247-272
date2010-03