Search
Search

연구성과물 검색 타이틀 이미지

HOME ICON HOME > Search by Achievements Type > Reports View

Reports Detailed Information

https://www.krm.or.kr/krmts/link.html?dbGubun=SD&m201_id=10061458&local_id=10086350
유한 시계열 동태적 패널의 횡단면 최우추정
Reports NRF is supported by Research Projects( 유한 시계열 동태적 패널의 횡단면 최우추정 | 2015 Year 신청요강 다운로드 PDF다운로드 | 최인(서강대학교) ) data is submitted to the NRF Project Results
Researcher who has been awarded a research grant by Humanities and Social Studies Support Program of NRF has to submit an end product within 6 months(* depend on the form of business)
사업별 신청요강보기
  • Researchers have entered the information directly to the NRF of Korea research support system
Project Number 2015S1A5A2A01009333
Year(selected) 2015 Year
the present condition of Project 종료
State of proposition 재단승인
Completion Date 2017년 09월 11일
Year type 결과보고
Year(final report) 2017년
Research Summary
  • Korean
  • 이 논문에서는 패널 AR(1) 모델을 위한 두개의 추정량이 제시되었다. 이 추정량은 초기 데이터를 회귀변수 (regressor)로 하고 마지막 데이터를 종속변수로 하는 횡단면 모델에 기초한다. 오차항과 회귀변수는 상관관계를 가지고 있다. 처음 추정량은 위에서 언급한 횡단면 모델에 기초하여 구성된 최우추정량이다.이 추정량은 일치성과 대수적 정규분포를 가지고 있다. 이러한 추정량을 초기 추정량을 사용하여 통합최소자승추정량을 이 논문은 제시한다. 이 추정량 또한 일치성과 대수적 정규분포를 가지고 있다. 이러한 추정량들은 시간에 따라 변하지 않는 회귀변수를 가진 패널 AR(1) 모델에 확장 사용하는 것이 가능하다. 이러한 추정량들의 장점은 패널 AR(1) 모델의 계수값이 어떤 값을 갖어도 상관 없다는 점이다. 실험을 통해 이 추정량들이 기존의 GMM 추정량보다 우월하다는 증거가 제시되어 있다.
  • English
  • We have proposed two, new estimators for the PAR(1) models with short T and large N. These estimators are based on the cross-sectional regression model using the first time series observations as a regressor and the last as a dependent variable. The regressors and errors of this regression model are dependent. The first estimator is the cross-sectional MLE under the assumption of normal distributions that are consistent in the presence of the regressor-error dependency of the cross-sectional regression model. Using the cross-sectional MLE, we constructed the pooled least squares estimator for the PAR model of order 1 that is free of bias is constructed. These two estimators were also extended to the PAR model with endogenous time-variant and time-invariant regressors. The estimators of this paper provide consistent estimates of the PAR coefficients for stationary, unit root and explosive PAR models, estimate the coefficients of time-invariant regressors consistently and can be computed as long as T≥2. The estimators were shown to perform quite well in finite samples relative to well-known GMM estimators.
Research result report
  • Abstract
  • This paper proposes new estimators for the panel autoregressive (PAR) models with short time dimensions (T) and large cross sections (N). These estimators are based on the cross-sectional regression model using the first time series observations as a regressor and the last as a dependent variable. The regressors and errors of this regression model are correlated. The first estimator is the maximum likelihood estimator (MLE) under the assumption of normal distributions. This estimator is called the cross-sectional MLE (CSMLE). The second estimator is the bias-corrected pooled least squares estimator (BCPLSE) that eliminates the asymptotic bias of PLSE by using the CSMLE. The CSMLE and BCPLSE are extended to the PAR model with endogenous time-variant and time-invariant regressors. The CSMLE and BCPLSE provide consistent estimates of the PAR coefficients for stationary, unit root and explosive PAR models, estimate the coefficients of time-invariant regressors consistently and can be computed as long as T≥2. Their finite sample properties are compared with those of some other estimators for the PAR model of order 1. The estimators of this paper are shown to perform quite well in finite samples.
  • Research result and Utilization method
  • 본 연구에서 제시된 추정량은 그 유용성이 받아 들여 지면 향후 노동경제학, 국제 경제학, 보건 경제학 등 경제학의 제 분야에서 사용되리라고 기대된다.
  • Index terms
  • 동태적 패널, 최우도추정량, 통합최소추정량, 안정성, 단위근, 폭발성
  • List of digital content of this reports
데이터를 로딩중 입니다.
  • This document, it is necessary to display the original author and you do not have permission
    to use copyrighted material for-profit
  • In addition , it does not allow the change or secondary writings of work
데이터 이용 만족도
자료이용후 의견
입력
트위터 페이스북
NRF Daejeon
(34113) 201, Gajeong-ro, Yuseong-gu, Daejeon, Korea
Tel: 82-42-869-6114 / Fax: 82-42-869-6777
NRF Seoul
(06792) 25, Heonreung-ro, Seocho-gu, Seoul, Korea
Tel: 82-2-3460-5500 / Fax: 82-2-3460-5759
KRM Help Center
Tel : 042-869-6086 Fax : 042-869-6580
E-mail : krmcenter@nrf.re.kr