Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

부스트래핑(bootstrapping)기업을 활용한 회귀분석open accessBootstrapping Regression Models: A Statistical Simulation

Authors
심준섭
Issue Date
Jun-2004
Publisher
한국정책분석평가학회
Keywords
부스트래핑; 회귀분석; 반복표본추출; 표준오차; Monte Carlo 시뮬레이션; simulation; bootstrapping; regression analysis; resampling; standard error
Citation
정책분석평가학회보, v.14, no.2, pp 167 - 183
Pages
17
Journal Title
정책분석평가학회보
Volume
14
Number
2
Start Page
167
End Page
183
URI
https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/28593
DOI
10.23036/kapae.2004.14.2.007
ISSN
1226-6841
Abstract
본 연구는 표본의 크기가 제한된 상황 하에서 전통적인 OLS 회귀분석에 의한 모수추정치들이 갖는 불안정성의 문제를 극복하기 위한 대안적 통계기법으로 회귀모형 부스트래핑(bootstrapping regression models)의 적용가능성을 Monte Carlo 시뮬레이션을 통하여 평가하였다. 통계적 시뮬레이션을 위해 정해진 모수들을 투입조건으로 가상의 데이터를 구성하고, 회귀모형에 쌍부스트래핑(pairs bootstrapping) 기법을 적용한 후 얻어진 회귀계수들이 어느 정도나 모수의 근사치를 제공하는가를 분석하였다. 연구결과에 따르면 부스트래핑을 활용한 회귀분석은 기존의 단일표본에 기초한 OLS 회귀분석에 비해 R2와 조정-R2의 계산에 있어서 상대적으로 우수한 기법으로 확인되었다.
The purpose of this study is to present the bootstrap technique in the areas of public administration and policy as an alternative method to deal with statistical estimation problems in the conventional OLS regression analysis resulting from a limited number of observations. In particular, pairs bootstrapping that involves choosing random samples in paris from the original data set was applied. To assess and compare the accuracy and stability of the conventional OLS and bootstrap estimates, repeated random sampling that provides precise estimates of the coefficients was also conducted. The results of a Monte Carlo simulation showed that the bootstrap technique provided considerably accurate estimates of the parameters including R^2 and the adjusted R^2. One tentative conclusion can be drawn that the bootstrap technique could be used to solve the overfitting problem of R^2 in the OLS regression analysis.
Files in This Item
Appears in
Collections
College of Social Sciences > Department of Public Service > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Shim, Junseop photo

Shim, Junseop
사회과학대학 (공공인재학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE