임금구조기본통계조사의 직업소분류별 임금추정에서 소지역추정법 적용방안 연구
A Study on Small Area Estimation for the Wage Estimation by Occupation in Minor Group in the Wage Structure Survey
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
본 연구에서는 임금구조기본통계조사 체계에서 직업 소분류단위별 평균임금 추정을 위한 소지역추정법의 적용 가능성을 검토하였다. 2005년 조사 자료 중 제조업 15 중분류 직업 소분류 단위의 평균임금 추정에서 설계기반 직접추정량, 일반선형회귀모형을 이용한 표본회귀추정량, 직접추정량과 표본회귀추정량의 가중평균인 복합추정량, 혼합선형모형을 이용한 경험적 최량선형불편예측추정량(EBLUP : Empirical Best Linear Unbiased Predictor)을 분석한 결과에서 표본 수가 작지 않으면 복합추정과 EBLUP추정은 유사한 결과를 보이고, 혼합모형을 이용한 EBLUP추정에서는 랜덤효과의 분산([ ])이 오차항의 분산(δ²)에 비해 상대적으로 매우 작은 경우, 표본회귀추정과 거의 동일한 추정결과를 보인다는 사실을 확인하였다.
Abstract
This paper examines the applicability of the small area estimation technique to estimate the mean wage by minor group(3 digit) of occupation with small size of sample using the data from the Wage Structure Survey(WSS). Basically, the results of the survey is produced the mean wage by sub-major group(2-digit) of occupation. The estimators are design-based direct estimator, sample regression estimator using generalized linear model, composite estimator which is defined as the weighted average of both direct and sample regression estimator, and the EBLUP(Empirical Best Linear Unbiased Predictor) using mixed linear model. The mean wage of occupation by minor group in manufacturing(food and drinks) are estimated using these estimation methods. The very similar results were derived between the composite and EBLUP for the groups where the enough sample was allocated. It has been verified that the results from the sample regression estimator are nearly the same as those from the EBLUP using the mixed model, where the variance of the random effect is relatively smaller than the variance of the error term. Thus, it might be concluded that we can estimate more reliable mean wage by minor group of occupation with small size of sample using the WSS data when the small area estimation technique is applied.
참고문헌 (16)
- 이계오, "시군구 실업자 추정을 위한 소지역 추정법", 응용통계연구, 13(2), pp.275~286 (2000)
- 한국통계학회, "임금구조통계조사 표본설계 최종보고서", ~ (2005)
- Battese, G. E., "Prediction and county crop areas using survey and satellite data, Proceedings of the Section on Survey Research Methods", pp.500~505 (1981), American Statistical Association
- Battese,G.E, "An error components model for prediction of county crop areas using survey and satellite data,", Journal of the American Statistical Association, 83, pp.28~36 (1988)
- Datta, G. S., "Empirical best linear unbiased and empirical Bayes prediction in multivariate small area estimation", Journal of Statistical Planning and Inference, 75, pp.269~279 (1999)
- Erickson,E.P, "A regression method for estimation populations of local areas,", Journal of the American Statistical Association, 69, pp.867~875 (1974)
- Fay,R.E, "Estimates of income for small places:An application of James-Stein procedures to census data,", Journal of the American Statistical Association, 74, pp.269~277 (1979)
- Ghosh,M, "Small area estimation:an appraisal,", Statistical Science, 9, pp.55~93 (1994)
- Gonzalez,M.E, "Use and evaluation of synthetic estimates", pp.33~36 (1973), American Statistical Association
- Henderson,C.R, "Estimation of genetic parameters,", Annals of Mathematical Statistics, 21, pp.309~310 (1950)
- Rao,J.N.K, "Some recent advances in model-based small area estimation", \Survey Methodology, 25(2), pp.175~186 (1999)
- Lahiri,P.A, "Robust estimation of mean squares error of small area estimators,", Journal of the American Statistical Association, 82, pp.758~766 (1995)
- Lahiri,M, "Composite estimation of drug prevalences for sub-state areas,", Survey Methodology, 25(1), pp.81~86 (1999)
- Prasad,N.G.N, "The estimation of mean squared errors of small area estimators,", Journal of the American Statistical Association, 85, pp.163~171 (1990)
- Purcell,N.J, "Estimation for small domains", Biometrics, 35, pp.365~384 (1979)
- Rao,J.N.K, "Small Area Estimation" (2003), Wiley, New York.