초록

AI-Helper

국가통계의 활용도가 높아질수록 통계에 대한 객관적인 품질평가 필요성도 높아지게 된다. 과거에 대표적인 품질평가지표로 간주되어 온 평균제곱오차나 응답률은 유용성에 많은 문제가 있으므로 통계이용자의 다양한 요구사항을 반영할 수 있는 새로운 품질지표 개발의 필요성이 대두되었다. 따라서 본 논문에서는 정부기관에서 작성하고 있는 표본통계조사를 대상으로 통계작성 절차의 흐름을 분석하고 각 절차별 투입자료와 산출결과를 인식함으로써 최종 집계결과의 품질에 영향을 미칠 수 있는 절차별 품질지표를 개발하는 방법이 연구되었다. 또한 발굴된 절차별 품질지표에 다른 통계간 또는 동일 통계간 품질을 비교할 수 있도록 품질지수 산출방법이 논의되었다.

Abstract ▼ AI-Helper

As the utilization of official statistics has been recently increased, the necessity of objective quality assessment also has been increased. Since mean square error(MSE) and response rate, which have been considered as representative quality indicators in the past, may have the limits of use, it ha...

As the utilization of official statistics has been recently increased, the necessity of objective quality assessment also has been increased. Since mean square error(MSE) and response rate, which have been considered as representative quality indicators in the past, may have the limits of use, it has been demanded to develop new quality indicators which are able to reflect the various requirements of users. In this paper, regarding sample surveys conducted by governmental agencies, the flow of procedures in statistics production is analyzed using input-output of each procedure. As the result, how to identify and develop quality indicators for each procedure is discussed, with some instances of indicators. Finally, the quality index using the results of quality assessment would be calculated based on a weighting method by the size of deviation of statistical measures.