응용통계연구 (The Korean Journal of Applied Statistics)

  • 제36권5호
  • /
  • Pages.457-471
  • /
  • 2023
  • /
  • 1225-066X(pISSN)
  • /
  • 2383-5818(eISSN)
한국통계학회 (The Korean Statistical Society)
권호 표지
DOI QR코드

DOI QR Code

일별 시계열을 이용한 월별 시계열의 계절조정

Seasonal adjustment for monthly time series based on daily time series

  • 이긍희 (한국방송통신대학교 통계.데이터과학과)
  • Geung-Hee Lee (Department of Data Science and Statistics, Korea National Open University)
  • 투고 : 2023.03.23
  • 심사 : 2023.04.18
  • 발행 : 2023.10.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

월별 시계열은 일별 시계열의 월별 합이지만, 일별 시계열을 대체로 관측할 수 없어서 요일구성변동, 명절·공휴일변동 등 달력변동을 가상적으로 가정한 가변수를 포함한 RegARIMIA 모형을 이용하여 추정하고 있다. 일별 시계열을 관측할 수 있다면 요일구성변동, 명절·공휴일변동 등 달력변동을 일별 시계열을 바탕으로 추정할 수 있고 이를 이용하여 월별 시계열의 계절조정을 개선할 수 있다. 이 논문에서는 일별 시계열의 달력변동 추정을 이용하여 월별 시계열의 계절조정을 개선하는 방법을 제안하고, 이 방법을 적용하여 3개의 월별 시계열을 계절조정하고 기존의 X-13ARIMA-SEATS를 이용한 계절조정과 비교하였다.

The monthly series is an aggregation of daily values. In the absence of observable daily data, calendar effects such as trading day and holidays are estimated using a RegARIMA model. However, if the daily series were observable, these calendar effects could be estimated directly from the daily series, potentially improving the seasonal adjustment of the monthly time series. In this paper, we propose a method to improve the seasonal adjustment of monthly time series by using calendar variation estimation based on daily time series. We apply this seasonal adjustment method to three monthly time series and compare our results with those obtained using X-13ARIMA-SEATS.

키워드

과제정보

이 논문은 2021년도 한국방송통신대학교 학술연구비 지원을 받아 작성된 것임.

참고문헌

  1. Bell WR and Hillmer SC (1983). Modeling time series with calendar variation, Journal of the American Statistical Association, 78, 526-534. https://doi.org/10.1080/01621459.1983.10478005
  2. Cleveland RB, Cleveland WS, McRae JE, and Terpenning I (1990). STL: A seasonal-trend decomposition procedure based on loess, Journal of Official Statistics, 6, 3-73.
  3. Hyndman RJ and Khandakar Y (2008). Automatic time series forecasting: The forecast package for R, Journal of Statistical Software, 27, 1-22. https://doi.org/10.18637/jss.v027.i03
  4. Lee GH (1998). X-12 ARIMA seasonal adjustment in Korean economic time series, Economic Analysis, 4, 205-242.
  5. Lee GH and Jang K (2022). Seasonal adjustment of Korean daily data, Economic Analysis, 2, 70-114.
  6. Ollech D (2018). Seasonal adjustment of daily time series, Discussion Paper, No. 41/2018, Deutsche Bundesbank, Retrieved Oct. 11, 2023, Available from: https://www.econstor.eu/bitstream/10419/183487/1/dkp-41.pdf
  7. Roberts CG, Holan SH, and Monsell B (2009). Comparison of X-12-ARIMA trading day and holiday regressors with country specific regressors, research report series, No. 2009-07, Retrieved Oct. 11, 2023, Available from: https://www.census.gov/content/dam/Census/library/working-papers/2009/adrm/rrs2009-07.pdf
  8. U.S. Census Bureau (2017). X-13ARIMA-SEATS reference manual, retrieved Oct. 11, 2023, Available from: https://www2.census.gov/software/x-13arima-seats/x-13-data/documentation/docx13as.pdf