The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

A study on forecasting provinces-specific fertility for Korea

시도별 출산력 예측에 대한 연구

  • Kim, Soon-Young (Statistical Research Institute, Statistics Korea) ;
  • Oh, Jinho (School of Basic Sciences, College of Engineering, Hanbat National University)
  • 김순영 (통계청 통계개발원) ;
  • 오진호 (한밭대학교 공과대학 기초과학부)
  • Received : 2018.12.21
  • Accepted : 2019.02.26
  • Published : 2019.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The Korean fertility rate has been declining rapidly since 2000 with the fertility rate among provinces following a uniform tendency. In particular, the province-specific fertility rate is an essential tool for local governments to prepare local policies for low fertility aging policy, education and welfare policies. However, there is limitation on how to reflect different trends on the province-specific fertility rate because the KOSTAT's (2017) province-specific fertility rate projection estimates information use the national average birth rate date of vital statistics for the last 10 years (5 years). In this study, we propose an improvement plan that simultaneously considers important stable pattern maintenance and provincial fertility rate differentiation for an annual birth rate estimation. The method proposed in this study (proposal 1 and 2) can reflect birth rate changes from past to present and national and provincial differences by age that use time series data of the annual fertility rate. Proposal 3 also reflects the unique fertility rate trend from the past to the present by age according to province regardless of the relationship with the national trend. Therefore, it is preferable to use a relationship to the national rate when predicting the birth rate, as in proposals 1 and 2 because the national and the provincial fertility rate pattern are similar. These proposals show improved stability in terms of age-specific fertility rates.

우리나라 출산율은 2000년 이후 빠르게 감소하고 있으며, 시도별 출산율도 대체적으로 동일한 추이를 나타내고 있다. 특히 시도별 출산율은 지방자치단체에서 저출산 고령화 대책, 교육 및 복지 등의 지역정책을 마련하기 위한 필수 자료이다. KOSTAT (2017) 시도별 출산율 추계 방법은 최근 10년(5년)간 전국 평균 출산율 정보를 이용하고 있으므로 이질적인 시도별 추이를 반영하는데 한계점이 있다. 따라서 본 연구에서는 시도별 출산율 추계에서 중요한 연도별 안정적 패턴 유지와 시도 출산율 차별성을 동시에 고려하는 개선방안을 제시하고자 한다. 본 연구에서 제안한 방법(제안 1, 2)는 연도별 출산율의 시계열 자료를 활용함으로써 연령별로 과거부터 현재까지의 출산율의 변동추이 및 전국과 시도의 차이를 반영할 수 있는 장점이 있다. 또한 제안3은 전국과의 관계는 고려하지 않고 시도의 연령별로 출산율의 과거부터 현재까지의 독자적 추이를 반영한다. 연구결과 우리나라의 경우 전국 출산율과 시도 출산율 패턴이 유사하므로 제안1, 2와 같이 시도 출산율 예측시 전국과의 관계를 이용하는 게 바람직하다 볼 수 있다. 이런 제안은 연령별 출산율 추이에 안정성을 개선시켰다.

Keywords

GCGHDE_2019_v32n2_229_f0001.png 이미지

Figure 2.1. Trend of total fertility rate (TFR).

GCGHDE_2019_v32n2_229_f0002.png 이미지

Figure 2.2. Trend on fertility rate of Seoul and Daegu by age.

GCGHDE_2019_v32n2_229_f0003.png 이미지

Figure 2.3. Trend on fertility rate of Jeonnam and Gyeongbuk by age.

GCGHDE_2019_v32n2_229_f0004.png 이미지

Figure 2.4. Trend of province-specific ASFR in the recent 10(5) years. ASFR = age specific fertility rate.

GCGHDE_2019_v32n2_229_f0005.png 이미지

Figure 2.5. Trend and projection of age specific fertility rate.

GCGHDE_2019_v32n2_229_f0006.png 이미지

Figure 2.6. Trend and projection of province-specific age specific fertility rate.

GCGHDE_2019_v32n2_229_f0007.png 이미지

Figure 2.7. Trend on fertility rate of Seoul and Daegu by age.

GCGHDE_2019_v32n2_229_f0008.png 이미지

Figure 2.8. Trend on fertility rate of Jeonnam and Gyeongbuk by age.

GCGHDE_2019_v32n2_229_f0009.png 이미지

Figure 3.4. (Proposal 2-1) Trend and projection of age specific fertility rate.

GCGHDE_2019_v32n2_229_f0010.png 이미지

Figure 3.17. Projection of TFR (up to 2045).

GCGHDE_2019_v32n2_229_f0017.png 이미지

Figure 3.1. (Proposal 1) Trends and projections of age specific fertility rate.

GCGHDE_2019_v32n2_229_f0018.png 이미지

Figure 3.2. (Proposal 1) Trend and projection on fertility rate of Seoul and Daegu by age.

GCGHDE_2019_v32n2_229_f0019.png 이미지

Figure 3.3. (Proposal 1) Trend and projection on fertility rate of Jeonnam and Gyeongbuk by age.

GCGHDE_2019_v32n2_229_f0020.png 이미지

Figure 3.5. (Proposal 2-2) Trend and projection of age specific fertility rate.

GCGHDE_2019_v32n2_229_f0021.png 이미지

Figure 3.6. (Proposal 2-3) Trend and projection of age specific fertility rate.

GCGHDE_2019_v32n2_229_f0022.png 이미지

Figure 3.7. (Proposal 2-4) Trend and projection of age specific fertility rate.

GCGHDE_2019_v32n2_229_f0023.png 이미지

Figure 3.8. (Proposal 2-1) Trend and projection on fertility rate of Seoul and Daegu by age.

GCGHDE_2019_v32n2_229_f0024.png 이미지

Figure 3.9. (Proposal 2-1) Trend and projection on fertility rate of Jeonnam and Gyeongbuk by age.

GCGHDE_2019_v32n2_229_f0025.png 이미지

Figure 3.10. (Proposal 3-ARIMA) Trend and projection of ASFR.

GCGHDE_2019_v32n2_229_f0026.png 이미지

Figure 3.11. (Proposal 3-ES) Trend and projection of ASFR.

GCGHDE_2019_v32n2_229_f0027.png 이미지

Figure 3.12. (Proposal 3-AR) Trend and projection of ASFR.

GCGHDE_2019_v32n2_229_f0028.png 이미지

Figure 3.13. (Proposal 3-FDM) Trend and projection of ASFR.

GCGHDE_2019_v32n2_229_f0029.png 이미지

Figure 3.14. (Proposal 3-Coherent FDM) Trend and projection of ASFR.

GCGHDE_2019_v32n2_229_f0030.png 이미지

Figure 3.15. (Proposal 3-ARIMA) Trend and projection on fertility rate of Seoul and Daegu by age.

GCGHDE_2019_v32n2_229_f0031.png 이미지

Figure 3.16. (Proposal 3-ARIMA) Trend and projection on fertility rate of Jeonnam and Gyeongbuk by age.

Table 3.1. Comparison of proposal methods on estimating province-specific fertility

GCGHDE_2019_v32n2_229_t0001.png 이미지

Table 3.2. MAFE on ASFR of Seoul (forecast period 2012–2016)

GCGHDE_2019_v32n2_229_t0002.png 이미지

Table 3.3. Index on jump off bias of Seoul (stability evaluation)

GCGHDE_2019_v32n2_229_t0003.png 이미지

References

  1. Choi, K. (2004). Causes of the recent fertility drop in Korea, Korean Journal of Population Studies, 27, 35-59.
  2. Eom, J. M. and Kim, K. W. (2013). A study on forecasting total fertility rate using female first marriage rate, Journal of the Korean Data Analysis Society, 15, 1261-1272.
  3. Eun, K. S. (2001). Age at marriage, marriage cohort and first birth interval, Korean Journal of Sociology, 35, 105-113.
  4. Greville, T. N. E. (1981). Moving-weighted-average smoothing extended to the extremities of the data. I. Theory, Scandinavian Actuarial Journal, 39-55.
  5. Kim, C. S. (2007). Parity specific approach to the plan of having an additional child, Korean Journal of Population Studies, 30, 97-116.
  6. Kim, S. Y. and Oh, J. H. (2017). A study comparisons of mortality projection using parametric and non-parametric model, The Korean Journal of Applied Statistics, 30, 701-717. https://doi.org/10.5351/KJAS.2017.30.5.701
  7. Kim, T. H., Lee, S. S. and Kim, D. H. (2006). Fertility differentials by demographic and socioeconomic characteristics: analysis of Korean population census data, Korean Journal of Population Studies, 29, 1-23.
  8. KOSTAT (2017). Population Projections for Provinces(2015-2045).
  9. Lee, R. D. and Carter, L. R. (1992). Modeling and forecasting U.S. mortality, Journal of the American Statistical Association, 87, 659-671. https://doi.org/10.2307/2290201
  10. Li, N. and Lee, R. (2005). Coherent mortality forecasts for a group of populations: an extension of the Lee-Carter method, Demography, 42, 575-594. https://doi.org/10.1353/dem.2005.0021
  11. Oh, J. H. (2014). A study on trend of the fertility model for population projections, Statistical Research Institute.
  12. Park, S. H. and Chun, D. W. (2004). Trends of child birth in older maternal age(1985-2003), Journal of Reproductive Medicine and Population, 17, 101-105.
  13. Park, Y. S., Kim, M. R., and Kim, S. Y. (2013). Probabilistic fertility models and the future population structure of Korea, Survey Research, 14, 49-78.
  14. Raftery, A. E., Chunn, J. L., Gerland, P., and Sevcikova, H. (2013). Bayesian probabilistic projections of life expectancy for all countries, Demography, 50, 777-801. https://doi.org/10.1007/s13524-012-0193-x
  15. Ramsay, J. O. and Silverman, B. W. (2005). Functional Data Analysis (2nd ed), Springer, New York.
  16. Statistics Canada (2015). Population Projections for Canada(2013 to 2063), Provinces and Territories: Technical Report on Methodology and Assumptions.
  17. Yoon, J. Y. and Kim, K. W. (2011). A comparison study for forecasting fertility rate by models and data type, Journal of the Korean Data Analysis Society, 13, 2901-2914.