Abstract
This chapter discusses a newly proposed method by the author for estimating small area demographics, and explains how to apply this method to long-term small area population projection. Since small area demographics are generally very unstable, various methods of estimating the true values of such data have been developed or considered, chiefly by statisticians and demographers. Most previous methods essentially perform data smoothing by using demographics from adjacent small areas. Empirical Bayes estimation is a representative smoothing method for small area demographics and has been widely applied to mortality. Although the theoretical precision of this method has already been proven, we should pay attention to the fact that there are a few disadvantages in applying it to population projection. In order to overcome those disadvantages, the author proposed a new estimation method of small area demographics in 2014, using the concept of population potential developed by Stewart in 1947. The new method consists of six formulas. This chapter examines the efficacy of the new method by applying two of those six formulas, and the empirical Bayes estimator, to actual mortality data, and then explains how to apply the new method to long-term population projection. A brief introduction of the original population projection system constructed on the internet using the new method is also included in the chapter. These discussions enable us to understand that the new method has the following advantages: first, it satisfactorily utilizes position or coordinate data of adjacent areas; second, the strength of its smoothing is adequate to the avoidance of yielding extraordinary values in projected population, especially in the case of long-term projection; and third, it does not require that in order for demographics to smooth they must follow the specific distribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This is called “small number problem” in spatial epidemiology (Haining et al. 2010).
- 2.
There are some studies that analyze geographical phenomena by using spatial filtering techniques different from taking simply moving averages. Please see, for example, Griffith (2003) for details.
- 3.
- 4.
When smoothing demographics by the method of type 3, that is, empirical Bayes estimation, we usually assume that the demographics follow Poisson distribution that shows the probability of very rare phenomenon. DARs and SMRs obviously follow Poisson distribution. As mentioned later, however, since CCRs indispensable for small area population projection cannot be considered as such probability, the smoothing of CCRs through type 3 requires close attention.
- 5.
The method of “median” based smoothing does not necessarily reflect demographics of an object area and cannot be considered as a desirable one, therefore this chapter excludes this method from discussion.
- 6.
The reason this variable takes the two different forms is that we must avoid division by zero in calculating the population potential of area i, whose distance from area i is naturally zero.
- 7.
Regarding the oldest age class, we must utilize the formula different slightly from equation [19]. Please see, for example, Smith et al. 2002 for details. If the fertility of women aged 15–19 and 40–49 shows a very low value as observed in Japan, it will be better to replace f i,t (15, 49) with f i,t (20, 39) in the calculation of CWRs.
- 8.
In this simulation, f i,t (20, 39) is used for the calculation of CWRs for the reason mentioned in footnote 7.
- 9.
This is the method of projecting population on the hypothesis that CCRs and CWRs of all small areas conform entirely to those of the municipality constituted by them.
- 10.
The author also described the brief manual for Japanese version of this system (Inoue 2016). This system is based on ArcGIS Online®, which is the Internet GIS system provided by Esri Corporation, so the interface and design of this website are changeable with updates of ArcGIS Online. In addition, please pay attention to possibility that the author may update its contents.
References
Anselin, L., Lozano, N., & Koschinsky, J. (2006). Rate transformations and smoothing. Spatial Analysis Laboratory, Department of Geography, University of Illinois, Urbana-Champaign.
Clayton, D., & Kaldor, J. (1987). Empirical Bayes estimates of age-standardized relative risks for use in disease mapping. Biometrics, 43(3), 671–681.
Datta, G., & Ghosh, M. (2012). Small area shrinkage estimation. Statistical Science, 27, 95–114.
Efron, B., & Morris, C. (1973). Stein’s estimation rule and its competitors: an empirical Bayes approach. Journal of the American Statistical Association, 68(341), 117–130.
Efron, B., & Morris, C. (1975). Data analysis using Stein’s estimator and its generalizations. Journal of the American Statistical Association, 70(350), 311–319.
Farrell, P. J., MacGibbon, B., & Tomberlin, T. J. (1997). Empirical Bayes estimators of small area proportions in multistage designs. Statistica Sinica, 7, 1065–1083.
Fay, R. E., & Herriot, R. A. (1979). Estimates of income for small places: An application of James-Stein procedures to census data. Journal of the American Statistical Association, 74(366), 269–277.
Ghosh, M., Kim, M. J., & Kim, D. H. (2008). Constrained Bayes and empirical Bayes estimation under random effects normal ANOVA model with balanced loss function. Journal of Statistical Planning and Inference, 138(7), 2017–2028.
Gonzalez, M. E., & Hoza, C. (1978). Small-area estimation with application to unemployment and housing estimates. Journal of the American Statistical Association, 73(361), 7–15.
Griffith, D. A. (2003). Spatial autocorrelation and spatial filtering: Gaining understanding through theory and scientific visualization. Berlin: Springer.
Haining, R. P., Kerry, R., & Oliver, M. A. (2010). Geography, spatial data analysis, and geostatistics: An overview. Geographical Analysis, 42(1), 7–31.
Hamilton, C. H., & Perry, J. (1962). A short method for projecting population by age from one decennial census to another. Social Forces, 41(2), 163–170.
Holt, D., Smith, T. M. F., & Tomberlin, T. J. (1979). A model-based approach to estimation for small subgroups of a population. Journal of the American Statistical Association, 74(366), 405–410.
Inoue, T. (2007). The concept of population potential and small area population statistics. Statistical Magazine, 58(12), 12–16. (in Japanese)
Inoue, T. (2014). A new method of estimating small area demographics using population potential. Working Paper Series, Institute of Economic Research, Aoyama Gakuin University 2014(3), 1–16.
Inoue, T. (2016). Development of the web system of small area population projection for whole Japan. Expertise in Statistics and Research for Leaders and Administrators (ESTRELA) 262, 2–9. (in Japanese)
Kubokawa, T. (2013a). Constrained empirical Bayes estimator and its uncertainty in normal linear mixed models. Journal of Multivariate Analysis 122, 377–392.
Kubokawa, T. (2013b). The benchmark problem on small area estimation and error estimate of constrained empirical Bayes estimation. CIRJE Research Report Series, CIRJE-R-12, 143–165. (in Japanese)
Laake, P. (1979). A predictive approach to subdomain estimation in finite populations. Journal of the American Statistical Association, 74(366), 355–358.
Louis, T. A. (1984). Estimating a population of parameter values using Bayes and empirical Bayes methods. Journal of the American Statistical Association, 79(386), 393–398.
MacGibbon, B., & Tomberlin, T. J. (1989). Small area estimates of proportions via empirical Bayes techniques. Survey Methodology, 15, 237–252.
Maritz, J. S. (1969). Empirical Bayes estimation for the Poisson distribution. Biometrika, 56(2), 349–359.
Marshall, R. J. (1991). Mapping disease and mortality rates using empirical Bayes estimators. Applied Statistics, 40(2), 283–294.
Mfungahema, R., & Kitamura, T. (1997). The significance of population potential at the local level and in rural areas: A case of Okayama and Tottori prefectures in Japan. Journal of Rural Planning Association, 16(3), 251–262.
Morris, C. N. (1983). Parametric empirical Bayes inference: Theory and applications. Journal of the American Statistical Association, 78(381), 47–55.
Mosteller, F., & Tukey, J. W. (1977). Data analysis and regression: A second course in statistics. Boston: Addison-Wesley.
Rich, D. C. (1980). Potential models in human geography: Concepts and techniques in modern geography, volume 26 of concepts and techniques in modern geography (Study Group in Quantitative Methods). Institute of British Geographers, University of East Anglia, Norwich: GeoBooks.
Shinozaki, N. (1991). Stein-type shrinkage estimators and their applications. Japanese Journal of Applied Statistics, 20(2), 59–76. (in Japanese)
Smith, S. K., Tayman, J., & Swanson, D. A. (2002). State and local population projections: Methodology and analysis. New York: Kluwer.
Smith, S. K., Tayman, J., & Swanson, D. A. (2013). A practitioner’s guide to state and local population projections. Dordrecht: Springer.
Stewart, J. Q. (1947). Empirical mathematical rules concerning the distribution and equilibrium of population. Geographical Review, 37(3), 461–485.
Swanson, D. A., & Tayman, J. (2012). Subnational population estimates. Dordrecht: Springer.
Swanson, D. A., Schlottmann, A., & Schmidt, B. (2010). Forecasting the population of census tracts by age and sex: An example of the Hamilton-Perry method in action. Population Research and Policy Review, 29(1), 47–63.
Tango, T. (1988). Empirical Bayes estimation for mortality indices: Applications to disease mapping. Japanese Journal of Applied Statistics, 17(2), 81–96. (in Japanese)
Tocalis, T. R. (1978). Changing theoretical foundations of the gravity concept of human interactions. In B. J. L. Berry (Ed.), Perspectives in geography 3: The nature of change in geographical ideas (pp. 67–124). DeKalb: Northern Illinois University Press.
Tsutakawa, R. K., Shoop, G. L., & Marienfeld, C. J. (1985). Empirical Bayes estimation of cancer mortality rates. Statistics in Medicine, 4(2), 201–212.
Waller, L. A., & Gotway, C. A. (2004). Applied spatial statistics for public health data. New York: Wiley.
Warntz, W. (1964). A new map of the surface of population potentials for the United States, 1960. Geographical Review, 54(2), 170–184.
Acknowledgements
This chapter is a result of a study that received financial support from the Japan Society for the Promotion of Science by grant-in-aid (grant number: 25370919 and 16H03525). The author deeply appreciates the assistance of Mr. Atsushi Kajimoto (Esri Japan Corporation) for constructing the online system “The Web System of Small Area Population Projection for the Whole Japan.”
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Inoue, T. (2017). A New Method for Estimating Small Area Demographics and Its Application to Long-Term Population Projection. In: Swanson, D. (eds) The Frontiers of Applied Demography. Applied Demography Series, vol 9. Springer, Cham. https://doi.org/10.1007/978-3-319-43329-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-43329-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-43327-1
Online ISBN: 978-3-319-43329-5
eBook Packages: Social SciencesSocial Sciences (R0)