學術產出-Theses
Article View/Open
Publication Export
-
題名 年輪變動比與小區域人口推估
A Study of Cohort Change Ratio and Small Area Population Projection作者 陳譽騰
Chen, Yu-Teng貢獻者 洪英超<br>余清祥
Hung, Ying-Chao<br>Yue, Ching-Syang
陳譽騰
Chen, Yu-Teng關鍵詞 小區域人口推估
年輪變動比
區塊拔靴法
遷移
回測法
Sub-national Population Projection
Cohort Change Ratio
Block Bootstrap
Migration
Backcast日期 2020 上傳時間 3-Aug-2020 17:32:45 (UTC+8) 摘要 人是國家組成的最重要元素，其數量及素質是國家競爭力的關鍵，提升人口數量及人力素質更是國家發展的核心議題。人口推估常用於制訂國家發展方針的依據，根據歷史數據及政策方向等假設，預測全國各地的人口總數及年齡結構，政府可根據推估結果制訂政策及分配資源。人口老化是臺灣在21世紀必須面對的挑戰，除了我國老化速度高於西方各國，各縣市的需求和問題也非常不同，若能瞭解各地未來的人口及結構，便能制定合乎地方特色的發展方針，減輕人口轉型帶來的衝擊。年輪組成法為我國官方目前用於全國人口的推估方法，但使用時對於生育、死亡、遷移等人口資料有較高要求，很難直接套用至縣市層級及以下之人口推估，近年學者建議小區域推估採用Hamilton and Perry（簡稱HP法）的年輪變動比（Cohort Change Ratio；簡稱CCR）。本文評估HP法用於小區域人口推估的可行性，以臺灣的各級行政區域為研究目標，驗證HP法是否能用於推估臺灣縣市、鄉鎮市區層級的人口及結構。本研究使用1975～2019年臺灣全國、縣市、鄉鎮市區層級的人口紀錄，透過區塊拔靴法與歷年平均法各兩種加權方式估計CCR，並運用回測法評估四種方法的MAPE誤差。研究發現HP法可用於小區域人口，15年之內短期推估與年齡組成法相當，但推估誤差未必隨著人口數減少而增加。另外，推估時建議採用單齡推估（五齡組誤差較大），區塊拔靴法及加權平均的效果接近，基底年數與地區特性有關，推估年數建議不超過15年。
People are the most important element of a country. Population policy is essential to national development and population projection is often used to provide insightful suggestions for planning government policies and allocating public resources. Ageing and migration are expected to the most significant factors in influencing the population size and age structure in the 21st century. However, the pace of population ageing in Taiwan is much faster than in developed countries and the migration pattern is very different in Asia as well. Since the demographic transition of countries varies a lot, the population projection method and assumption usually depend on each country’s population characteristics.The cohort component method is currently used in projecting the national level population in Taiwan, but this method requires detailed population data, such as the records of births, deaths, and migration. It is difficult to acquire these data in county and township level and we need to seek an alternative method for the sub-national population projection. In this study, we evaluate whether the Cohort Change Ratio (CCR), proposed by Hamilton and Perry, is suitable for the sub-national population projection via backcasting the historical data in Taiwan (1975-2019). In specific, we are interested in compare the projecting accuracy of CCR and cohort component methods, and we found that the CCR method can be used for short-term projection (e.g., 15 years or less) for county and township levels. Also, we projection errors are smaller using the single-age data, and there are little differences in using block bootstrap or weighted average to predict the future CCR.參考文獻 中文部分1. 王信忠與余清祥（2011），「規律折扣數列與高齡死亡率」，《人口學刊》，43，37-70。2. 王信忠、金碩、余清祥（2012），「小區域死亡率推估之研究」，《人口學刊》，45，121-154。3. 何正羽（2006），「高齡人口Gompertz死亡率推估模型的建構與應用」，東吳大學商用數學系碩士論文。4. 余清祥、簡于閔、梁穎誼（2020），「健保資料與抽樣調查」，《調查研究－方法與應用》，44，97-130。5. 吳欣蓉（2017），「都會區大眾捷運路網對於鄰近房價之影響－以桃園機場捷運、臺中捷運綠線為例」，國立中央大學產業經濟研究所碩士論文。6. 林佩柔（2019），「由全民健保資料庫探討就醫習性與人口移動的關聯」，國立政治大學統計學系碩士論文。7. 郭孟坤與余清祥（2008），「電腦模擬、隨機方法與人口推估的實證研究」，《人口學刊》，36，67-98。8. 陳政勳與余清祥（2010），「小區域人口推估研究：臺北市、雲嘉兩縣、澎湖縣的實證分析」，《人口學刊》， 41，153-183.。9. 曹郁欣（2013），「小區域生育率與人口推計研究」，國立政治大學統計學系碩士論文。二、英文部分1. Alho, J.M. and Spencer, B.D. (2006), Statistical Demography and Forecasting, Springer.2. Bühlmann, P. (2002), “Bootstraps for Time Series”, Statistical Science, 17(1), 52-72.3. Cannan, E. (1985), “The Probability of a Cessation of the Growth of Population in England and Wales during the Next Century”, The Economic Journal, 5(20), 505-515.4. Denton, F.T., Feaver, C.H., Spencer, B.D. (2005), “Time Series Analysis and Stochastic Forecasting：An Econometric Study of Mortality and Life Expectancy”, Journal of Population Economics, 18(2), 203-227.5. Efron, B. (1979), “Bootstrap Methods：Another Look at the Jackknife”, The annals of statistics, 7(1), 1-26.6. Hall, P. (1985), “Resampling a Coverage Pattern”, Stochastic Processes and their Applications, 20(2), 231-246.7. Hamilton, C. and Perry, J. (1962), “A Short Method for Projecting Population by Age from one Decennial Census to Another”, Social Forces, vol. 41, 163-170.8. Lee, R.D. and Carter, L.R. (1992), “Modeling and Forecasting US Mortality”, Journal of the American Statistical Association, 87(419), 659-671.9. Lewis, E.B. (1982), “Control of Body Segment Differentiation in Drosophila by the Bithorax Gene Complex”, Embryonic Development, vol.1, 269-288.10. Politis, D.N. and Romano, J.P. (1994), “The Stationary Bootstrap”, Journal of the American Statistical Association, 89(428), 1303-1313.11. Smith, S.K. and Tayman, J. (2003), “A Evaluation of Population Projections by Age”, Demography, vol.40(4), 741-757.12. Swanson, D.A. and Tayman, J. (2017), “A Long Term Test of the Accuracy of the Hamilton-Perry Method for Forecasting State Populations by Age” in The Frontiers of Applied Demography, edited by D.A. Swanson, Cham：Springer.13. Whelpton, PK (1928), “Population of the United States, 1928 to 1975”, American Journal of Sociology, 253-270. 描述 碩士
國立政治大學
統計學系
107354028資料來源 http://thesis.lib.nccu.edu.tw/record/#G0107354028 資料類型 thesis dc.contributor.advisor 洪英超<br>余清祥 zh_TW dc.contributor.advisor Hung, Ying-Chao<br>Yue, Ching-Syang en_US dc.contributor.author (Authors) 陳譽騰 zh_TW dc.contributor.author (Authors) Chen, Yu-Teng en_US dc.creator (作者) 陳譽騰 zh_TW dc.creator (作者) Chen, Yu-Teng en_US dc.date (日期) 2020 en_US dc.date.accessioned 3-Aug-2020 17:32:45 (UTC+8) - dc.date.available 3-Aug-2020 17:32:45 (UTC+8) - dc.date.issued (上傳時間) 3-Aug-2020 17:32:45 (UTC+8) - dc.identifier (Other Identifiers) G0107354028 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/130963 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 統計學系 zh_TW dc.description (描述) 107354028 zh_TW dc.description.abstract (摘要) 人是國家組成的最重要元素，其數量及素質是國家競爭力的關鍵，提升人口數量及人力素質更是國家發展的核心議題。人口推估常用於制訂國家發展方針的依據，根據歷史數據及政策方向等假設，預測全國各地的人口總數及年齡結構，政府可根據推估結果制訂政策及分配資源。人口老化是臺灣在21世紀必須面對的挑戰，除了我國老化速度高於西方各國，各縣市的需求和問題也非常不同，若能瞭解各地未來的人口及結構，便能制定合乎地方特色的發展方針，減輕人口轉型帶來的衝擊。年輪組成法為我國官方目前用於全國人口的推估方法，但使用時對於生育、死亡、遷移等人口資料有較高要求，很難直接套用至縣市層級及以下之人口推估，近年學者建議小區域推估採用Hamilton and Perry（簡稱HP法）的年輪變動比（Cohort Change Ratio；簡稱CCR）。本文評估HP法用於小區域人口推估的可行性，以臺灣的各級行政區域為研究目標，驗證HP法是否能用於推估臺灣縣市、鄉鎮市區層級的人口及結構。本研究使用1975～2019年臺灣全國、縣市、鄉鎮市區層級的人口紀錄，透過區塊拔靴法與歷年平均法各兩種加權方式估計CCR，並運用回測法評估四種方法的MAPE誤差。研究發現HP法可用於小區域人口，15年之內短期推估與年齡組成法相當，但推估誤差未必隨著人口數減少而增加。另外，推估時建議採用單齡推估（五齡組誤差較大），區塊拔靴法及加權平均的效果接近，基底年數與地區特性有關，推估年數建議不超過15年。 zh_TW dc.description.abstract (摘要) People are the most important element of a country. Population policy is essential to national development and population projection is often used to provide insightful suggestions for planning government policies and allocating public resources. Ageing and migration are expected to the most significant factors in influencing the population size and age structure in the 21st century. However, the pace of population ageing in Taiwan is much faster than in developed countries and the migration pattern is very different in Asia as well. Since the demographic transition of countries varies a lot, the population projection method and assumption usually depend on each country’s population characteristics.The cohort component method is currently used in projecting the national level population in Taiwan, but this method requires detailed population data, such as the records of births, deaths, and migration. It is difficult to acquire these data in county and township level and we need to seek an alternative method for the sub-national population projection. In this study, we evaluate whether the Cohort Change Ratio (CCR), proposed by Hamilton and Perry, is suitable for the sub-national population projection via backcasting the historical data in Taiwan (1975-2019). In specific, we are interested in compare the projecting accuracy of CCR and cohort component methods, and we found that the CCR method can be used for short-term projection (e.g., 15 years or less) for county and township levels. Also, we projection errors are smaller using the single-age data, and there are little differences in using block bootstrap or weighted average to predict the future CCR. en_US dc.description.tableofcontents 第壹章、 緒論 1第一節、 研究動機及背景 1第二節、 研究目的 3第貳章、 文獻探討與研究方法 5第一節、 年輪組成法 5第二節、 HAMILTON AND PERRY METHOD 7第三節、 區塊拔靴法 9第四節、 研究方法與過程 11第參章、 資料介紹與探索性資料分析 19第一節、 資料介紹與檢查 19第二節、 年輪變動比 24第三節、 生育、死亡、遷移 27第肆章、 電腦模擬與實證分析比較 39第一節、 臺灣與縣市的人口推估 39第二節、 HP法與年輪組成法的比較 41第三節、 小區域人口推估的建議 44第四節、 鄉鎮市區人口推估 54第五節、 實證比較 60第伍章、 結論與建議 64第一節、 結論 64第二節、 後續研究之建議 65參考文獻 67 zh_TW dc.format.extent 3903994 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0107354028 en_US dc.subject (關鍵詞) 小區域人口推估 zh_TW dc.subject (關鍵詞) 年輪變動比 zh_TW dc.subject (關鍵詞) 區塊拔靴法 zh_TW dc.subject (關鍵詞) 遷移 zh_TW dc.subject (關鍵詞) 回測法 zh_TW dc.subject (關鍵詞) Sub-national Population Projection en_US dc.subject (關鍵詞) Cohort Change Ratio en_US dc.subject (關鍵詞) Block Bootstrap en_US dc.subject (關鍵詞) Migration en_US dc.subject (關鍵詞) Backcast en_US dc.title (題名) 年輪變動比與小區域人口推估 zh_TW dc.title (題名) A Study of Cohort Change Ratio and Small Area Population Projection en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 中文部分1. 王信忠與余清祥（2011），「規律折扣數列與高齡死亡率」，《人口學刊》，43，37-70。2. 王信忠、金碩、余清祥（2012），「小區域死亡率推估之研究」，《人口學刊》，45，121-154。3. 何正羽（2006），「高齡人口Gompertz死亡率推估模型的建構與應用」，東吳大學商用數學系碩士論文。4. 余清祥、簡于閔、梁穎誼（2020），「健保資料與抽樣調查」，《調查研究－方法與應用》，44，97-130。5. 吳欣蓉（2017），「都會區大眾捷運路網對於鄰近房價之影響－以桃園機場捷運、臺中捷運綠線為例」，國立中央大學產業經濟研究所碩士論文。6. 林佩柔（2019），「由全民健保資料庫探討就醫習性與人口移動的關聯」，國立政治大學統計學系碩士論文。7. 郭孟坤與余清祥（2008），「電腦模擬、隨機方法與人口推估的實證研究」，《人口學刊》，36，67-98。8. 陳政勳與余清祥（2010），「小區域人口推估研究：臺北市、雲嘉兩縣、澎湖縣的實證分析」，《人口學刊》， 41，153-183.。9. 曹郁欣（2013），「小區域生育率與人口推計研究」，國立政治大學統計學系碩士論文。二、英文部分1. Alho, J.M. and Spencer, B.D. (2006), Statistical Demography and Forecasting, Springer.2. Bühlmann, P. (2002), “Bootstraps for Time Series”, Statistical Science, 17(1), 52-72.3. Cannan, E. (1985), “The Probability of a Cessation of the Growth of Population in England and Wales during the Next Century”, The Economic Journal, 5(20), 505-515.4. Denton, F.T., Feaver, C.H., Spencer, B.D. (2005), “Time Series Analysis and Stochastic Forecasting：An Econometric Study of Mortality and Life Expectancy”, Journal of Population Economics, 18(2), 203-227.5. Efron, B. (1979), “Bootstrap Methods：Another Look at the Jackknife”, The annals of statistics, 7(1), 1-26.6. Hall, P. (1985), “Resampling a Coverage Pattern”, Stochastic Processes and their Applications, 20(2), 231-246.7. Hamilton, C. and Perry, J. (1962), “A Short Method for Projecting Population by Age from one Decennial Census to Another”, Social Forces, vol. 41, 163-170.8. Lee, R.D. and Carter, L.R. (1992), “Modeling and Forecasting US Mortality”, Journal of the American Statistical Association, 87(419), 659-671.9. Lewis, E.B. (1982), “Control of Body Segment Differentiation in Drosophila by the Bithorax Gene Complex”, Embryonic Development, vol.1, 269-288.10. Politis, D.N. and Romano, J.P. (1994), “The Stationary Bootstrap”, Journal of the American Statistical Association, 89(428), 1303-1313.11. Smith, S.K. and Tayman, J. (2003), “A Evaluation of Population Projections by Age”, Demography, vol.40(4), 741-757.12. Swanson, D.A. and Tayman, J. (2017), “A Long Term Test of the Accuracy of the Hamilton-Perry Method for Forecasting State Populations by Age” in The Frontiers of Applied Demography, edited by D.A. Swanson, Cham：Springer.13. Whelpton, PK (1928), “Population of the United States, 1928 to 1975”, American Journal of Sociology, 253-270. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202001106 en_US
