Publications-Theses

題名 台灣地區自殺企圖者之重複自殺企圖次數統計模型探討
作者 王文華
貢獻者 江振東
王文華
關鍵詞 自殺企圖
自殺率
卜瓦松分配
廣義卜瓦松分配
Zero-inflated分配
Suicide attempt
Suicide rate
Poisson distribution
Generalized Poisson distribution
Zero-inflated distribution
日期 2008
上傳時間 8-Dec-2010 14:48:46 (UTC+8)
摘要 世界衛生組織表示「先前有過自殺行為的人,再度自殺的機率比一般人高」,因此如何針對自殺企圖者提供即時的關懷與介入服務,是世界各國重要的自殺防治策略之一。本研究希望針對曾有過自殺企圖的個案,經由統計模型的配適來找出自殺企圖個案的「自殺危險因子」,區別出再度自殺的高危險個案,以方便將人力及醫療資源投入到最需要被協助的個案上。
本研究的反應變項為「重複自殺企圖次數」,但是由於資料中「零值」的人數相當多,此外也呈現出變異數大於平均數的現象,因此我們採用可以同時處理Zero-inflated及Over-dispersion情況的廣義Zero-inflated卜瓦松迴歸模型 (Generalized Zero-inflated Poisson Regression Model)來進行資料的配適。我們得知重複自殺企圖之高風險因子有「65歲以上」、「曾患有精神疾病」、「不確定是否曾患有精神疾病」及「離婚」之個案,而「治癒」可能性較高的因子為「45~64歲」、「因情感因素自殺」、「已婚」之個案。藉由模型也可以進一步估計自殺企圖個案之再企圖機率,並且對自殺企圖個案進行分層,以進行不同程度的關懷與訪視,藉以提昇關懷的即時性及有效性。
World Health Organization (WHO) has indicated that suicide attempt rate is much higher among those who have ever had suicide attempts. Hence, how to express concerns and provide timely consultations for suicide reattempters has become one of the key issues in suicide prevention. In this study, we try to identify the risk factors associated with suicide reattempters, and predict high-risk cases so that the limited resources can be distributed effectively.
The primary variable of interest is the number of repeated suicide attempt for a suicide attempter after his/her index attempt. However, there are more zeros and greater variability in the data than that would be predicted by a Poisson model. We hence fit the data using a zero-inflated generalized Poisson regression model, a model that is frequently used for modeling over-dispersed count data with too many zeros. We find that the risk factors for repeated suicide attempts are those who are 65 or older, those who are classified as psychiatric disorders and those diagnostically uncertain cases, and those who are divorced. We also find that non-repeaters are more likely among those who are between 45 to 65 of age, married, and having a suicide attempt history due to an emotional reason. Through the use of the model, we can also estimate a subject’s reattempt probability, classify them, and provide them with suitable care and attention accordingly.
參考文獻 行政院經濟建設委員會網站,http://www.cepd.gov.tw/。
行政院衛生署 自殺防治中心網站,http://www.tspc.doh.gov.tw/tspc/portal/index/。
法鼓山人文社會基金會【你可以不必自殺】網站,http://www.no-suicide-no.com/。
財團法人董氏基金會【自殺防治網】,http://www.jtf.org.tw/suicide_prevention/。
Böhning, D. (1998) “ Zero-Inflated Poisson Models and C.A.MAN: A Tutorial Collection of Evidence, ” Biometrical Journal, 7: 833-843.
Cameron, A. C. , and Trivedi P. K. (2005) icroeconometrics: methods and applications, Cambridge University Press.
Consul , P. C. (1989) Generalized Poisson distribution, Marcel Dekker, Inc.
Consul, P.C. ,and Jain, G.C. (1970) “ On the eneralization of Poisson distribution,”Annals of Mathematical tatistics, 41:1387.
Cox, D. R. (1983) “ Some remarks on over-dispersion,” Biometrika, 70: 269-274.
Czado, C. , Erhardt, V. , Min, A. ,and Wagner, S. (2007)
“ Zero-inflated generalized Poisson models with regression effects on the mean, dispersion and zero-inflation level applied to patent outsourcing rates,” Statistical Modelling, 7:125-153.
Deng, D. , and Paul, S. R. (2005) “ Score tests for zero-inflation and over-dispersion in generalized linear models,” Statistica Sinica, 15: 257-276.
Famoye, F. , and Singh, K.P. (2003) “ On inflated generalized Poisson regression models,” Advances and Applications in Statistics, 3: 145–58.
Famoye, F. , and Wang, W. (2004) “ Censored Generalized Poisson Regression Model,” Computational Statistics & Data Analysis, 46: 547-560.
Famoye, F. , and Wulu, J. T. , Jr. , and Singh, K. P. (2004) “ On the generalized Poisson regression model with an application to accident data,” Journal of Data Science, 2:287-295.
Gupta, P. L. , Gupta, R. C. , and Tripathi, R. C. (1996) “ Analysis of zero-adjusted count data, “ Computational Statistics & Data Analysis, 23: 207-218.
Jessen, G. , Jensen, B. F. , Arensman, E. , Bille-Brahe, U. , Crepet P. , De Leo, D., Hawton, K. , Haring, C. , Hjelmeland, H. , Michel, K. , Ostamo, A. ,
Salander- Renberg, E. , Schmidtke, A. , Temesvary, B. , and Wasserman, D. (1999) “ Attempted suicide and major public holidays in Europe: finding from the WHO/ EURO Multicentre Study on Parasuicide,” Acta Psychiatr Scand, 99: 412-418.
Lambert, D. (1992) “ Zero-inflated Poisson regression, with an application to defects in manufacturing,” Technometrics, 34:1-14.
Morrell, S. , Taylor, R. , Slaytor, E. , and Ford, P. (1999) “ Urban and rural suicide differentials in migrants and the Australian-born, New South Wales, Australia 1985-1994,” Social Science & Medicine, 49: 81-91.
Mullahy, J. (1986) “ Specification and testing of some modified count data models,” Journal of Econometrics, 33: 341-365.
Pirkis, J. , Burgess, P. , and Jolley, D. (1999) “ Suicide attempts by psychiatric patients in acute inpatient, long-stay inpatient and community care,” Soc Psychiatry Psychiatr Epidemiol, 34: 634-644.
World Health Organization (WHO) website, http://www.who.int/en/.
Zeileis, A. , Kleiber, C. , and Jackman, S. (2008)
“ Regression Models for Count Data in R,” Journal of Statistical Software, 27.
描述 碩士
國立政治大學
統計研究所
96354001
97
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0096354001
資料類型 thesis
dc.contributor.advisor 江振東zh_TW
dc.contributor.author (Authors) 王文華zh_TW
dc.creator (作者) 王文華zh_TW
dc.date (日期) 2008en_US
dc.date.accessioned 8-Dec-2010 14:48:46 (UTC+8)-
dc.date.available 8-Dec-2010 14:48:46 (UTC+8)-
dc.date.issued (上傳時間) 8-Dec-2010 14:48:46 (UTC+8)-
dc.identifier (Other Identifiers) G0096354001en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/49596-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 統計研究所zh_TW
dc.description (描述) 96354001zh_TW
dc.description (描述) 97zh_TW
dc.description.abstract (摘要) 世界衛生組織表示「先前有過自殺行為的人,再度自殺的機率比一般人高」,因此如何針對自殺企圖者提供即時的關懷與介入服務,是世界各國重要的自殺防治策略之一。本研究希望針對曾有過自殺企圖的個案,經由統計模型的配適來找出自殺企圖個案的「自殺危險因子」,區別出再度自殺的高危險個案,以方便將人力及醫療資源投入到最需要被協助的個案上。
本研究的反應變項為「重複自殺企圖次數」,但是由於資料中「零值」的人數相當多,此外也呈現出變異數大於平均數的現象,因此我們採用可以同時處理Zero-inflated及Over-dispersion情況的廣義Zero-inflated卜瓦松迴歸模型 (Generalized Zero-inflated Poisson Regression Model)來進行資料的配適。我們得知重複自殺企圖之高風險因子有「65歲以上」、「曾患有精神疾病」、「不確定是否曾患有精神疾病」及「離婚」之個案,而「治癒」可能性較高的因子為「45~64歲」、「因情感因素自殺」、「已婚」之個案。藉由模型也可以進一步估計自殺企圖個案之再企圖機率,並且對自殺企圖個案進行分層,以進行不同程度的關懷與訪視,藉以提昇關懷的即時性及有效性。
zh_TW
dc.description.abstract (摘要) World Health Organization (WHO) has indicated that suicide attempt rate is much higher among those who have ever had suicide attempts. Hence, how to express concerns and provide timely consultations for suicide reattempters has become one of the key issues in suicide prevention. In this study, we try to identify the risk factors associated with suicide reattempters, and predict high-risk cases so that the limited resources can be distributed effectively.
The primary variable of interest is the number of repeated suicide attempt for a suicide attempter after his/her index attempt. However, there are more zeros and greater variability in the data than that would be predicted by a Poisson model. We hence fit the data using a zero-inflated generalized Poisson regression model, a model that is frequently used for modeling over-dispersed count data with too many zeros. We find that the risk factors for repeated suicide attempts are those who are 65 or older, those who are classified as psychiatric disorders and those diagnostically uncertain cases, and those who are divorced. We also find that non-repeaters are more likely among those who are between 45 to 65 of age, married, and having a suicide attempt history due to an emotional reason. Through the use of the model, we can also estimate a subject’s reattempt probability, classify them, and provide them with suitable care and attention accordingly.
en_US
dc.description.tableofcontents 第一章 緒論 1
第一節 研究背景與動機 1
第二節 名詞定義 4
第三節 問題定義 5
第四節 研究目的 6
第五節 論文結構 7
第二章 理論架構與分析模型 8
第一節 基準分配 8
2.1.1 卜瓦松分配 8
2.1.2 廣義卜瓦松分配 9
第二節 Zero-inflated分配 11
2.2.1 Zero-Inflated 卜瓦松分配 12
2.2.2 Zero-inflated 廣義卜瓦松分配 14
第三節 迴歸模型介紹 15
2.3.1 卜瓦松迴歸模型 16
2.3.2 廣義卜瓦松迴歸模型 16
2.3.3 Zero-inflated卜瓦松迴歸模型 17
2.3.4 Zero-inflated廣義卜瓦松迴歸模型 18
第四節 迴歸模型在自殺防治上的應用 19
第三章 資料來源與模型架構 21
第一節 資料來源 21
3.1.1 資料介紹 21
3.1.2 通報關懷系統與相關系統之串連 21
第二節 資料基本分析 22
3.2.1 資料整理狀況 22
3.2.2 變項定義及說明 23
第三節 模型配適架構 26
3.3.1 資料說明與分析假設 26
3.3.2 模型配適之反應變項說明 26
3.3.3 模型配適之解釋變項說明 28
3.3.4 模型配適說明 29
第四節 模型比較方法介紹 30
3.4.1 比較步驟 30
3.4.2 Goodness-of-fit準則及檢定方法選擇 30
第四章 資料分析結果與討論 32
第一節 迴歸模型配適結果 32
4.1.1 Zero-inflated廣義卜瓦松迴歸模型分析結果 32
4.1.2 卜瓦松迴歸模型分析結果 36
4.1.3 廣義卜瓦松迴歸模型分析結果 37
4.1.4 Zero-inflated卜瓦松迴歸模型分析結果 39
4.1.5 模型配適小結 41
第二節 概似比檢定之結果 42
第五章 研究結論與建議 43
第一節 研究結論 43
第二節 研究限制 43
第三節 未來研究方向 44
參考文獻 47
中文部分 47
英文部分 47
附錄 49
附錄A 不同參數值下之機率密度函數圖形 49
附錄A-1 卜瓦松分配機率密度函數圖形 49
附錄A-2 廣義卜瓦松分配機率密度函數圖形 50
附錄A-3 Zero-Inflated卜瓦松分配機率密度函數圖形 51
附錄A-4 Zero-Inflated廣義卜瓦松分配機率密度函數圖形 52
附錄B 分配之期望值及變異數公式推導 54
附錄B-1 廣義卜瓦松分配之期望值及變異數推導 54
附錄B-2 Zero-Inflated 卜瓦松分配期望值及變異數推導 56
附錄B-3 Zero-Inflated 廣義卜瓦松分配期望值及變異數推導 57
附錄C 配適迴歸模型所使用之R程式碼 59
附錄C-1 配適卜瓦松迴歸模型之程式碼 59
附錄C-2 配適廣義卜瓦松迴歸模型之程式碼 59
附錄C-3 配適Zero-inflated卜瓦松迴歸模型之程式碼 59
附錄C-4 配適Zero-inflated廣義卜瓦松迴歸模型之程式碼 59
附錄D 未來研究方向之初步分析結果 61
附錄D-1 「首次自殺企圖即死亡」個案之敘述性統計分析 61
附錄D-2 「接受訪視」個案之ZIGP模型配適 67
zh_TW
dc.format.extent 228976 bytes-
dc.format.extent 271477 bytes-
dc.format.extent 302020 bytes-
dc.format.extent 306844 bytes-
dc.format.extent 377248 bytes-
dc.format.extent 379470 bytes-
dc.format.extent 380610 bytes-
dc.format.extent 343659 bytes-
dc.format.extent 353975 bytes-
dc.format.extent 296201 bytes-
dc.format.extent 435631 bytes-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0096354001en_US
dc.subject (關鍵詞) 自殺企圖zh_TW
dc.subject (關鍵詞) 自殺率zh_TW
dc.subject (關鍵詞) 卜瓦松分配zh_TW
dc.subject (關鍵詞) 廣義卜瓦松分配zh_TW
dc.subject (關鍵詞) Zero-inflated分配zh_TW
dc.subject (關鍵詞) Suicide attempten_US
dc.subject (關鍵詞) Suicide rateen_US
dc.subject (關鍵詞) Poisson distributionen_US
dc.subject (關鍵詞) Generalized Poisson distributionen_US
dc.subject (關鍵詞) Zero-inflated distributionen_US
dc.title (題名) 台灣地區自殺企圖者之重複自殺企圖次數統計模型探討zh_TW
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) 行政院經濟建設委員會網站,http://www.cepd.gov.tw/。zh_TW
dc.relation.reference (參考文獻) 行政院衛生署 自殺防治中心網站,http://www.tspc.doh.gov.tw/tspc/portal/index/。zh_TW
dc.relation.reference (參考文獻) 法鼓山人文社會基金會【你可以不必自殺】網站,http://www.no-suicide-no.com/。zh_TW
dc.relation.reference (參考文獻) 財團法人董氏基金會【自殺防治網】,http://www.jtf.org.tw/suicide_prevention/。zh_TW
dc.relation.reference (參考文獻) Böhning, D. (1998) “ Zero-Inflated Poisson Models and C.A.MAN: A Tutorial Collection of Evidence, ” Biometrical Journal, 7: 833-843.zh_TW
dc.relation.reference (參考文獻) Cameron, A. C. , and Trivedi P. K. (2005) icroeconometrics: methods and applications, Cambridge University Press.zh_TW
dc.relation.reference (參考文獻) Consul , P. C. (1989) Generalized Poisson distribution, Marcel Dekker, Inc.zh_TW
dc.relation.reference (參考文獻) Consul, P.C. ,and Jain, G.C. (1970) “ On the eneralization of Poisson distribution,”Annals of Mathematical tatistics, 41:1387.zh_TW
dc.relation.reference (參考文獻) Cox, D. R. (1983) “ Some remarks on over-dispersion,” Biometrika, 70: 269-274.zh_TW
dc.relation.reference (參考文獻) Czado, C. , Erhardt, V. , Min, A. ,and Wagner, S. (2007)zh_TW
dc.relation.reference (參考文獻) “ Zero-inflated generalized Poisson models with regression effects on the mean, dispersion and zero-inflation level applied to patent outsourcing rates,” Statistical Modelling, 7:125-153.zh_TW
dc.relation.reference (參考文獻) Deng, D. , and Paul, S. R. (2005) “ Score tests for zero-inflation and over-dispersion in generalized linear models,” Statistica Sinica, 15: 257-276.zh_TW
dc.relation.reference (參考文獻) Famoye, F. , and Singh, K.P. (2003) “ On inflated generalized Poisson regression models,” Advances and Applications in Statistics, 3: 145–58.zh_TW
dc.relation.reference (參考文獻) Famoye, F. , and Wang, W. (2004) “ Censored Generalized Poisson Regression Model,” Computational Statistics & Data Analysis, 46: 547-560.zh_TW
dc.relation.reference (參考文獻) Famoye, F. , and Wulu, J. T. , Jr. , and Singh, K. P. (2004) “ On the generalized Poisson regression model with an application to accident data,” Journal of Data Science, 2:287-295.zh_TW
dc.relation.reference (參考文獻) Gupta, P. L. , Gupta, R. C. , and Tripathi, R. C. (1996) “ Analysis of zero-adjusted count data, “ Computational Statistics & Data Analysis, 23: 207-218.zh_TW
dc.relation.reference (參考文獻) Jessen, G. , Jensen, B. F. , Arensman, E. , Bille-Brahe, U. , Crepet P. , De Leo, D., Hawton, K. , Haring, C. , Hjelmeland, H. , Michel, K. , Ostamo, A. ,zh_TW
dc.relation.reference (參考文獻) Salander- Renberg, E. , Schmidtke, A. , Temesvary, B. , and Wasserman, D. (1999) “ Attempted suicide and major public holidays in Europe: finding from the WHO/ EURO Multicentre Study on Parasuicide,” Acta Psychiatr Scand, 99: 412-418.zh_TW
dc.relation.reference (參考文獻) Lambert, D. (1992) “ Zero-inflated Poisson regression, with an application to defects in manufacturing,” Technometrics, 34:1-14.zh_TW
dc.relation.reference (參考文獻) Morrell, S. , Taylor, R. , Slaytor, E. , and Ford, P. (1999) “ Urban and rural suicide differentials in migrants and the Australian-born, New South Wales, Australia 1985-1994,” Social Science & Medicine, 49: 81-91.zh_TW
dc.relation.reference (參考文獻) Mullahy, J. (1986) “ Specification and testing of some modified count data models,” Journal of Econometrics, 33: 341-365.zh_TW
dc.relation.reference (參考文獻) Pirkis, J. , Burgess, P. , and Jolley, D. (1999) “ Suicide attempts by psychiatric patients in acute inpatient, long-stay inpatient and community care,” Soc Psychiatry Psychiatr Epidemiol, 34: 634-644.zh_TW
dc.relation.reference (參考文獻) World Health Organization (WHO) website, http://www.who.int/en/.zh_TW
dc.relation.reference (參考文獻) Zeileis, A. , Kleiber, C. , and Jackman, S. (2008)zh_TW
dc.relation.reference (參考文獻) “ Regression Models for Count Data in R,” Journal of Statistical Software, 27.zh_TW