Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 違約戶稀少時之估計條件違約機率
Estimating Conditional PD when Defaults Number is Small
作者 唐延新
Tang,yan hsin
貢獻者 劉惠美<br>陳麗霞
唐延新
Tang,yan hsin
關鍵詞 巴賽爾資本協定
違約機率
ROC曲線
Basel II
default probability
ROC curve
日期 2009
上傳時間 5-Sep-2013 16:09:33 (UTC+8)
摘要 新版巴賽爾資本協定的內部評等法中,銀行可自行對借貸戶進行評分,並且根據
評分估算信用風險以提領準備金,因此估算借貸戶評分分數的違約機率(PD)是相當
重要的一環。過去估算違約機率的研究中,大多假定評分分數為離散型式,本文針對
評分分數為連續形式時,提出一種利用曲線函數來配適估計模型。估計模型是使用伽
瑪的截尾分配去配適ROC曲線函數,再利用此ROC曲線函數來估計各評分分數下的
違約機率P(D|S),在伽瑪分配中的兩參數則是用兩階段的方法求解。本文所提的估
計方法並無假設評分分數的分配,因此在數值方法中使用不同的分配、參數設定、違
約機率等,來驗證此方法的準確度與穩定度,並且與Van der Burgt (2008)、Tasche(2009)的估計方法比較。
By the internal rating-based approach of Basel II, banks estimate borrowers` default risks to withdraw reserves independently. Hence, estimating default probability (PD) of borrowers is important. Most of previous studies estimating PD assume that evaluation scores are discrete, In this study, we use curve function to fit estimation model in the condition that the evaluation scores are continuous
. We use truncated gamma distribution to fit ROC curve function. And we use the ROC curve function to estimate PD of different scores. And use two-step method to find the value of two parameters in gamma distribution. The estimation method in this study doesn`t assume the distribution of estimation scores,so we use different distributions, parameters, and default probabilities to test the
accuracy and stability of this method. In the end, we also compare our methods with Van der Burgt (2008) and Tasche (2009)` methods.
參考文獻 Benjamin, N., Cathcart, A., and Ryan, K. (2006), "Low default portfolios: A proposal for conservative estimation of default probabilities"

Dwyer, D. (2006), "The distribution of defaults and Bayesian model validation"

Forrest, A (2005), "Likelihood approaches to low default portfolios."

Kiefer, N.M. (2009), "Default estimation for low-default portfolios"

Pluto, K. and Tasche, D. (2005), "Estimating probabilities of default for low default portfolios"

Tasche, D. (2005), "Rating and probability of default validation"

Tasche, D.(2009), "Estimating discriminatory power and PD curves when the number of defaults is small", Working Paper.

Van der Burgt, M. (2008), \\Calibrating low-default portfolios, using the cumulative accuracy profile"
描述 碩士
國立政治大學
統計研究所
97354002
98
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0097354002
資料類型 thesis
dc.contributor.advisor 劉惠美<br>陳麗霞zh_TW
dc.contributor.author (Authors) 唐延新zh_TW
dc.contributor.author (Authors) Tang,yan hsinen_US
dc.creator (作者) 唐延新zh_TW
dc.creator (作者) Tang,yan hsinen_US
dc.date (日期) 2009en_US
dc.date.accessioned 5-Sep-2013 16:09:33 (UTC+8)-
dc.date.available 5-Sep-2013 16:09:33 (UTC+8)-
dc.date.issued (上傳時間) 5-Sep-2013 16:09:33 (UTC+8)-
dc.identifier (Other Identifiers) G0097354002en_US
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/60477-
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) 97354002zh_TW
dc.description (描述) 98zh_TW
dc.description.abstract (摘要) 新版巴賽爾資本協定的內部評等法中,銀行可自行對借貸戶進行評分,並且根據
評分估算信用風險以提領準備金,因此估算借貸戶評分分數的違約機率(PD)是相當
重要的一環。過去估算違約機率的研究中,大多假定評分分數為離散型式,本文針對
評分分數為連續形式時,提出一種利用曲線函數來配適估計模型。估計模型是使用伽
瑪的截尾分配去配適ROC曲線函數,再利用此ROC曲線函數來估計各評分分數下的
違約機率P(D|S),在伽瑪分配中的兩參數則是用兩階段的方法求解。本文所提的估
計方法並無假設評分分數的分配,因此在數值方法中使用不同的分配、參數設定、違
約機率等,來驗證此方法的準確度與穩定度,並且與Van der Burgt (2008)、Tasche(2009)的估計方法比較。
zh_TW
dc.description.abstract (摘要) By the internal rating-based approach of Basel II, banks estimate borrowers` default risks to withdraw reserves independently. Hence, estimating default probability (PD) of borrowers is important. Most of previous studies estimating PD assume that evaluation scores are discrete, In this study, we use curve function to fit estimation model in the condition that the evaluation scores are continuous
. We use truncated gamma distribution to fit ROC curve function. And we use the ROC curve function to estimate PD of different scores. And use two-step method to find the value of two parameters in gamma distribution. The estimation method in this study doesn`t assume the distribution of estimation scores,so we use different distributions, parameters, and default probabilities to test the
accuracy and stability of this method. In the end, we also compare our methods with Van der Burgt (2008) and Tasche (2009)` methods.
en_US
dc.description.tableofcontents 謝誌. . . . . . . . . . . . . . . . . . . . . . . . i
中文摘要. . . . . .. . . . . . . . . . . . . . . . . ii
英文摘要. . . . . . . . . . . . . . . . . . . . . . iii
目錄. . . . . . . . . . . . . . . . . . . . . . . . iv
表目錄. . . . . . . . . . . . . . . . . . . . . . . vi
圖目錄. . . . . . . . . . . . . . . . . . . . . . . vii
第一章緒論. . . . . . . . . . . . . . . . . . . . . .1
第一節研究動機. . . . . . . . . . . . . . . . . . . . 1
第二節研究目的. . . . . . . . . . . . . . . . . . . . 5
第二章研究方法. . . . . . . . . . . . . . . . . . . . 6
第一節評分模型的鑑別力. . . . . . . . . . . . . . . . 7
第二節CAP與ROC曲線的特性. . . . . . . . . . . . . . . 9
第三節常態核函數. . . . . . . . . . . . . . . . . . . 10
第四節經驗分配. . . . . . . . . . . . . . . . . . . . 11
第五節校正違約機率. . . . . . . . . . . . . . . . . . 13
第三章模型架構. . . . . . . . . . . . . . . . . . . . 14
第一節估計條件違約機率. . . . . . . . . . . . . . . . 14
第二節估計模型. . . . . . . . . . . . . . . . . . . . 15
第三節Van der Burgt的方法. . . . . . . . . . . . . . 16
第四節Tasche的方法. . . . . . . . . . . . . . . . . . 17
第五節Gamma方法. . . . . . . . . . . . . . . . . . . 21
第四章數值結果. . . . . . . . . . . . . . . . . . . . 25
第一節估計步驟. . . . . . . . . . . . . . . . . . . . 25
第二節常態分配下. . . . . . . . . . . . . . . . . . . . 27
第一小節估計樣本與預測樣本的違約率相同. . . . . . . . . . . 27
第二小節估計樣本與預測樣本的違約機率不相同. . . . . . . . . 34
第三節伽瑪分配下. . . . . . . . . . . . . . . . . . . . 40
第一小節估計樣本與預測樣本的違約機率相同. . . . . . . . . .. 40
第二小節估計樣本與預測樣本的違約機率不相同. . . . . . . . .. 42
第五章結論. . . . . . . . . . . . . . . . . . . . . . 45
參考文獻. . . . . . . . . . . . . . . . . . . . . . . 47
zh_TW
dc.format.extent 1223326 bytes-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0097354002en_US
dc.subject (關鍵詞) 巴賽爾資本協定zh_TW
dc.subject (關鍵詞) 違約機率zh_TW
dc.subject (關鍵詞) ROC曲線zh_TW
dc.subject (關鍵詞) Basel IIen_US
dc.subject (關鍵詞) default probabilityen_US
dc.subject (關鍵詞) ROC curveen_US
dc.title (題名) 違約戶稀少時之估計條件違約機率zh_TW
dc.title (題名) Estimating Conditional PD when Defaults Number is Smallen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) Benjamin, N., Cathcart, A., and Ryan, K. (2006), "Low default portfolios: A proposal for conservative estimation of default probabilities"

Dwyer, D. (2006), "The distribution of defaults and Bayesian model validation"

Forrest, A (2005), "Likelihood approaches to low default portfolios."

Kiefer, N.M. (2009), "Default estimation for low-default portfolios"

Pluto, K. and Tasche, D. (2005), "Estimating probabilities of default for low default portfolios"

Tasche, D. (2005), "Rating and probability of default validation"

Tasche, D.(2009), "Estimating discriminatory power and PD curves when the number of defaults is small", Working Paper.

Van der Burgt, M. (2008), \\Calibrating low-default portfolios, using the cumulative accuracy profile"
zh_TW