國立高雄大學圖資館 |

語系: 繁體中文

說明(常見問題)

圖資館首頁

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

以隱藏馬可夫模型預測整體信用評等等級總數之變化及其各別公司評等之變動 =...

周正修

以隱藏馬可夫模型預測整體信用評等等級總數之變化及其各別公司評等之變動 = Predict number of the credit ratings and firm’s rating change by Hidden Markov Model

紀錄類型:	書目-語言資料,印刷品 : 單行本
並列題名:	Predict number of the credit ratings and firm’s rating change by Hidden Markov Model
作者:	周正修,
其他團體作者:	國立高雄大學
出版地:	[高雄市]
出版者:	撰者;
出版年:	2012[民101]
面頁冊數:	57面圖，表格 : 30公分;
標題:	信用評等
標題:	credit ratings
電子資源:	http://handle.ncl.edu.tw/11296/ndltd/64947560005872036690
附註:	參考書目：面39
摘要註:	信評機構對公司債券及國家主體履行財務承諾的相對能力做評比，面對不同評等之公司，投資人可依其對風險的承受能力選擇不同的投資標的，因此公司的信用評等為投資人重要的參考指標。然而，在經濟不景氣時，公司表現的微小差異較繁榮時更容易影響投資人的投資態度，所以較精細的評等此時顯得更重要。傳統文獻中，多在固定信用評等總數的假設下進行討論，本文則以隱藏馬可夫模型為工具，探討在不同經濟情況時，評等總數的調整以因應景氣的變化以及面對評等總數調整時，公司評等變化的即時資訊。本文分成兩個部分討論，第一，利用可觀察的財務比率做為信用評等的預測變數，以複回歸模型預測未來表現，並將其分成不同評等，再利用模型配適度檢定其評等之分配是否與原始分配相符。其次，在分配不相符合的期間，討論評等的變動，並重新估計轉置矩陣。本文將進行模擬實驗，以上述方法驗證在經濟繁榮、衰退、持平時，評等總數的變化及公司評等改變的影響，亦以包含金融業及製造業的一百家台灣上市公司（資料來源為公開資訊觀測站）進行實證研究，預期找出在金融海嘯期間信用評等總數及公司評等的變化。 Credit rating company rates the firm’s bonds and the ability of repaying the debts of countries. For the different ratings of companies, the investors can choose a different investment according to their risk-bearing capacity. So, the company's credit rating is an important reference indicators for investors. However, during the economic down-turn, the small differences between the company's performance is more easily affect the investment attitude of the investors, the finer rating information is more important. In Traditional paper, the most parts of this are under the assumption of the fixed number of credit ratings, In this article while Hidden Markov Model as a tool to explore the total numbers of credit ratings change by different economic situations and the information of companies’ rating change when the total numbers of credit ratings change. This article is divided into two sections. First, use the financial ratios be the observed as the credit rating predictor variables and multiple regression model to predict the future performance. Use modest test of the distribution to test the consistency with the original distribution. Second, during the distribution is not consistent with the original, discussion of assessment, such as numbers of credit rating change and re-estimated the transition matrix. This paper will conduct simulated experiment to verify the total number of rating changes of economic prosperity, recession, flat and discuss the impact of rating changes to the companies. Also, an empirical research include the 80’s listed companies in Taiwan and we will to find whether the number of credit rating change during the financial crisis.

以隱藏馬可夫模型預測整體信用評等等級總數之變化及其各別公司評等之變動 = Predict number of the credit ratings and firm’s rating change by Hidden Markov Model
周, 正修

以隱藏馬可夫模型預測整體信用評等等級總數之變化及其各別公司評等之變動 = Predict number of the credit ratings and firm’s rating change by Hidden Markov Model / 周正修撰 - [高雄市] : 撰者, 2012[民101]. - 57面 ; 圖，表格 ; 30公分.
參考書目：面39.
信用評等credit ratings

以隱藏馬可夫模型預測整體信用評等等級總數之變化及其各別公司評等之變動 = Predict number of the credit ratings and firm’s rating change by Hidden Markov Model
LDR:04232nam a2200277 4500 001 346151
005 20170214091028.0
009 346151
010 0 $b 精裝
010 0 $b 平裝
100 $a 20170214d2012 k y0chiy05 e
101 1 $a chi $d chi $d eng
102 $a tw
105 $a ak am 000yy
200 1 $a 以隱藏馬可夫模型預測整體信用評等等級總數之變化及其各別公司評等之變動 $d Predict number of the credit ratings and firm’s rating change by Hidden Markov Model $z eng $f 周正修撰
210 $a [高雄市] $c 撰者 $d 2012[民101]
215 0 $a 57面 $c 圖，表格 $d 30公分
300 $a 參考書目：面39
314 $a 指導教授：俞淑惠博士
328 $a 碩士論文--國立高雄大學統計學研究所
330 $a 信評機構對公司債券及國家主體履行財務承諾的相對能力做評比，面對不同評等之公司，投資人可依其對風險的承受能力選擇不同的投資標的，因此公司的信用評等為投資人重要的參考指標。然而，在經濟不景氣時，公司表現的微小差異較繁榮時更容易影響投資人的投資態度，所以較精細的評等此時顯得更重要。傳統文獻中，多在固定信用評等總數的假設下進行討論，本文則以隱藏馬可夫模型為工具，探討在不同經濟情況時，評等總數的調整以因應景氣的變化以及面對評等總數調整時，公司評等變化的即時資訊。本文分成兩個部分討論，第一，利用可觀察的財務比率做為信用評等的預測變數，以複回歸模型預測未來表現，並將其分成不同評等，再利用模型配適度檢定其評等之分配是否與原始分配相符。其次，在分配不相符合的期間，討論評等的變動，並重新估計轉置矩陣。本文將進行模擬實驗，以上述方法驗證在經濟繁榮、衰退、持平時，評等總數的變化及公司評等改變的影響，亦以包含金融業及製造業的一百家台灣上市公司（資料來源為公開資訊觀測站）進行實證研究，預期找出在金融海嘯期間信用評等總數及公司評等的變化。 Credit rating company rates the firm’s bonds and the ability of repaying the debts of countries. For the different ratings of companies, the investors can choose a different investment according to their risk-bearing capacity. So, the company's credit rating is an important reference indicators for investors. However, during the economic down-turn, the small differences between the company's performance is more easily affect the investment attitude of the investors, the finer rating information is more important. In Traditional paper, the most parts of this are under the assumption of the fixed number of credit ratings, In this article while Hidden Markov Model as a tool to explore the total numbers of credit ratings change by different economic situations and the information of companies’ rating change when the total numbers of credit ratings change. This article is divided into two sections. First, use the financial ratios be the observed as the credit rating predictor variables and multiple regression model to predict the future performance. Use modest test of the distribution to test the consistency with the original distribution. Second, during the distribution is not consistent with the original, discussion of assessment, such as numbers of credit rating change and re-estimated the transition matrix. This paper will conduct simulated experiment to verify the total number of rating changes of economic prosperity, recession, flat and discuss the impact of rating changes to the companies. Also, an empirical research include the 80’s listed companies in Taiwan and we will to find whether the number of credit rating change during the financial crisis.
510 1 $a Predict number of the credit ratings and firm’s rating change by Hidden Markov Model $z eng
610 0 $a 信用評等 $a 隱藏馬可夫模型 $a 轉置矩陣
610 1 $a credit ratings $a Hidden Markov Model $a transition matrix
681 $a 008M/0019 $b 343201 7712 $v 2007年版
700 1 $a 周 $b 正修 $4 撰 $3 576371
712 0 2 $a 國立高雄大學 $b 統計學研究所 $3 166081
801 0 $a tw $b NUK $c 20121107 $g CCR
856 7 $z 電子資源 $2 http $u http://handle.ncl.edu.tw/11296/ndltd/64947560005872036690