為了符合國際清算銀行在 2006 年通過的新巴賽爾資本協定，且有鑑於近年 來整體經濟環境欠佳，銀行業者面對外部的規定以及內部的需求，積極地尋求 信用風險模型的建置方法，希望將整個融資的評等過程系統化以提高對信用風 險的控管。 本研究希望利用 92 至94 年未上市上櫃中小企業之營造業的資料，依循新 巴賽爾資本協定之規定並配合資料採礦的技術，擬出一套信用風險模型建置與 評估的標準流程，其中包含企業違約機率模型以及信用評等系統的建置，前者 能預測出授信戶的違約情形以及違約機率；後者則是能利用前者的分析結果將 授信戶分成數個不同的等級，藉此區別授信戶是否屬於具有高度風險的違約授 信戶，期待能提供銀行業者作為因應新巴賽爾協定中內部評等法的建置，以及 中小企業的融資業務上內部風險管理的需求一個參考的依據。 研究結果共選出 5 個變數作為企業違約機率模型建立之依據，訓練資料以 及原始資料的AUC 分別為0.799 以及0.773，表示模型能有效的預測違約機率 並判別出違約授信戶以及非違約授信戶。接著，經過回顧測試與係數拔靴測試， 證實本研究的模型具有一定的穩定性。另外，透過信用評等系統將所有授信戶 分為8 個評等等級，並藉由等級同質性檢定以及敏感度分析的測試，可以驗證 出本研究之評等系統具有將不同違約程度的授信戶正確歸類之能力。最後，經 由轉移矩陣可以發現，整體而言，營造業在2003 年到2005 年間的表現有逐漸 好轉的趨勢，與營造業實際發展情形相互比較之下，也確實得到相互吻合的結 論。 / In order to conform to the New Basel Capital Accord passing in 2006 by the Bank for International Settlements and due to the slump faced by economies globally and the rise in the number of defaulters in the recent years, the banking industry has aggressively looked for ways to establish the reliable credit risk model that can accommodate required regulations set forth by the Accord as well as the internal banking procedure demands. The banking industry attempts to standardize the process of evaluating credit rating in regards to capital risk in the loan business to enhance the control of credit risks. The attempt of this research is to perform the process of the establishment and evaluation of the credit risk model which includes the default risk model of companies and the credit rating system within the framework of the New Basel Capital Accord using the statistical tool known as data mining. The data adopted in this study is taken from the construction industry of the SMEs from 2003 to 2005. The default risk model assesses the probability whether a company is at risk of being defaulted. In addition the credit rating system assigns credit scores to a company in question based on the application result from the default risk model to differentiate those who have high risk of being defaulted. More importantly this research provides banking industry of varying degrees of complexity to monitor its risk assessment as well as becoming a reference basis of the loan business in the SMEs. Based on the result of this study, five variables are selected as the default probability model basis. The AUC for the training data is 0.799 and for the raw data is 0.773 which represents the accuracy and reliability of the model in predicting the probability of default risk and determining the likelihood of the companies to default. After series of testing, our model stability plays a key role in determining whether the algorithm produces an optimal model in this study. The credit rating system formulates credit scores of the companies into 8 credit ratings. Applying homogeneity test and sensitive analysis, this study is able to verify the validity and accuracy of the rating system to correctly classify different levels of credit risk that could have jeopardized the companies to default. Finally, through the transformation matrix, there has been an improvement trend of performance in the construction industry from 2003 to 2005 which coincides with the result of this study.

2008年，美國華爾街危機影響全球金融市場，即使美國擬出許多救市計畫，全球股市依舊暴跌。在此危機衝擊下，各大金融機構不但利潤下滑，且資產減記和信貸損失也愈來愈嚴重。造成此一現象的主因即是次級房貸的影響，次級房貸主要是針對收入低、信用不佳卻需要貸款購屋的民眾，這類客戶通常借貸不易，倘若銀行內部沒有完善的評等機制那放款則需承受較大的違約風險。為因應此趨勢，本研究以台灣未上市中小企業為實例，資料的觀察期間為2003至2005年，透過資料採礦流程，建構企業違約風險模型及其信用評等系統。 本研究分別利用羅吉斯迴歸、類神經網路、和分類迴歸樹三種方法建立模型並加以評估比較其預測能力。發現羅吉斯迴歸模型對於違約戶的預測能力及有效性皆優於其他兩者，並選定為本研究之最終模型，並對選定之模型作評估及驗證，發現模型的預測能力表現尚屬穩定，確實能夠在銀行授信流程實務中加以應用。 / In 2008, the financial crisis on Wall Street had severe impacted the global economy. Although the US government has drawn up regulatory policies in an attempt to save the stock market, the value of global stock market has shrunk drastically. As such, the profits of many financial institutes’ have not only plunged, their value of assets have decreased while loss related to mortgage became more severe. The main cause behind this global phenomenon can be attributed to the effect of subprime mortgages. Subprime mortgages are mainly aimed at consumers who have low income and poor credit history but wish to purchase homes through the means of mortgage. These consumers usually find it difficult to obtain mortgage loans. If banks do not have a well structured evaluation system, they would have to bear more risks in the case of a default. To better understand this trend, this research chooses middle and small private enterprises as its samples. The period of observation is 2003 to 2005. Using the data mining process, this research builds a model that shows the risk associated with contract failure and credit score system. The research builds a model based on logistic regression, Neural Network, and cart to compare and contrast each of the three model’s ability to predict. The result shows that logistic regression is better at predicting defaults and is more effective than the other two models. The research, therefore, concludes logistic regression model as the research’s final model to study and evaluate. In process, the research result demonstrates that the logistic regression model makes more precise prediction and its prediction is fairly stable. Logistic regression model is capable for banks to employ in performing credit check.

近年來隨著台灣人口日漸少子化，「養兒防老」的傳統觀念已不符時勢所趨，面對高齡化社會所帶來龐大的財政負擔及老年人口安養等社會問題。過去研究結果提供了一可能的解決方案－「逆向房屋抵押貸款（Reverse Mortgage, RM）」，然而，對於此種新型貸款在台灣推行之完整可行性分析，相關研究尚付之闕如。是故，本研究從承貸雙方角度出發，旨在深入探討未來逆向房屋抵押貸款在台推行之可行性。 首先，對於申貸者而言，本研究以30至60歲且名下擁有不動產之家戶為研究單位，並用問卷調查台灣中年房屋持有者申請逆向房屋抵押貸款之意願程度。針對調查結果，再以「羅吉斯迴歸（Logistic Regression）」分析影響申請意願之顯著因子，據以探討申請意願與受訪者特性兩者之關係。 其次，從承貸者角度建立一貸款定價模型，模擬分析於損益兩平條件下，貸款機構有無貸款保險，以及於不同貸款給付方案中，其可提供逆向房屋抵押貸款之最高可貸款成數（Loan to Value, LTV）。再者，進一步結合台灣各主要都會區房價資料，研究顯示所得替代率（Income Replacement Ratio, IRR-RM）符合多數申貸者之基本需求。 本研究預期「逆向房屋抵押貸款」除了有效解決人口老化所衍生之社會問題外，亦兼具政府「就地老化（Aging in Place）」政策效益，提升了老年生活品質，維護老年人口的尊嚴。 / With the continuously declining fertility rates and the increasing life expectancy, Taiwan has become one of the aging societies in the world. To release the financial strain of the government, a great number of literature has suggested an alternative option, Reverse Mortgage (RM), to improve the retiring life quality of the elders. However, little attention has been given specifically to the feasibility of the application of RM and the pricing model in individual countries. This study thus conducted the questionnaire and collected the data in Taiwan for analysis in order to show the implementation feasibility of RM in aging society for both the aspects of both lenders and borrowers. First of all, to find out the factors affecting the willingness in applying for RM and the characteristic of the middle-aged homeowners, we designed a survey and a quantitative analysis of the questionnaire through Logistic Regression Analysis. Second, under a break-even hypothesis, we analyzed the ratio of Loan to Value (LTV) a reverse mortgage lender would offer through the simulation model. Furthermore, the housing data from different metropolises of Taiwan is integrated into the study in order to determine whether if the Income Replacement Ratio of RM (IRR-RM) could meet the basic needs of Taiwanese. Results found in this paper suggest that RM could satisfy the general need of people in Taiwan. Procedures conducted in this study may also provide precious insight for other aging countries. This paper suggests that reverse mortgage could not only solve the society issues, but also secure the retiring lives of the elders and preserve their living qualities.

假設二元反應曲線為簡單線性羅吉斯迴歸模型(Simple Linear Logistic Regression Model)，在樣本數為偶數的前題下，所謂的最佳D型設計(D-Optimal Design)是直接將半數的樣本點配置在第17.6個百分位數，而另一半則配置在第82.4個百分位數。很遺憾的是，這兩個位置在參數未知的情況下是無法決定的，因此逐次實驗設計法(Sequential Experimental Designs)在應用上就有其必要性。在大樣本的情況下，本文所探討的逐次實驗設計法在理論上具有良好的漸近最佳D型性質(Asymptotic D-Optimality)。尤其重要的是，這些特性並不會因為起始階段的配置不盡理想而消失，影響的只是收斂的快慢而已。但是在實際應用上，這些大樣本的理想性質卻不是我們關注的焦點。實驗步驟收斂速度的快慢，在小樣本的考慮下有決定性的重要性。基於這樣的考量，本文將提出三種起始階段設計的方法並透過模擬比較它們之間的優劣性。 / The D-optimal design is well known to be a two-point design for the simple linear logistic regression function model. Specif-ically , one half of the design points are allocated at the 17.6- th percentile, and the other half at the 82.4-th percentile. Since the locations of the two design points depend on the unknown parameters, the actual 2-locations can not be obtained. In order to dilemma, a sequential design is somehow necessary in practice. Sequential designs disscused in this context have some good properties that would not disappear even the initial stgae is not good enough under large sample size. The speed of converges of the sequential designs is influenced by the initial stage imposed under small sample size. Based on this, three initial stages will be provided in this study and will be compared through simulation conducted by C++ language.

IPCC於第四次報告書中，模擬氣候持續暖化預測未來海平面上升之情形，而海平面上升對於人口集中的台北都會區將產生莫大之衝擊，同時亦會造成土地利用變遷。本研究目的在於探討海平面上升對台北都會區土地利用變遷之影響，以及受淹沒地區之人口未來可能之遷移區位，主要係從社會經濟發展層面進行分析。運用二元羅吉斯迴歸模式並結合土地利用轉換與影響模型（CLUE-s），以四種不同情境模擬土地利用變遷之情況，其情境分別為海平面上升59公分管制農林地與不管制，以及海平面上升100公分管制農林地與不管制。 　　研究結果顯示，海平面上升之情形越嚴重，未來的都市建地發展會越趨向擴張的形式，對農林地產生變遷之壓力；而於同一海平面上升水平下，針對農林地進行管制，其建地之發展會較為集中於都市計畫地區範圍內，且多數人口亦將遷移至此，容易形成人口壓力。此外，土地利用變遷模擬所得之新增建地部分，於情境A、C下足以容納受影響之人口，但情境B、D則不足以容納，皆會對台北都會區產生容受力之問題，產生累計人口超過計畫人口之現象。因此，建議未來政府於都市發展上，可調整都市計畫內之土地使用強度或都市範圍，也可利用都市更新之方式減少新的土地開發；此外，從國家層級分析，未來的國土計畫法於立法上，亦可將更多氣候變遷相關影響因子納入四大功能分區，透過適宜性分析進行分類分級，以做為未來土地利用發展之引導。 / The 4th IPCC report simulated climate warming and predicted future sea-level rise scenarios. A sea level rise will have a great impact on the population of the Taipei metropolitan area, and it will also produce land-use changes. The purpose of this study is to research the impact of sea level change on land use changes and population migration in Taipei metropolitan, and the areas that will be immigrated by the flooded areas. The method used includes binary logistic regression model combined with Conversion of Land Use and its Effects Model (CLUE-s). Setting the sea-level rise and regulating agricultural land, forest land of the four simulated situations. The results show that the higher sea level rises, the more transformation towards urban development in the future, and the higher sea level will also pressure agriculture and forestry changes. As a result of population pressure on Taipei metropolitan area, the same level of sea-level rise for the regulation of agriculture and forestry land, the development of building sites and population migration will be more concentrated on urban planning areas. In addition, the simulation of land use change generated new building sites, sufficient enough to accommodate the affected population under A and C simulated situations, but B and D couldn’t generate such results. Instead, it will generate a carrying capacity issue. Therefore, this thesis suggests that the government adjust the intensity of land use in urban development, urban areas and urban renewal of urban planning. In addition, the analysis from the national level, the future legislation of Land Planning Act should include the relation of climate change impact factors as a consideration of future land use development.

基於累積殘差的廣義線性模型檢查方法，由Su和Wei(1991)所提出。在本次研究中利用蒙地卡羅模擬的方式探討，在各種模型下該檢定方法的成效，當中包含：卜瓦松迴歸模型、羅吉斯迴歸模型及負二項迴歸模型。由於負二項分配相較於卜瓦松分配及二項分配多了一個參數r，其中負二項分配之隨機變數定義為：直到第r次成功之失敗次數。因此，亦探討了在不同參數r下，基於累積殘差的廣義線性模型檢查方法是否有成效上的差異。結果發現，當r較小時，該模型檢查方法，需要較多的樣本數；而當參數r過大時，由於參數r的估計結果與實際值差異過大，便會導致檢定結果成效不佳。另一部分，亦將基於累積殘差的廣義線性模型檢查方法輔以傳統的迴歸模型參數T檢定，使得模型的適合度檢定流程趨於完善。

本研究預測違約機率的方法為:Binary Regression Quantiles(二元分量迴歸)，此理論基礎與預測方式是使用美國學者Grigorios Kordas(2004)的方法，將分量迴歸運用在應變數為二元的屬質變數上之計量方法。 最小平方法是目前最常見到的迴歸分析，但在古典線性迴歸模型中，應變數的解釋是來自於自變數的相對應的平均變化，而忽略了不同規模與分配下應變數的邊際變化，本文試圖以此方法和以最大概似估計法所建構出的Logit模型做一比較，而研究資料為台灣於民國85年至93年曾被列為全額交割類股的上市公司。 本研究發現Kordas (2004)的方法，雖然能將分量迴歸應用在屬質二元變數上，但是在預測方面相較於傳統Logit方法卻沒有出現較佳的預測能力。 / The method implemented in PD calculation in this study is “Binary Regression Quantiles”. The foundation of the research and the way to forecast is according to the Ph.D Thesis of Grigorios Kordas(2004). He apply the binary variable for Quantile Regression. The Ordinary Least Square is the most common way to regression analysis, but in the classic linear regression the change of dependent variable comes from the independent variable averagely. It neglects the marginal change of the dependent variable according to different scale and distribution. We want to compare the Binary Regression Quantiles with the Logit Regression. Although we could apply the binary variable for Quantile Regression successfully, the outcome of the forecast is not as efficient as the Logit Regression.

財務危機模型的研究一般納入財務正常公司與財務危機公司兩者當樣本，探討區分危機與正常公司的因素，本研究則進一步以財務危機公司為樣本，探討在財務危機公司中區分舞弊公司與正常經營公司的基本因素。 本研究從財務危機公司中，分出財務舞弊公司與正常經營公司，因此研究樣本包含發生舞弊的財務危機公司與正常經營而發生財務危機的公司。研究變數則從文獻篩選23個財務解釋變數，以及13個公司治理解釋變數，運用羅吉斯迴歸法進行實證，結果顯示3個財務變數和1個公司治理變數在區分財務危機公司中的財務舞弊公司與正常經營公司有顯著的區別能力，公司治理變數的董監事持股比率尤其顯著。 / Financial distress prediction is usually based on both financial distressed firms and non-distressed firms. Based on financial distressed firms, this study further investigates the factors distinguishing financial fraud firms from non-fraud firms. The sample includes fraud and no-fraud firms while both are financial distressed. Twenty-three financial and thirteen corporate governance variables are surveyed from literature. The empirical result of logit regression shows that three financial variables and one corporate governance variable are significant factors in distinguishing fraud from no-fraud firms in distressed companies. Especially, the percentage of holding stocks of board of directors is the most significant variable.

在行銷策略、品牌推廣中，廣告一直是不可獲缺的重要角色。因此如何有效的傳達廣告中產品的訊息、品牌的理念，讓消費者接收到商品及品牌的優點並且產生消費的意願，一直是廣告行銷者最大的挑戰。然而每一支廣告從拍攝購買播出時段往往需花上龐大之金額，是故欲拍攝廣告之廠商，希望將每一塊錢都花在刀口上，期望能以最適當之廣告型態來為其商品拍攝廣告，準確地達成廣告之目的。故本研究將國內5年來登記上映之電視廣告挑選八大商品類別作為研究對象，以廣告型態(代言人、手法、調性)及秒數作為研究變項，探討各商品類別的電視廣告與廣告型態間之關聯性，進而找出最適合各商品類別之廣告型態。 本研究使用卡方獨立性檢定、單因子變異數分析及羅吉斯廻歸等方法，將廣告代言人分為名人、素人及動畫；廣告手法分為故事式、生活片段式、名人推薦式、真人反應及意見式、一般廣告歌式、動畫廣告歌式、訊息直接敘述式等七種；廣告調性分為Kuso(幽默)、輕鬆、感性，研究各商品類別、廣告型態及廣告秒數間的關係。研究結果發現： 1. 廣告代言人中以素人之比例為最高、動畫之比例最少，而以名人之成長率最為穩定。 2. 廣告手法以生活片段式及訊息直接敘述式之比例為最高、動畫廣告歌式之比例最少，而以故事式及訊息直接敘述式之成長率最為穩定。 3. 廣告調性以輕鬆之比例為最高。 4. 不同商品類別傾向選擇不同之廣告代言人。 5. 不同商品類別傾向選擇不同之廣告手法。 6. 不同商品類別傾向選擇不同之廣告調性。 7. 不同廣告手法、廣告調性對於廣告播出秒數有顯著性差異。

永續發展的概念現今已被運用於都市，其中，都市綠地在環境、生態、景觀、社會各層面之機能皆可提升都市永續性，在快速的都市化下，都市內綠地減少，土地利用變遷帶來之環境衝擊影響已自個體單元累積到全球。然而，過去研究中未有關注在綠地的變化趨勢與其他土地利用間的互動關係，以及在不同區域下的變化差異。因此，本研究採用GIS和景觀指數看在1995年至2006年間台北都會區綠地變遷趨勢，並分區探討土地利用間的互動關係，最後藉由二元羅吉斯迴歸分析綠地變化可能原因。 研究結果顯示，在1995年至2006年間，台北都會區整體發展是建地增加，林地也呈上升趨勢，而草地是土地利用轉移下被犧牲掉最多的土地，綠地轉移成其他土地利用情形以都會邊緣地區最嚴重。不同綠地型態在1995年至2006年間的變遷仍有差異，林地在整個台北都會區屬於景觀中的基質，主導性未受動搖，僅在都會中心減少並受破壞；而農地面積略微下降，呈破碎化發展，尤其以都會中心外圍區農地被破壞情形最明顯；草地面積亦下降，破碎化情形較農地更嚴重，在都會郊區、次中心之草地被破壞嚴重，草地各方面機能降低。透過二元羅吉斯迴歸分析發現自然環境、社會經濟與計畫環境皆影響台北都會區的綠地變遷。根據研究結果，建議未來政府於都市計畫上應將綠地空間納入考量，對於不同綠地型態應有不同管制措施，考量各區域綠地型態之差異性，以及自然環境、社會經濟和計畫環境對於綠地變遷的影響，以促進都市朝向永續發展。 / The concept of sustainable development has been applied in cities. Urban green space plays an important role in enhancing the sustainability of the city in regards to the environment, ecology, landscape and society aspects. Under rapid urbanization, green space has greatly declined in cities. Environmental impact resulting from land use change has grown from local to global proportions. However, researches did not pay attention to interactions between green spaces and other land-use change trends or different types of change in different areas. This research used GIS and landscape metrics to investigate the green space change trend and interactions among different land use types in the Taipei metropolitan area from 1995 to 2006. Furthermore, this research analyzed possible reasons that may have caused green space change through logistic regression. The results showed that, from 1995 to 2006, the built up area and the forest increased in Taipei Metropolitan Area; however, the grass decreased because of land use change. Urban fringe was the place that green space changed to other land-use most. There were differences of land use change for different types of green space. Forest was the matrix in the landscape of Taipei metropolitan area. It still kept the predominant role, only decreased and was destroyed in the center of metropolitan area. Farmland slightly decreased and became fragmented, especially in the periphery of the urban center. Grassland area decreased and became fragmented much more than farmland. In suburb and sub-center, grassland was destroyed seriously and became less functional. Through binary logistic regression, the study found that natural environment, socio-economic and government planning do have influence on green space changes in the Taipei metropolitan area. According to the result of the study, the recommendation was that government should take green space into consideration when doing urban planning. For different types of green space and different areas, the government needs to have different measures and needs to consider the impact factors of green space change in order to accelerate sustainable development in cities.