長期以來，不動產估價相關研究皆著重在估價理論與技術的改進，以使最後估值能更為精確。然而實際上，估價人員的行為才是影響價格評定的本質因素；尤其國內、外對於市場比較法的相關研究，皆發現估價人員有偏離理論規範的現象。故本文第一部份是分析估價人員系統行為偏誤問題；第二部分探討特徵價格模型的偏誤，並應用分量迴歸改進不同高低價格的估價模型準確度；第三部分比較估價師個別估價與大量估價模型之偏誤與差異；為提升客觀估價方法，第四部分探討以估價師估值樣本產生最可能價格與機率的方式。本研究藉由估價師估價行為與大量估價模型不同面向的研究，重新檢視市場比較法的各種偏誤現象。 一、市場比較法估價之系統行為偏誤 市場比較法是估價人員最常使用的方法，但在估價過程中主觀判斷部分相對較多也最易引起爭議。過去市場比較法研究著重在估價理論與技術改進，以減少主觀判斷造成的隨機偏誤，然而，研究指出行為偏誤造成的系統偏誤，其持續性的偏誤對於估價偏誤有重要影響。過去探討估價行為的研究，受限於資料樣本取得，幾乎都是以問卷或實驗得到結果，而非實證結果。本文則是以實際估價報告書進行實證分析，以鄒檢定(Chow Test)及似無相關檢定(Seemingly Unrelated Regression)，發現勘估標的估值與比較標的市場成交值兩模型係數有顯著差異，表示估價人員估值模型起始點高於市場成交值模型，估價人員對於使用類型有高估現象，對於面積估計有低估現象，支持估價人員有系統行為偏誤。此外，也發現評估不同市場時，行為偏誤程度亦不同，估價人員於評估拍賣價格時，因估價經驗與比較案例較少，較傾向參考比較案例，行為偏誤亦較小，僅面積係數有差異；但於評估正常市場價格時，估價行為偏誤較大，區位、使用類型及面積係數皆有差異。 二、不同高低價格不動產估價模型之偏誤改進－分量迴歸模型之應用 隨著國內不動產市場M型化推案趨勢，非典型住宅（如：高總價豪宅和低總價小套房）類型逐漸增多，對於此類型產品的估價精準度也需要提升。從過去研究發現，最小平方迴歸估計忽略各特徵屬性對價格條件分配的差異。本研究乃以分量迴歸方法建立住宅大量估價模型，藉以瞭解住宅特徵對於不同價格分量的差異，實證結果發現以最小平方迴歸模型估計相較於分量迴歸，對於一樓、頂樓、車位、區位等變數有高估或低估的情形。比較估值模型預測精確度，本文透過30次重複實驗，發現分量迴歸對於兩側尾端樣本有較佳的預測能力。從實證方法而言，本文改進以最小平方迴歸模型對兩尾端價格高估或低估問題；就實務應用方面，隨著不動產產品差異度增加，以及新版巴塞爾協定（Basel Ⅱ）實施對不動產價值更新的需求，分量迴歸模型可提升兩尾端估計精確度，並提供住宅大量估價系統另一種資產重估方法。 三、大量估價與個別估價之差異分析 不動產估價研究可分為個別估價與大量估價兩類，過去有關個別估價研究多為估價行為或估價方法改進，而大量估價研究則多是運用數量方法建立模型，由於兩者建構方式不同，欲同時進行兩者實證比較並不容易。本文藉由相同勘估標的，取得估價師個別估價資料，與資料庫建立的自動估價系統，進行案例選取、權重調整及最後估值三階段的比較分析。經本文差異比較發現，前二個階段的比較結果，皆是自動估價系統優於個別估價，從估價行為觀點，顯示自動估價系統具有較客觀且符合估價理論程序優點。然而第三階段的估值比較，發現自動估價系統的表現並不如預期，此結果與過去研究結論不同，分析兩者差異值大的案例，發現資料庫樣本較少地區以及非典型住宅類型（面積過大或過小），是造成個別估價估值與自動估價系統估值差異大的原因，顯示自動估價系統有其適用限制，未來若增加資料庫樣本或次市場模型，兩者估值差異將可獲得改善。 四、不動產估值認知與估值機率 本章以估價師估值資料為樣本，藉由蒙地卡羅模擬估值機率模型，其模擬結果可客觀估計最可能價格（the most probable price）與機率。由於資料樣本來自於專業估價師的判斷，估值分配代表的是估價師所估計的可能估值結果；相較於過去僅以單一估值決定資產價值，藉由多位專業估價師所判斷結果而建立的估值區間與最可能價格及機率，應該是更具客觀性且接近市場價值，而且估值機率的呈現將有助於估價報告書使用者評估存在於資產價值的上方（upside risk）及下方風險（downside risk）。 / In the real estate appraisal research, appraisers and mass appraisal are the two methods most often used in the sales comparison approach. Past studies focused on appraisers behavior and mass appraisal model, lack of compared the difference by appraisers for the same objects as well as mass. The first essay reviews the behavior literature regarding real estate appraisers and summarizes the two hypotheses for departure from normative models. The study is based on appraisers’ reports analyzes for the appraisal valuation and the market transaction by hedonic price models. Among the 112 appraisal reports of the transaction data of 230 comparables and the valuations of 224 subjects, the results reveal the effect of the variables on the appraisal valuation are not consistent with those of the market transaction. In addition, comparing the appraisers’ behavior on the general market with the auction market, the result found is the differences between the valuation models and the transaction models are less than the models on the auction market. The empirical evidences support the two hypotheses and can be explained plausibly by the appraisers’ behavioral contention. The second essay analize the current domestic trend of residential types, it is easy to find that high-priced dwelling units and low-priced dwelling units keep gaining popularity. Thus, the estimation of these two types of residences should be more precise. Since ordinary least square regression can not signify the variation caused by different quantile functions of a conditional distribution, this study estimates the housing price by quantile regression. We compare the models by using ordinary least square regression and quantile regression. The empirical results show that the distributions of some variables, such as first floor, top floor, parking lot, location, are different between two models. These are easily to be underestimated or overestimated when ordinary least square regression is applied. Based on thirty repeated experiments using random sampling, the results of hit rate and mean absolute percentage error show that quantile regression estimates more accurately on two-tailed distribution. For mass appraisal application, a quantile regression advances the estimate on two-tailed price and provides a new method on assets reevaluation of banks.

到期還本的指數連動型證券為一種連結權益(equity)的債權證券，所連結的權益部分通常以隱含選擇權的方式建立。指數連動證券具有自動資產配置調整的特性，當股票市場表現不錯時，此契約給予投資人較高的股票市場風險暴露（因為股票上漲時，Delta值增加）。若股票市場表現不佳，則契約收益特徵接近債券的型式。所以是保守型投資得以參與部分股票市場表現之設計。 本論文所研究之中短期連動型票券，係以零息債券持有至到期（其面額等於到期還本金額），期間不可贖回或申購，並以期初零息債券貼現的部分來購買不同的請求權，以做為連動股票市場表現的機制。在推導多重標的資產請求權評價模型上，係採Martingale方式，其中並證明在Gisanov轉換機率測度下，多重標的之隨機項轉換的規則。 本文主要研究Rainbow Call與Spread Call的評價模型與避險參數；進一步研究標的資產間相關係數對選擇權價值之影響與避險上的財務經濟意義。另一方面，運用Martingale此一有力的工具，佐以現金流量分析，來推導跨國標的之評價模型，並提出跨國之避險操作方法，與說明標的資產與匯率間相關係數在避險上的財務經濟意義。 本文最後就兩套請求權設計之指數連動票券，模擬比較在不同相關係數下，與其他選擇權設計之指數連動票券的表現。並嘗試提出該設計票券之較佳表現時機。

本研究的目的在暸解教師流動的型態與調動的因素，從83學年度臺灣省國民中學調動教師中抽取384人，並同時抽取380位未調動教師作為參照。 　　本研究採用虛擬依變項的迴歸分析，探討導致教師調動的因素。結果發現教師調動的型態存在往都會地區流動的現象。調動與非調動教師的比較中，在性別、教學年資、婚姻狀況與配偶的勞動參與率、自用住宅的擁有、調動次數、學校規模、以及是否為居民的變項上有顯著的不同。 　　在調動機率的影響方面，性別、教學年資、婚姻狀況與配偶的勞動參與率、調動次數、學校規模、以及薪資與福利措施的滿意度上，有著顯著的預測力。研究的結論是教育人力資源分配仍不平均，從影響教師調動機率的因素中，可以提供導引教育人力資源分配更加均衡的線索。 / The main purpose of this study is to inquire into the style about the teachers' mobility and the factors affecting such mobility. Sampling from 1994 academic year in Taiwan, the researcher focuses on the 384 cases of all mobilized teachers and their counterpart-380 nonmobilized cases. 　　A dummy dependent regression analysis is conducted to explore the factors. As a result, the phenomenon for mobility tends to flow into the metropolis. Factors affecting the mobility exhibits significant differences compared to nonmobility; such as factors among sex, seniority, marriage, inhibition, frequcncy of mobility and the scale of the school. 　　In additions, the propensity to mobile, as this study finds, has to do with their sex, seniority, marriage and the labor participation of spouse, frequcency of mobility, degree of the content about their wages and welfare, and the scale of the school. The conclusions made here are: the human resources in education is still scanty. From the factors influenced mobility probability, it can provide some clues to make the human resources in education more equal.

The main purpose of this study is to inquire into the style about the teachers' mobility and the factors affecting such mobility. Sampling from 1994 academic year in Taiwan, the researcher focuses on the 384 cases of all mobilized teachers and their counterpart-380 nonmobilized cases. A dummy dependent regression analysis is conducted to explore the factors. As a result, the phenomenon for mobility tends to flow into the metropolis. Factors affecting the mobility exhibits significant differences compared to nonmobility; such as factors among sex, seniority, marriage, inhibition, frequcncy of mobility and the scale of the school. In additions, the propensity to mobile, as this study finds, has to do with their sex, seniority, marriage and the labor participation of spouse, frequcency of mobility, degree of the content about their wages and welfare, and the scale of the school. The conclusions made here are: the human resources in education is still scanty. From the factors influenced mobility probability, it can provide some clues to make the human resources in education more equal.

根據1990年住宅普查結果顯示，臺灣的住宅自有率為78.44%，空屋率為13.29%。此結果相較於1980年住宅普查的自有率79.11%與空屋率13.09%，發現十年來此兩住宅現象變化不大，其中臺灣的空屋現象與歐美國家一般正常3~5%的空屋水準比較，明顯偏高。然而臺灣長期面對如此高的空屋率，其背後的涵意、原因與影響為何？是否隱含臺灣住宅投資的偏高資本利得預期與偏低的持有成本及租金等現象？值得研究。尤其臺灣近年來的偏高房價並未因為高空屋率而有明顯的下降情形，此又代表何種意義？更重要的是：政府面對如此高的空屋現象，應有何住宅政策以為因應？ 　　本研究首先透過兩次住宅普查與臺灣電力公司表燈用電不足底度資料澄清臺灣地區各縣市空屋狀況。發現臺灣地區歷年空屋率均相當高，而至1993年底空屋數量持續增加達到歷年最高記錄：約76萬戶空屋，空屋率約為14%，此現象預期對未來房地產市場不景氣有嚴重深遠影響。本文其次利用計量經濟模型分析：一、影響臺灣空屋率的主要原因，藉此解釋臺灣各地區不同的空屋狀況；二、空屋率與價格間之相互關係，並計算臺灣地區各縣市歷年自然空屋率，以此探討現行空屋率是否合理；三、利用信義房屋公司之仲介資料，分析在市場上空屋所有權人之屬性及住宅屬性對住宅成為空屋機率之影響。最後，針對過去空屋現況與上述研究，研擬提高空屋利用之策略，並建議政府檢討國宅政策，有效利用空屋，從根本上解決日益嚴重之住宅問題。 / According to 1990 Taiwan's housing census, the homeowner occupancy rate was 78.44% and the vacancy rate was 13.29%. The result compared with homeowner occupancy rate 79.11% and vacancy rate 13.09% of 1980 census, it was not much different during the past 10 years. Comparing with the reasonable vacancy rate, 4-5% in the most western countries, the-vacancy rate in Taiwan was very high obviously. What are the implication, reasons, and impacts of high vacancy rate? Does it imply the expectation of high capital gain of housing investment as well as the low holding costs and rents in Taiwan? The most critical issue is what kind of housing policy should be proposed to solve the problems of high housing vacancy. 　　This thesis used housing census data and under minimum use of electricity data of Taiwan Power Company to clarify the phenomenon of housing vacancy in Taiwan during every past year. ffe found that housing vacancy rate was always high, 14.58% in average (1.2% in standard deviation) during 1980-1992. Up to the end of 1993, the stock of vacant house was about 760,000 units and the vacancy rate was about 14%. ffe then established econometric model to analyze the following topics: 　　(1) the reasons of high vacancy rate in Taiwan; 　　(2)the relationship between vacancy rate and housing price, and then to caculate the natural vacancy rate of each city in Taiwan; 　　(3)the possibility of a housing unit to be vacant was effected by characteristics of housing itself and its homeowner. 　　Finally, we suggest some housing strategies and policies to solve the high vacancy issue to the government.

動態規劃的問題並不一定都存在封閉解(closed form solution)，即使存在，其過程往往也相當繁雜。本研究擬以 Gerrard & Haberman (2004) 的模型為基礎，並使用逼近動態規劃理論解的數值方法來求解，此方法參考自黃迪揚(2009)，其研究探討在有無封閉解的動態規劃下，使用此數值方法求解可以得到 逼近解。本篇嘗試延伸其方法，針對不同類型的限制，做更多不同的變化。Gerrard & Haberman (2004)推導出退休後投資於風險性資產與無風險性資產之最適投資策略封閉解， 本研究欲將模型投資之兩資產衍生至三資產，分別投資在高風險資產、中風險資產與無風險資產，實際市場狀況下禁止買空賣空的情況與風險趨避程度限制資產投資比例所造成的影響。並探討兩資產與三資產下的投資結果，並加入不同的目標函數:使用控制變異數的限制式來降低破產機率、控制帳戶差異部位讓投資更具效率性。雖然加入這些限制式會導致目標函 數過於複雜，但是用此數值方法還是可以得出逼近解。 / Dynamic Programming’s solution is not always a closed form. If it do exist, the solution of progress may be too complicated. Our research is based on the investing model in Gerrard & Haberman (2004), using the numerical solution by Huang (2009) to solve the dynamic programming problem. In his research, he found out that whether dynamic programming problem has the closed form, using the numerical solution to solve the problems, which could get similar result. So in our research, we try to use this solution to solve more complicate problems. Gerrard & Haberman (2004) derived the closed form solution of optimal investing strategy in post retirement investment plan, investing in risky asset and riskless asset. In this research we try to invest in three assets, investing in high risk asset, middle risk asset and riskless asset. Forbidden short buying and short selling, how risk attitude affect investment behavior in risky asset and riskless asset. We also observe the numerical result of 2 asset and 3 asset, using different objective functions : using variance control to avoid ruin risk, consideration the distance between objective account and actual account to improve investment effective. Although using these restricts may increase the complication of objective functions, but we can use this numerical solution to get the approximating solution.

本研究的目的為研究國中九年級學生在學習機率單元前後，對於機率概念的了解與代表性偏誤、可利用性偏誤Kahneman＆Tversky(1974)）及結果取向判斷偏誤(Konold1989)的異同。主要採量的分析，以自訂的問卷評量工具對受試者進行筆試。研究之樣本為學過國小簡單機率的國中九年級學生，問卷實施的方式為筆試，研究過程設計了前測、後測兩份試卷，並在施測前進行預試來評估試題信度、效度。前測問卷施測目的在探討學生在教學前利用常識、直觀來解題所可能造成的機率偏誤。教學過後也進行後測問卷的施測，並利用前後兩次施測的結果，探討國中生在教學前後機率判斷偏誤上的差異性。本研究之對象為中學九年級學生，共148位學生來進行施測，研究者依學生數學分組教學之成績，分為高分群、中間群、低分群，依據性別和分群兩個變項來進行分析。分析結果發現： 1.性別變項無顯著差異，故教學過程中不用特別考慮性別差異。 2.分群分析結果如下： (1)結果取向 在一次投擲問題中，前、後測問卷分析結果發現，中、高分群前後測整體表現皆無偏誤的比例較低分群來的少。 (2)代表性偏誤 在代表性偏誤中的正時近效應與負時近效應的問題中，低分群在前、後測仍犯有偏誤比中、高分群前後測都犯有偏誤的比例來的高。而改變樣本空間問題中，中、高分群在前、後測皆沒有偏誤的比比例較低分群高。複合樣本問題中探討代表性偏誤，低分群在前、後測仍然有偏誤的比例較中、高分群前、後測犯有偏誤高。 (3)可利用性偏誤 三群在前、後測的綜合表現並無顯著差異。 / The study aims to explore the differences of judgmental heuristic and biases on representativeness, availability (Kahneman &Tversky, 1974) and outcome approach (Konold, 1989) in terms of comprehension of probability concepts by ninth graders before and after studying the subject. The results are based on a quantitative analysis of the data collected from two sets of paper-and-pencil self-designed questionnaires. Pre-test questionnaire is meant to explore students’ potential probability biases when they work out the problems based on their previous knowledge and intuition prior to any instruction, while post-test questionnaire is conducted after instruction. The subjects in our experiment are composed of one hundred and forty-eight ninth graders who have only learned some basic probability concepts in primary school, and are classified into high-, mid- and low-scorer groups based on their previous academic performance. The findings suggest that: 1. Gender effect is not significantly different, so there is no need to pay attention to the gender difference in teaching process. 2. The results of analyses for different groups are listed in what follows. (1) Outcome approach: In the problem of tossing a coin, the results of pre-test and post-test indicate that the proportion of subjects who are without biases is higher in mid- and high-scorers than that of low-scorers. (2) Representativeness bias: In the problem of positive recency effect and negative recency effect, the proportion of committing biases is higher in low-scorers than that of mid- and high-scorers in both pre- and post-tests. In the problem of changes in sample spaces, the proportion of lack of biases is higher in mid- and high-scorers than that of low-scorers. In the composite-event problem that deals with representative biases, the proportion of committing biases among low-scorers is higher than that of mid- and high-scorers in both pre- and post-tests. (3) Availability bias: There is no significant difference in the overall performance of pre- and post-tests among the three groups.

人民幣是否可能成為另一個重要的國際貨幣，甚至挑戰美元的國際地位？此即本論文的問題意識。對此，本論文進一步提出三個研究問題：一是如何測量當前的人民幣國際化程度？二是如何測量當前的人民幣資本開放程度？三是資本開放對於人民幣國際化程度的影響為何？ 為此，本研究利用主成分分析（PCA），以建構人民幣國際化程度（CIDI）與人民幣資本帳開放程度（CAOI）。其次再利用動態追蹤資料模型──系統一般動差估計法（SGMM），以檢證各項人民幣綜合競爭力對於貨幣國際化程度的影響。最後，本研究進一步梳理人民幣資本帳開放的進程，並結合上述所有實證分析的結果，進而預估漸進資本開放下人民幣國際化的前景。研究對象包括人民幣在內的33種國際貨幣，研究時間則起自1999年歐元成立，迄於2009年。 本論文的發現三：一是，當前人民幣國際化程度進展相當快速。但截至2009年年底，人民幣國際化程度還很低，遠落後於美元、歐元、日圓，以及英鎊等主要國際貨幣。不僅如此，人民幣國際化程度也遜於俄羅斯盧布、巴西里拉，以及印度盧比等開發中國家所發行的貨幣。 二是，過去10年來，人民幣資本帳開放程度不升反降，截至2009年年底，人民幣的資本帳開放程度維持在零，這表示：人民幣是世界上管制最為嚴格的貨幣。相對而言，美元、歐元、日圓，以及英鎊的資本帳開放程度至少都在70％以上，特別是英鎊的資本帳開放程度更趨近於完全開放。 三是，根據SGMM的實證結果顯示，網路外部性、經濟規模、金融市場規模、貨幣穩定度，以及資本開放程度都是影響貨幣國際化程度的關鍵因素。在此基礎上，本研究利用發生機率（odds ratio），以計算不同資本開放情境下，人民幣成為前10大國際貨幣的可能性。結果顯示，如果人民幣的資本帳開放到73％左右，人民幣便可擠進前10大國際貨幣（發生機率為65.6％）。 不過，這只是最為保守的估計。原因有二：一是，隨者中國經濟實力的崛起，以及人民幣預期升值的脈絡下，國際市場對於人民幣的需求原本就很高。此時，人民幣資本帳如果能適時開放，則人民幣的國際持有將大幅增加。換言之，本研究沒有考量到，各貨幣競爭力因素與資本開放程度之間的加乘效果。 二是，資本開放不僅直接對貨幣國際化程度產生影響，也會透過擴大金融市場規模與網路外部性等其他貨幣競爭力因素，間接對貨幣國際化程度造成影響。這間接效果，本研究也沒有考量到。因此，可以預期的是，只要人民幣資本帳能夠漸進開放，人民幣國際化的前景將比本研究所預估的高出許多。 / This paper discusses whether the Renminbi (RMB) will become an international currency, even challenging to the U.S. dollar. In order to examine above question, this paper take the following three steps: 1. By using principal component analyses (PCA), this paper constructs two indices: currency internationalization degree index (CIDI) and capital account liberalization degree index (CAOI); 2. By using dynamic panel data model-system generalized method of moment (SGMM), this paper analyzes factors affect the CIDI, including economic and trade size, financial system, network externalities, confidence in the currency’s value, and CAOI; 3. According to the PCA and SGMM results, this paper calculates the odds ratio of RMB becoming important international currency. The reserch achieved the following results. First, the degree of internationalization of the RMB progress very fast, but the RMB CIDI is still very low, its CIDI far behinds the dollar, euro, Japanese yen, and pounds. Second, over the past 10 years, RMB CAOI is not increased but decreased. Its CAOI is at zero in 2009, this means that: the RMB is the most stringent controls in the world currency. In contrast, U.S. dollars, euros, yen, and pound CAOI are at least in more than 70%. Third, according to the SGMM results, economic size, financial system, network externalities, confidence in the currency’s value, and CAOI are key factors affect the CIDI. Based on this output, this paper forecasted that if the RMB CAOI is open to about 73%, RMB could be squeezed into the top 10 of the international currency. (The odds ratio is 65.6%) It is noteworthy that this is only the lowest estimates. This is because that this paper did not consider the interaction effects of each currency competitiveness factors and CAOI. Therefore, if RMB CAOI continues open, the prospect of RMB CIDI is much higher than estimated by this paper.

住宅抵押貸款保險(Mortgage Insurance)為管理違約風險的重要工具，在2008年次級房貸風暴後更加受到金融機構的關注。為了能更準確且更有效率的預測房價及合理評價住宅抵押貸款保險，本文延續Christoffersen, Heston and Jacobs (2006)對股票報酬率的研究，提出新的GARCH模型，利用Inverse Gaussian分配取代常態分配來捕捉房價序列中存在的自我相關以及典型現象(stylized facts)，並且同時考慮房價市場中所隱含的價格跳躍現象。本文將新模型命名為IG-GARJI模型，以便和傳統GARCH模型作區分。由於傳統的GARCH模型在計算保險價格時，通常不存在封閉解，必須藉由模擬的方法來計算價格，會增加預測的誤差，本文提供IG-GARJI模型半封閉解以增進預測效率與準確度，並利用Bühlmann et al. (1996)提出的Esscher transform方法找出其風險中立機率測度，而後運用Heston and Nandi (2000)提出之遞迴方法，找出適合的住宅抵押貸款保險評價模型。實證結果顯示，在新建房屋市場中，使用Inverse Gaussian分配會比常態分配的表現要好；對於非新建房屋，不同模型間沒有顯著的差異。另外，本文亦引用Bardhan, Karapandža, and Urošević (2006)的觀點，利用不同評價模型來比較若房屋所有權無法及時轉換時，對住宅抵押貸款保險價格帶來的影響，為住宅抵押貸款保險提供更準確的評價方法。 / Mortgage insurance products represent an attractive alternative for managing default risk. After the subprime crisis in 2008, more and more financial institutions have paid highly attention on the credit risk and default risk in mortgage market. For the purpose of giving a more accurate and more efficient model in forecasting the house price and evaluate mortgage insurance contracts properly, we follow Christoffersen, Heston and Jacobs (2006) approach to propose a new GARCH model with Inverse Gaussian innovation instead of normal distribution which is capable of capturing the auto-correlated characteristic as well as the stylized facts revealed in house price series. In addition, we consider the jump risk within the model, which is widely discussed in the house market. In order to separate our new model from traditional GARCH model, we named our model IG-GARJI model. Generally, traditional GARCH model do not exist an analytical solution, it may increase the prediction error with respect to the simulation procedure for evaluating mortgage insurance. We propose a semi-analytical solution of our model to enhance the efficiency and accuracy. Furthermore, our approach is implemented the Esscher transform introduced by Bühlmann et al. (1996) to identify a martingale measure. Then use the recursive procedure proposed by Heston and Nandi (2000) to evaluate the mortgage insurance contract. The empirical results indicate that the model with Inverse Gaussian distribution gives better performance than the model with normal distribution in newly-built house market and we could not find any significant difference between each model in previously occupied house market. Moreover, we follow Bardhan, Karapandža, and Urošević (2006) approach to investigate the impact on the mortgage insurance premium due to the legal efficiency. Our model gives another alternative to value the mortgage contracts.

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.