51 |
封閉式等候網路機率分配之估計與分析 / Estimation of Probability Distributions on Closed Queueing Networks莊依文 Unknown Date (has links)
在這一篇論文裡,我們討論兩個階段的封閉式等候線網路,其中服務時間的機率分配都是Phase type分配。我們猜測服務時間的機率分配和離開時間間隔的機率分配滿足一組聯立方程組。然後,我們推導出非邊界狀態的穩定機率可以被表示成 product-form的線性組合,而每個product-form可以用聯立方程組的根來構成。利用非邊界狀態的穩定機率, 我們可以求出邊界狀態的機率。最後我們建立一個求穩定機率的演算過程。利用這個演算方法,可以簡化求穩定機率的複雜度。 / In this thesis, we are concerned with the property of a two-stage closed system in which the service times are identically of phase type. We first conjecture that the Laplace-Stieltjes Transforms (LST) of service time distributions may satisfy a system of equations. Then we present that the stationary probabilities on the unboundary states can be written as a linear combination of product-forms. Each component of these products can be expressed in terms of roots of the system of equations. Finally, we establish an algorithm to obtain all the stationary probabilities. The algorithm is expected to work well for relatively large customers in the system.
|
52 |
銀行住宅擔保品鑑估價格與契約價格之關係 / The relationship between the contract price and the estimated price of residential collateral by financial institutions丁嘉言, Ting, Chia Yen Unknown Date (has links)
銀行在面對借款人以不動產申請抵押貸款時,產生對住宅擔保品估價之需求,以為債權之確保。然銀行的估價過程與一般估價最大不同,肇因於其估價前,擔保品本身已先產生一組買賣契約價格。過去研究指出,估價會嘗試以某些較易取得的價格資訊作為定錨點(anchor),藉以調整並成為最後的價格。而我國不動產交易價格資訊不透明,契約價格往往由借款人提供的情況下,銀行內部估價人員可能因資訊不易取得、定錨效果,在擔保品的鑑估結果上受到契約價格影響,倘有心人士欲藉此獲得高額貸款、牟取不法利益,將損及銀行債權,即使採用自動估價系統降低人為影響因素,因資料來源不佳,只會產生所謂「garbage in garbage out」的結果。據此,如何分辨契約價格是否具有參考力變成為關鍵,亦為本文欲補足的研究缺口。
本文採用國內某銀行臺北市不動產擔保品8,348筆估價資料為樣本,建立以挑選契約價格是否具有參考力的機率預測模型,尋求影響能判定契約價格是否具有參考力的主要因素,並研究在最適的機率界限下,篩選出具有參考力的契約價格樣本。而研究結果所建立的模型,其預測並篩選出的契約價格樣本均較未經模型篩選者,對擔保品價格之估計有顯著提升。因此本研究所建立的契約價格篩選模型確能提升銀行估價準確性,使不動產擔保品鑑估價格的形成過程中,獲得更多可靠的參考資訊,降低人為操縱的空間,並在成交價格資訊不足的情況下,提升估價人員對契約價格的辨識能力。 / In the face of the borrower to apply for a mortgage of real estate, financial institutions have estimated the price of the collateral requirements to protect the debt claim. However, the biggest difference with the general valuation and that of financial institutions, valuation of its causes before the collateral itself has produced a first sale contract price. In the past research that one attempts to estimate the price of some greater access to information act to anchor in order to adjust and become the final price. Because financial institutions are not easy to obtain price information on real estate transactions in Taiwan, price information is often provided by the borrower. A small number of loans borrower deliberate fraud to forgery or false irrigation Contract price sale and purchase agreement in order to obtain high credit. Even with the automatic valuation system to reduce the human impact factor, due to poor data sources, it will only produce so-called "garbage in garbage out" of the results. Accordingly, how to tell whether the contract price to a reference force becomes critical, and also in this article want to complement the research gap.
We adopt 8,348 estate collateral valuation data in Taipei City of a domestic bank for the sample to establish a binary logistic regression model. And we try to seek the main factors that determine whether the contract price of the reference force, and find out the optimal cutoff point, filter out of a sample of the contract price of the reference force. The results confirm the model in this paper. The selected samples of the contract price is estimated that the price of collateral significantly improved compared with those without filtering. Therefore, the model established in this study can really improve the accuracy of bank valuation. Enhance the recognition ability of the bank's internal appraisers on the contract price in the lack of transaction price information.
|
53 |
台灣選舉事件與台指選擇權的資訊效率李明珏, Li, Ming-Chueh Unknown Date (has links)
台灣特殊的兩黨對立政治環境及幾乎每年都會有的固定選舉,使得政治的不確定性深深的影響著國內的投資環境及投資人心態。本研究便是要探討,2002/1/1~2006/1/16 研究期間台灣的投資人在選舉前後的投資行為,是否真如大家所預期的,會受到台灣選舉事件的影響。
本研究首先利用適當的機率密度函數模型及選擇權市場資訊來導出隱含的風險中立密度值。再利用這些風險中立密度值,求出各個選舉事件相對應的機率分配圖形,並透過其機率分配圖形及波動率指數等統計值於投票日前後的變化來觀察某一選舉事件前後投資者的反應。
研究結果發現:1. 選舉事件的發生確實會影響投資者的心理,且投資者會透過選擇權市場有效率的反應預期的未來股價指數分佈情況。2. 越大型、越具爭議且全國性的選舉結果,其選舉期間機率分配圖形及波動率指數具有較高的波動性。3. 一般而言,選舉過後市場不確定因素降低,將使投資者對於股市的預期較為一致和樂觀。而若這個選舉結果使投資者感到意外,因而增加了市場的不確定性,則選後機率分配圖形及波動率指數的改變反而會更為明顯。4. 在此研究下對數常態混合法比傳統的 Black-Scholes 方法產生較低的誤差值,因此就實證的分析上能提供更好的配適。 / This research examines the behavior of investors during election periods from January 1st 2002 to January 6th 2006 in Taiwan. The research includes a few steps. First, we adopted a proper probability density function composed of stock index options data to construct the implied distribution. Then, when changing the whole shape of the risk-neutral implied distribution, the volatility indexes, and the statistics of the implied distribution, we observed investors' response around a specific election event.
According to the empirical results, we found that: 1. An election event would influence investors’ behavior, and investors tend to reflect their expectation of future stock index in the option market in an efficient way. 2. The result of a large-scale and more disputed nationwide election will cause a higher fluctuation in both the implied distribution and the volatility index. 3. In general, the factor resulting from investors’ uncertainty of the market is likely to reduce after the election, which makes investors’ relatively unanimous and optimistic expectation of the stock market. However, if this election result surprises investors, their uncertainty of the market will increase, and thus the changes of the implied distribution and the volatility index become quite obvious. 4. The in-sample performance of the lognormal mixtures method employed in the research is considerably better than that of the traditional Black-Scholes model by having a lower root mean squared error.
|
54 |
不確定情況下台北市不動產開發投資決策之研究─蒙地卡羅模擬方法之運用黃勝榮, HUANG,SHENG-RONG Unknown Date (has links)
不確定的時代VS不動產開發抽資決策
1.影響不動產投資之各種因素均具有不確定性:
(1) 收益因素:售價、租金等。
(2) 成本因素:土地市價、建築材料、工資、利率等。
2.傳統確定性決策模式已不適用於不確定的時代。
如果在不確定情形下正確地作不動產開發投資決策? 蒙地卡羅模擬模型正符合需要。
貳、研究目的
1.修正蒙地卡羅模擬模型,使其適用於台北市不動產開發投資。
2.在考慮風險情況之下,如何運用機率性模型之模擬結果作出投資決策?
3.考慮風險情況與不考慮風險情況所作決策之間是否不同? 亦即以蒙地卡羅作出之決
策與以確定性模型作出之決策是否有所不同?
參、研究方法
先修正蒙地卡羅模擬方法運用之理論基礎,再以修正過之方法作個案研究,最後再以
個案研究之結果,作一般化之建議。
本篇論文所用到之研究工具為蒙地卡羅模擬模型。並以專家意見調查法及效用理論作
修正。
肆、研究範圍
1.針對台北市不動產開發的投資決策作研究,亦即模擬測試之外在環境為台北市。
2.就同一塊基地之開發,評估其不同的開發策略,並作決策。
3.以開發者之立場為本篇論文研究之立場。
伍、研究假設
1.對任何不確定之變數,其變數值均可以機率分配型態表示。
2.每位專家對變數的真正機率分配並非完全知道,但亦並非完全不知道。
3.每位專家受其經驗及接觸環境限制,個別很難估計出正確的變數機率分配。結合多
數專家之意見而產生之機率分配,可縮小誤差範圍。
4.不確定變數的變數值,乃依其機率分配型態隨機產生。
陸、研究步驟
一、擬定開發策略
作成決策的第一個階段為擬定經營策略。擬定策略受經營者的企業目標和外在環境影
響。
二、選擇評估標準
在考慮時間因素,並且考慮投資報酬之絕對量和相對量之影響之下,同時採用凈現值
( NPV)和內部報酬率 (IRR)為評估標準。
三、擬定確定性模型
以現金流量模型為理論基礎,將各種收益和費用變數,結合成會計方程式。再利用各
變數之間的關係,擬出關係方程式,將模式加以簡化。
四、專家意見調查及整理
由不動產專家估計每一變數之變數值,並對各可能之狀態變數,估計其機率分配。
故為了簡化對專家解釋機率意義的過程,在意見調查中,每個專家僅估計每個變數之
最低–最可能–最高三個估計值,並且指定三個估計值的發生機率為 10%,80%,10.
% 。所諮詢的專家樣本數為 30.位。
五、區分狀態變數和控制變數
以敏感性分析加以區分。假設變數為 X,評估標準為 NPV,則 X變化 1.%,NPV 變化
大於或等於 1.%時,X 對NPV 的影響較大,即視為狀態變數。反之,X 變化 1.%,NP
V 變化小於 1.%時,X 即視為控制變數。
六、結合狀態變數之機率分配
經專家對每個變數估計出三個變數值後,必須考慮如何結合多位專家的意見。結合專
家意見的方法有三種:加權法、交感法、測度法。本篇論文採用加權法作為結合各專
家意見的理論基礎。
七、蒙地卡羅模擬
首先將狀態變數的機率分配函數結合確定性模型的架構設計出可執行的電腦程式,作
為模擬工具。為求操作簡便起見,本篇論文採用具有亂數函數的LOTUS 1-2-3 套裝軟
體作為模擬工具。
八、比較分析
1.NPV 和 IRR之期望值和變異數比較。
2.NPV 和 IRR之期望值和損失機率比較。
九、投資決策
1.以期望值較高,變異數及損失機率較低為較優策略。
2.找出期望值╱變異數和期望值╱損失機率之無異曲線,以效用較高者為較優策略。
3.以無法量化之因素,如開發者之企業目標,開發者之個人喜好等,衡量難以取捨之
策略。
|
55 |
多變量模擬輸出之統計分析許淑卿, XU, SHU-GING Unknown Date (has links)
本論文共一冊,分八章八節。
內容:本論文所擬探討之對象為多變量統計分配函數模擬(Simulation)之最佳停止
法則問題(Optimal Stopping Rule Problem ),此類問題之目的在於如何利用盡量
小的樣本數之觀察值來求得未知母數(Unknoron Parameter)的信區間(域)(Co-
nfidence interval )(Confidence Region),而此信賴區間(域)之寬度(Width
)及包含機率(Coverage Probability)均已事先指定。
以往研究對象多傴限於單變量統計分配函數,而多變量統計分配函數模擬之最佳停止
法則問題,仍尚在研究階段,因此本論文之重點乃在於探討如何求得滿足最佳停止法
則之最小樣本數。在此以多變量常態分配函數為重心,並進而嗜試推廣至其他多數量
統計分配函數。
|
56 |
購屋方案選擇評估指標建立之研究 / The Study on Housing Choice Decision-Making Factors for Home-Buyer---An Empirical Analysis of Taipei-Taoyuan Areas黃國保 Unknown Date (has links)
住宅,不只是一個房子,還是一個家的所在。所以購屋,當然是一生中重大的決定。而與住宅相關的價格、環境、交通、品質、交易安全等這些都需要有專門的知識與經驗。另外住宅還涉及了很多風水、信仰、喜好等沒有對、錯的個人價值觀等問題。而且一生中發生的次數不多,不容易累積足夠的知識與經驗,所以要從購屋市場供給的產品中,找到完全符合自身需求住宅,不但一般人不容易做到,即使不動產的專業相關人員,由於購屋過程涉及多樣專業,亦不能面面俱到,作出最佳的購屋決策。本研究藉由文獻回顧與實證分析,就這個即重大又複雜的購屋問題,探討三個主題,其研究結果之結論如下:
一、我國各購屋方案可量化購屋影響因素,所存在的價格差異性
在實證結果部分,不論從地區上的分類,或是從時間上的分類,經自我選擇偏誤問題校正後。其拍賣市場相對於搜尋市場的住宅價格折價百分率確有差異,折價差異大約在1.53% ~3.69%間。實證結果顯示,購屋時機的不同階段呈現價差差異性,在2005~2007年第一季期期間景氣狀況較佳時價差不明顯之外,由不同地區與第一階段購屋時機(2003~2004) 景氣狀況較差時結果都顯示拍賣市場相對於搜尋市場的住宅價格仍有17%~24%明顯的折價現象。然替選方案之購屋影響因素,除了價格因素之價差外,仍有可量化之住宅條件因素與可量化之購屋者條件因素顯示其重要性。
二、不動產從業人員和一般人購屋決策的差異性
在這個主題裡,我們利用AHP(分析層級分析法)探討了與不動產密切的不動產從業人員和一般的購屋者,由不同地區來看,其最大的不同,是在台北縣及桃園縣的「不動產從業人員」購屋者,都最重視「住宅條件」,但在台北市的「不動產從業人員」的選擇上,卻優先考慮的是「價格」。
三、消費者購屋選擇決策的影響因素之評估指標及方案分析
我們利用AHP(分析層級分析法),在台北市、台北縣、桃園縣三個地區,分別進行問卷調查、評估指標分析。發現在最優先考慮購屋方案的問題上,在五個購屋替代方案預售屋、成屋、金拍屋、銀拍屋、法拍屋,消費者最可能的購屋方案都是選擇成屋,權重都是五個替選方案中最高者。從此一結果結果得知,就購屋者認知的效用而言,成屋優於預售屋,且優於各拍賣市場的金拍、銀拍、法拍。
影響消費者選擇購屋決定的四個評估指標為價格、住宅條件、交易制度及購屋者條件四個因素,其中購屋者最重視的是「價格」及「住宅條件」,特別是價格,在台北市不論是「不動產從業人員」及「一般購屋者」、台北縣的「一般購屋者」及桃園縣「一般購屋者」,其權重都是四個評估指標中最高者。「價格」仍是大部分購屋決策中最重要的影響因素。但是不是有坊間所提的:「沒有賣不出去的房子,只有賣不出去的價格」,那般極端強調「價格」就是一切呢?仍值得商榷。
另外,在評估指標之影響因素細準則方面,從「價格」準則中其第三層細準則三個因素價差、交易費用、貸款中都為前三項之首選,可見得在購屋市場中建立「價格」資訊、秩序是很迫切的。在影響房屋住宅條件的因素中內環境、外環境為前三項之首選,而內環境為不論地區或各種購屋著都為重要考慮因素。「不動產從業人員」及「一般購屋者」的受訪者,除了價差為共同考量因素外,其差異性為前者亦考慮貸款,而後者加入交易費用之考量。以地區性來看只有桃園縣之不動產從業人員較重視環境,其他地區仍以價差為首選之考量因素。 / A residence is not just a house but also a place where people set up their homes. Purchasing a house is certainly a very important decision throughout everyone’s lifetime. However, the elements such as pricing, environment, traffic, quality, and transaction security that are closely in connection with such an important choice all take specialized knowledge as well as experiences. Besides, to appraise a residence also involves some personal view of values such as fate, beliefs, and fondness, which are rather difficult to be thought of as good or bad. Moreover, purchasing a house is something that isn’t going to happen frequently throughout one’s life, so there won’t be many chances to accumulate enough knowledge and experiences in this field. Not only is it difficult for common public to choose, among the supply of housing market, a residence that would completely meet their own demand but it is quite a challenge for a professional real estate agent to make a decision on how to purchasing a most suitable residence as the process is often so diversified and specialized. In this study, by means of reviewing related documents and analysis, three main subjects based on this critical and complicated issue of house purchasing have been explored, and the conclusions of the research are given as follows:
1. The price differences among quantifiable and determination factors of each house purchasing alternatives.
In practices, it is verified that whether it is classified based on regional divisions or based on timing of purchasing, differences do exist in housing price discount percentage between auctioning market and searching market after correcting the estimate bias of self-selection, and differences of price discount fall roughly between 1.53% and 3.69. It is also verified that, by observing various districts in the first house purchasing stage (2003~2004), a period falling in economical recession, price differences do vary with different purchasing timings in the stage. The price differences of the auctioning market relative to searching market appear significant price discount percentage ranging from 17% to 24%. The only exception to this case might be during each of the first seasons in the years from 2005 to 2007, a period of booming economy, in which price differences didn’t seem so significant. However, when it comes to decisive factors of alternative house purchasing choices, there are still some quantifiable elements of resident condition and quantifiable purchaser elements that can be evaluated in addition to price differences.
2. The difference in making decision on house purchasing between real estate professionals and ordinary buyers.
In this theme, we utilize AHP to explore the interaction between real estate professionals who are closely related to this industry and ordinary buyers. From the regional point of view, the most significant variance appears in Taoyuan County and Taipei County where real estate professionals and ordinary buyers both value “resident conditions” as a most important factor while in Taipei City real estate professionals would view the price as the first priority.
3. Evaluation indicators and alternatives analysis of the factors which affect consumer in making decision on house purchasing.
Adopting AHP as an analytical method, we carried out questionnaire survey in Taipei City, Taipei County, and Taoyuan County as well as analyze their appraisal indicators. The findings are that, among five purchasing programs, namely newly completed houses, houses ordered before being built, houses auctioned by court, houses auctioned by banks, and houses auctioned by private financial sectors, the most likely case that consumers will choose is that of newly completed houses.
The four evaluation indicators that have affected consumers’ decision on buying a house are price, residential conditions, transaction system, and purchasers’ conditions. Among them, price and residential conditions are given more weight by consumers, but price alone possesses the highest weight to which both real estate professionals and ordinary buyers in Taipei City, ordinary buyers in Taipei County, and ordinary buyers in Taoyuan County all have given. Price is still the most influential factor when making a decision on house purchasing. However, is it realistic that price is so decisive as to reach to the extent like many people say “There is not any unmarketable house but an unacceptable level of price” ? The extremely aspect of this view needs be further considering deliberately.
As for the influential factors set up under the four evaluation indicators, here are the analyses: The three factors (price difference, transaction fee, and loan) of the first indicator named “housing price” are the first three valued factors either observed based on regional variance or based on purchasers. It can therefore be realized that how important and urgent it is to establish “price” information of the house purchasing market. In the second appraisal indicator named residential conditions, internal/external environment are the first three valued factors. However, internal environment seems to have more priority, and that is quite consistent with the traits of our fellow people, most of whom think only to care about themselves. Such phenomenon is quite common in many residential communities nowadays.
The real estate professionals and ordinary buyers both value “price difference” as a most important factor while the former added the factor of transaction fee, and the latter added up loan. From the difference areas point view, only Taoyuan County value “environment” more important than others. The rest of areas value “housing price” is the most important factor than others.
|
57 |
從事件自我相關程度探討訊息呈現方式對風險知覺之影響廖楷民, Liao, Kai-min Unknown Date (has links)
以機率或頻率方式呈現訊息對風險知覺評估的影響,過去的研究有不一致的結果,原因可能來自於判斷事件與受試者的自我相關程度不同,而引發捷思或系統性的訊息處理歷程。實驗一發現當事件的自我相關程度高,受試者會採用系統性的認知處理,而事件的自我相關程度低時,受試者會採用捷思性的認知處理。實驗二詢問受試者認為以機率或頻率方式呈現訊息何者較清楚明確,結果發現有77.5%的受試者認為以頻率方式呈現訊息較以機率方式呈現訊息清楚明確。實驗三操弄「事件自我相關程度」與「機率或頻率方式呈現訊息」,結果發現當事件為高自我相關時,機率或頻率方式呈現訊息在風險知覺的判斷上沒有差異;而當事件為低自我相關時,則頻率方式呈現訊息的「風險知覺」與「事件聯想負向詞數量」均大於機率方式呈現訊息。另外,當事件為低自我相關時,訊息明確度與事件聯想負向詞數量對風險知覺有顯著的預測力。以上的結果支持不同事件自我相關程度會引發捷思或系統性訊息處理,而頻率方式呈現訊息較機率方式呈現訊息清楚明確的原因,與Slovic等人(2000)提出頻率較具體,容易想像的推論符合,但不支持Gigerenzer和Edwards (2003)認為機率的參照類別不清楚的假設。此外,自我相關程度與可得性捷思為影響頻率或機率方式呈現訊息對風險知覺判斷結果不一致的重要變項。
|
58 |
最低保證給付人壽保險附約之風險分析 / Risk analysis for guaranteed minimum benefit life insurance riders李一成 Unknown Date (has links)
保險人因提供最低保證給付之投資型商品,使公司亦涉入投資風險。本研究旨在探討最低保證給付人壽保險附約之風險分析。首先利用隨機模型建構投資者帳戶價值的動態過程,進而推導出在未來時點帳戶發生餘額不足之機率及其所符合的偏微分方程式。並藉由數值方法-有限差分法,求出投資帳戶餘額不足之機率。最終,以不同的參數選取之下,進行敏感度分析,探討參數值的設定對於帳戶發生餘額不足之機率的影響。本研究結果可以提供保險公司與監理機關,作為日後發行保證給付商品時,一項風險管理上的考慮因素。
研究結果可以歸納為兩點結論:
1. 在市場因素中,投資帳戶連結之標的報酬率與帳戶餘額不足機率呈現反向變動,而波動度則是與帳戶餘額不足機率呈現正向變動。在兩因素同時考慮下,當報酬率愈高且波動度愈低,投資帳戶發生餘額不足的機率會愈低。當波動度愈高且報酬率愈低時,帳戶餘額不足機率則會愈高。其兩者的力量會相互抵銷,對投資帳戶餘額不足之機率的影響需視何者的力量較強而定。
2. 在條款設計的因素中,保證附約相關費用率、保證提領比率與保證提領期間對於投資帳戶發生餘額不足機率的影響皆呈現正向的關係。而投資帳戶期初的價值則與帳戶餘額不足機率呈現反向變動。其中保證提領比率對於投資帳戶的價值影響最大,其帳戶餘額不足機率之變動百分比相較於其他因素而言,變動幅度較大,範圍皆大於4%以上,甚至高達37.11%。 / Insurers have investment risks because they issue the guaranteed minimum benefit life insurance riders. Therefore, the purpose of this thesis is analyzing the risk for the riders. In the context, we implement numerical PDE solution to compute the ruin probability of separate account which is the probability that guaranteed minimum benefit life insurance riders will lead to financial insolvency under stochastic investment returns. Moreover, we will do sensitivity analyses to discuss the two aspects, market factors and contract designs, how to influence the ruin probability.
Finally, we conclude two main results:
1. For market factors, the rate of investment return is negatively related to ruin probability; however, the volatility is positive correlation.
2. For contract designs, the results show negative correlation between ruin probability and insurance fee, withdrawals, and withdrawal period. But the initial account value shows positive correlation.
|
59 |
信用風險模型研究--無金融機構往來紀錄之借款人評等加強李文文 Unknown Date (has links)
目前國內銀行針對無擔保消費金融業務,不再僅是重視放款量,控制申請人的信用風險、提高授信品質,更是不能等閒以對的重點。如何建構信用評分機制,降低呆帳率和授信逾放比,以減少銀行損失、增加實質獲利,已成為國內銀行共同關切與努力的課題。本研究擬藉由對無擔保消費金融商品之研究,瞭解該類借款人之信用風險,透過建置信用評分模型,做為銀行決策之參考。
國內銀行在審核無擔保消費金融貸款時,因貸款件數多,大都使用信用風險評分模型評估借款人風險。但實務上常發生借款人無JCIC資料,可評估其違約風險。目前可查到的建立信用風險模型研究中並沒有針對無JCIC資料借款人之研究。如何強化信用風險模型對於此客群之評估為本研究的目的。最後,本研究亦提出了一些重要的未來研究建議,以供後續的研究作為參考。
|
60 |
投資型購屋者機率預測模型之建立 / The Probability predictive model of housing investors邱于修, Chiou,Yu Shiou Unknown Date (has links)
住宅為兼具消費及投資之雙重功能財貨,因此若從購屋動機劃分購屋族群,可以分為自住者及投資者,近年來受到國內房市呈現生氣蓬勃之景象及利率持續走低等總體經濟因素影響之下,出現越來越多以投資為主要目的之投資型購屋者,對於金融機構之購屋貸款業務來說,投資者之還款行為相較於自住者是比較不穩定的。故本文之研究目的即藉由探討自住者及投資者之購屋特徵異同,建立投資者之機率預測模型,預測某購屋者成為投資者之機率,提供一較為客觀之機率預測模型,供作金融機構放貸參考準則。接著進一步探討在不同機率界限(cutoff point)下之預測準確率,找出預測準確率最高之機率界限值,提高本模型之預測準確度;並探討金融機構在不同經營方針下之較適機率界限值。 / 本文使用台灣住宅需求動向季報之已購屋者問卷,建立二元羅吉特模型。研究結果顯示,區位在中心都市、高單價、小面積產品及大面積產品、預售屋及拍賣屋市場屬於投資型產品,而搜尋時間短、搜尋間數少、年齡較長、男性、無固定職業及家庭平均月收入較高者成為投資者之機率較高。接著,運用貝氏定理計算出預測準確率最高之機率界限值,結果當機率界限值為0.70時預測準確率最高,投資者達72.22%,自住者達80.07%。此外,並使用2007Q4的資料作樣本外驗證,投資者命中率為65.52%,自住者命中率為84.51%。最後,為提供金融機構運用,本文模擬兩種預測誤差在不同權重下對於金融機構所造成的損失,找出損失最少的機率界限值,結果皆是以0.70為最適機率界限值。 / Housing is dual function goods, consumption and investment, so if we separate the home buyers by their motives, they can be defined as two groups, owner-occupiers and investors. Recently, because the housing market is vigorous inland and the rates are fairly low, there are more and more home buyers buying houses for investment. To financial institutions, their payment behaviors are more instable, compare to owner-occupiers. So this article is aim to build a probability predictive model of housing investors by discussing the different home buying characters between owner-occupiers and investors. Therefore we can provide financing institutions a more objective method evaluating if they should lend money to the home buyers. Then we discuss the predictive accuracy with different cutoff points, finding the cutoff point with highest predictive accuracy, therefore we can elevate the model`s predictive accuracy. Besides, we also discuss the most optimal cutoff point for financial institutions under different administration principles. / This article builds binary logit model by the data of “Housing Demand Survey in Taiwan”. Our results suggests that if the houses in downtown、high unit price、big and small acreage、presale and court auction housing market belong to investing houses. And short search duration、few search items、older、male、non-constant job、higher income are getting higher probability to be housing investors. Then, we use Bayesian Theorem to figure out the cutoff point with highest predictive accuracy, and Our results suggests that 0.70 cutoff point with highest predictive accuracy , at that time, investor predictive accuracy is 72.22%, owner-occupier is 80.07%. Besides, we also do the out-sample test by the 2007Q4 data, the investor`s hit-rate is65.52%, the owner-occupier`s hit-rate is 84.51%. At the end, in order to provide financial institution to use, we give two predictive deviation different weights, to find the smallest loss cutoff point, the result all suggest that 0.70 is the most optimal cutoff point.
|
Page generated in 0.0627 seconds