在存活分析中，含有轉折點的指數分配（又稱二段式指數分配）的模式,常被拿來研究某些疾病的復發率，以決定其治療方式是否有效。然而在文獻上，對這一個模式的探討大都局限在單一母體上，其問題不外乎有兩個：一是檢定此一轉折點是否存在；二是估計此一轉折點。 　　本文將此一問題擴充，從一個母體提昇至兩個母體，比較兩個母體是否具有相同的轉折點、起始危險率或轉換率。基本上，我們使用了貝氏方法和古典方法來分析。 　　我們利用貝氏方法，推導出兩個母體在不同的已知條件下，各母數比值或差值的事後分配。但是他們的形式幾乎都很複雜，使得欲做進一步的分析，困難重重。因此，我們引進了 Gibbs 抽樣法，利用各完全條件事後分配，萃取出各邊際事後分配，以供推論之用。 　　而在古典分析中，我們係採用概似比值檢定法。而最大的問題在於轉折點未知時，我們不知其對數概似比的分配為何。我們除了介紹兩個文獻中估計轉折點的方法，我們更利用了自助法 (bootstrap) 來估計其對數概似比的分配，以供檢定之用。 　　對於這樣兩母體的比較，在醫學上、工業上甚具意義。本文不僅推導出其供比較用的統計架構，更提供了具體而實用的抽樣方法， 對這問題的分析，頗具貢獻。

轉折型時間序列在現實生活中常常可見，例如因戰爭、政策改變、罷工或自然界的條件劇變等，而使時間序列的走勢發生明顯的轉變。傳統上，對這種轉折型時間序列資料進行轉折點的偵測時，大部分均從事後的觀點，主觀上先行認定結構轉變發生的時點，而後再以檢定加以確認。但此種方法過於主觀，而且轉型並非一蹴可幾，若以單一的轉折點來解釋轉型的現象，似乎不太恰當。 　　有鑑於此，本文利用模糊轉折區間統計認定法，以事前的觀點，對具有平均數或變異數改變的轉折型時間序列進行轉折區間的認定。並以匯率及貿易餘額的實際例子，利用我們所提出的方法進行單變數及雙變數的模糊分類，進而求出個別及聯合的轉折區間。 / Structure-changing time series are often seen in daily life. For example, war, change of policy, labor strike, or change of natural phenomena result in obvious change of time series. Most of detection of change points for structure-changing time series take place afterwards. In this paper, we pre-sent a change periods detection method for trend time series using the concept of fuzzy logic. Empirical example about exchange rate and balance of international trade is illustrated with detailed analysis.

景氣循環的擴張、收縮期的認定，以及轉折點的預測，向來是經濟學家、政府機構、企業及一般大眾所關注的焦點。越能掌握經濟發展的狀況，而適切的提早做出反應，越能充分利用經濟情勢的不同，以達成獲利的目標，或是減少企業的虧損。 本文即嘗試以票券、債券、股票、外匯及金融機構等金融變數，透過Kaminsky, Lizondo and Reinhart (1998)用以建構銀行危機預警綜合指標之訊號法（Signal Extraction Approach），以及可以解釋logit模型係數之發生比率（odds ratio），分別結合二元 logit 模型，建構預測景氣循環轉折點之金融綜合指標。 研究結果顯示，於1990年1月至2009年6月期間，金融指標對景氣循環轉折點的確有預測能力，且不論是預測景氣谷底或是高峰，表現最優良之綜合指標正確率皆高達九成以上，且不論是預測景氣之高峰或谷底，以發生比率建構之二元logit模型都有最好的預測能力。 / To confirm the expansion and contraction of business cycle, and to forecast the turning point, has always been economists, government institutions, enterprises and the public cared about. The more control on the state of economic development and take advantage of the different economic situation, the more they could response appropriately, and furthermore this could maximize their profit or reduce business losses. This article attempts to use financial variables, such as the indicators about bills, bonds, equities, foreign exchange, financial institutions, and use signal approach which was created by Kaminsky, Lizondo and Reinhart in 1998 to construct a composite index warning the banking crisis early. I also try to use odds ratio combine with binary logit model in order to predict business cycle turning point. The results show that in January 1990 to June 2009, the financial indicators of business cycle turning points does have predictive power, and the accurate prediction of the index over ninety percent. The result also show that the best performance of the model is combination of odds ratio and binary logit method.

人口流動具有各種型態。其中包含了遷移、移動、以及通勤人口。在宏觀模型框架下，空間互動模型(簡稱SIM)對於測量人口流動扮演了重要的角色。距離遞減效應為空間互動模型中重要的因子。該效應描述了人口流動的頻率會隨著移動距離而逐漸下降。然而，從實證上，本研究發現人口流動與移動距離的函數，並非在距離上保有恆定的關係。 在本文中，我們提出了對此非恆定的距離遞減效應之修正方法。本修正法運用了轉折點模型的特點，套入了空間互動模型的距離函數上。本文首先運用了電腦模擬驗證了此方法的穩定性與有效性。接下來，研究將此方法應用在兩個人口流動資料。第一個是從台灣健保資料庫觀察出的民眾就醫地變化。健保資料庫包含了總人口的5%抽樣資料。由於在抽樣上瑕疵不大，因此健保抽樣資料具有了一定的代表性。第二個資料則是英國統計局所提供的人口遷移普查資料。在這兩個資料上，我們發現本研究所提修正法，相較於傳統的空間互動模型具有更好的模型配適表現。此改善程度在非都市地區尤其更為明顯。 / Population movement encompasses various forms, such as migration, mobility, and commuting. Spatial Interaction Model (SIM) serves as an important tool to calibrate these movements in the sense of macro modelling. One of the important features of this model is that the number of migrants often decays with the distance. However, we found that this is not always the case in practice and the decay pattern may change with distance. In this study, we propose a distanced-based modification to the SIM, via applying the techniques of change-point problem to construct distance functional form. Computer simulation is illustrated to validate the method and the empirical analysis of flow data from Taiwan’s National Health Insurance Research Database (NHIRD), and also England & Wales internal migration data also provides sound evidences to support the proposed approach. Note that the flow data from the NHIRD consists of a sample of about one million people and can be treated as a fine sample representative of Taiwan’s whole population (about 23 million people). Our results show that the modified approach is more adequate than the traditional SIM, especially for describing the movements of suburban areas in Taiwan.

本研究是以個案公司為例，藉以了解企業公司盛衰起伏的背後原由。對於這些果與因，雖然不能直接以簡單的原由來歸納與說明，但其發展過程中勢必有其脈絡，可以幫助了解公司發展與適應的做法。因此本研究透過描述個案公司各項策略作為，來了解企業經營的歷程。 　　本文第貳章說明研究動機與問題，並對本研究的各項變數做必要的定義。第參章對個案公司的基本資料與背景有較多的說明。本研究主體係個案公司責任中心二(Strategic Business Unit II)，該事業單位為自動資料蒐集產業(Automatic Data Collection)的本土製造商，自1985年第一台條碼閱讀機問世至今，在產業中已將近十六年的時光。 　　十六年以來，由人機介面(Input Device)的定位，以開發個人電腦鍵盤與自動資料辨識產品(Automatic Identification & Data Capture，AID)的條碼閱讀機(Bar Code Reader)，到目前以自動資料蒐集(Automatic Data Collection)產業的主流產品攜帶式自動資料蒐集終端機(Portable Data Collection Terminal)為主的經營範疇；經銷通路從貿易商為主的型態，轉而進入經銷商與系統整合商的通路；由完全沒有產業知名度，到進入美國前十名的自動資料蒐集產業供應商。地理構形也從本土企業出發，成為跨美、歐、日與大陸都有分支機構的跨國經營。 　　從以上的說明可以了解個案公司的發展歷程，詳細的內容可以參考第參章與第肆章的兩個策略轉折點前後的各個構面分析；本文中另以競技場分析，比較個案公司歷經策略轉折點之後在體系、產業結構、產品/市場的相關位置，透過競技場分析可以讓經營者更清楚未來的策略走向。 　　本文第伍章則提出研究發現與後續研究建議，其中的研究建議較值得注意的是個案公司最新的主流產品WinCE攜帶式終端機即將進入開放式的主流環境，在開放式的主流環境對未來成長有絕對的幫助，但風險當然也就大很多。而這項經驗在個案公司早期投入個人電腦鍵盤產品時期非常類似，若能透過對個人電腦產業的反思，相信面對未來的競爭思考能有方向的指引作用。 / “The Company” has been used as an example for my thesis, that helps to understand how an enterprise been successful and going dead. Those reasons and results to be successful and dead, which maybe not easy to get conclusion from simple examples, but we did understand all possible development from those tracks. We are also possible to find the way to adapt all those changes from all tracks’ studies. 　　In this case, the chapter 2 gives the motivation and answers about the reasons to have this thesis. It also defines all variables. In Chapter 3, I give more information and back ground about “The Company.” The major studied body is the SBU II (Strategic Business Unit II) of “ The Company”. That SBU II is the Taiwanese local maker for ADC (Automatic Data Capture) industry. The SBU II produced first Bar Code Reader since 1985 and is existed in the ADC industry more than 16 years. 　　Since last 16 years, “The Company” was positioned as “Input Device Provider,” that developed the keyboard for IBM Personal Computer and Bar Code Reader for AIDC (Automatic Identification and data collection) Industry. Up to now, the business scopes of “The Company” is producing the main trend products for ADC industry, which is Portable Data Collecting Terminal. During last 16 years, the distribution channels of “The Company” are changed from “Trading Company” to “VAR (Value Added Retails) and SI (System integrators). It is also changed from “ No Named Company” becomes one of ten major players of ADC industry in USA market. The geographical point of view is also changed from Taiwanese company to become multiple locations in Europe, USA, The Mainland China and Japan. 　　The description above helps to understand the development of “ The Company”. The detailed information will refer all details in “Three Dimensional Analysis” of those two strategic turning points in the Chapter 3 and Chapter 4. In these chapters, “The Competitive Field Model” is used to compare the different related positioning between two industrial structures, Products and Markets. After that study, I hope that can guide “The Company” to be much clear the way to the future. 　　In Chapter 5, I give some comments about my own development and also give some hints for future studies. There are some key comments about “The WinCE Portable Terminals”, which are going to be the main trend products and opened architecture environment. In the opened architecture environment that is very high growth in market size and industrial business. That is of course coming with very high risky in the future. This experience is very similar with the age of IBM PC Keyboard. If we can rethink the related experience from IBM PC age that may help a lot to face all future market competition. That is one of the key reasons to have this case study.

本研究欲探究個股新聞影響台灣股票市場之關係，透過蒐集宏達電、台積電與鴻海等三間上市公司從2012年6月至2013年5月的歷史交易資料和個股新聞，使用文字探勘技術找出各新聞內容的特徵，再透過歷史資料、技術分析指標與kNN和2-way kNN演算法將新聞先做分類後分群，建立預測模型，分析新聞對股價漲跌的影響與程度，以及漲跌幅度較高之群集與股價漲跌和轉折的關係。 研究結果發現，加入技術分析指標後能夠提升分類的準確率，而漲跌類別內的分群能夠界定各群集與股價漲跌之間的關係，且漲跌幅度較高之群集的分析則能大幅提升投資準確率至80%左右，而股價轉折點之預測則能提供一個明確的投資進場時間點，並確保當投資人依照此預測模型的結果進行7交易日投資時，可以在風險極低的前提下，穩當且迅速的獲取2.82%至22.03%不等的投資報酬。 / This study investigated the relation that the stock news effect on Taiwan Stock Market. Through collected the historical transaction data and stock news from July, 2012 to May, 2013, and use text mining、kNN Classification and 2-Way kNN Clustering technique analyzing the stock news, build a forecast model to analyze the degree of news effect on the stock price, and find the relation between the cluster which has great degree and the reversal points of stock price. The result shows that using the change range and Technical Indicator rise classification’s accuracy, and clustering in the ”up” group and “down” group can identify the range stock price move, and rise the invested accuracy up to about 80 percent. The forecast of reversal points of stock price offers a specific time to invest, and insure the investors who execute a 7 trading day investment depend on this model can get 2.82 to 22.03 percent return reliably and quickly with low risk.

本文使用具有事前訊息的領先指標與期間利差作為預測變數,根據不同利差與落後期選擇的 Probit 模型,利用遞迴的方式預測景氣轉折點發生機率,並進一步將個別預測結果進行組合,試圖找出能降低不確定性且優於個別預測結果的方法。實證結果發現,使用 Diebold and Mariano 檢定的預測包容法為其中最優的組合方法,無論是轉折點訊號或預測誤差都能優於半數以上的個別預測。此外,本文亦估計即期景氣轉折點的發生機率,根據模型的估計結果推斷,自 2012 年 2 月至 2015 年 3 月為止,景氣仍處於擴張階段。

近年來，富士康受到國際間高度的重視，然而，富士康中國工廠員工的高自殺率使得學者較重視員工的工作情況，鮮少對公司的擴張、轉移以及搬遷進行研究。本文聚焦於過去四十年富士康在中國的經濟發展面向。 使用雁行理論分析中國經濟發展的文獻不斷增加，富士康也參與於該理論所描述之中國邊境的工廠遷移現象，因此，本文整理學者對雁行理論的論辯，指出該理論無法解釋中國邊境發生的經濟現象。為彌補雁行理論的不足，我們將敘明中國空間發展於不同區域的漸進式轉變，係透過中央與地方政策的施行而開始。 研究結果顯示，依據區域經濟的發展階段差異，投資往往發生在相對優勢的地區，然而， 透過政策影響國家之動態優勢，以及投資趨動力……等，並不符合日本學者赤松要提出之雁形理論。一份關於富士康的直接與間接投資的分析指出，富士康的發展方向反映了中國的整體經濟發展，並且有兩個同時進行的發展方向：其一，地理上來說，富士康將投資從中國沿岸地區轉移至內陸地區，甚至進一步移往東南亞及歐美地區。其二，富士康將其產品種類擴大並提升到更多元及優質的方向。 / Over the last few years, Foxconn has started to gain massive international attention, however influenced by the high rate of suicides that afflicted plants in Mainland China, scholars focused the most on the labor condition of Foxconn workers, pushing the company’s very interesting business expansion, diversion and relocation into the background. This paper will focus on these processes in the context of China’s economic development of the past forty years. A growing literature about the latest developments of the Chinese economy adopts the flying geese model to describe the phenomenon of factory relocation that is taking place within the Chinese national borders. Foxconn is also part of the process. For this reason this work will also join in the scholar debate about the flying geese, making clear that the model falls short in explaining some aspects of this phenomenon. A detailed description of China spatial development, that is the gradual development of different regions brought about the launch of national and local policies, will make up for the shortcomings. Results show that investments were often taken according to the relative comparative advantage of regions in their respective stage of development, however in some cases China’s governmental policies changed the country’s comparative advantage dynamics, and investments’ driving forces were therefore in contrast with Akamatsu’s precepts. An analysis of Foxconn direct and indirect investments shows that the company has mirrored the growth of China, and evolved simultaneously in two different ways: geographically speaking they have moved investments from the Chinese coast to the central regions, and further to South East Asia, US and Europe; while at the same time expanding production into a more diverse and advanced set of products.