在國內外實證文獻中，已有許多學者研究市場過度反應的現象，但由採取的研究方法不盡相同，故結論也有所差異．本研究是希望能對台灣股市的個別股票報酬率作一較完整的檢視，先瞭解股票報酬率前後期的相關情形，試圖找出一些一致性，再提出股市交易的策略，並比較策略的獲利性。 將樣本分成對稱與不對稱的形成期及檢定期，採Spearman等級相關係數法先對台灣股市同一股票的報酬率在不同期間（形成期及檢定期）的表現是否有相關作一檢視，接著檢定此相關係數時間序列是否具有隨機的特質，而後將證券交易稅及手續費納入考慮後，比較三種投資策略－買入持有輸家、中間、贏家的獲利性、風險及績效表現。 本文的實證結果：由單位風險報酬率來看，投資股市應以買入有長期的策略才會有較好的績效表現，而買入持有短期的績效是最差的。以不同的樣本期間討論台灣股市是否有價格反彈，結果並不相同。在1980年-1998年的Spearman等級相關係數多為正值，表示市場在288天以下多沒有價格反彈，且以連檢定的結果多為顯著，以Jensen α檢定之，贏家投資策略能獲得超額報酬。在1990年-1998年不論是重覆取樣、未重覆取樣，Spearman等級相關係數，多為負值，表示市場應存有價格反彈的現象，且以連檢定的結果多為顯著，但以Jensen α檢定之，輸家卻無法獲得超額報酬。可能是因為考慮了交易稅與手續費，而影響了投資策略的獲利性。 / There have been many articles discussing overreaction. Because of the difference of methods and samples, the conclusions are different. This thesis tries to make a more complete examination of Taiwan Stock Market. We divide sample period to be formation period and test period which are symmetric and asymmetric. Besides that, we adopt overlapping and nonoverlapping sampling. The sample period is 1980 January 1 to 1998 January 22. Three investment strategies are buying and holding loser portfolio、middle portfolio and winner portfolio. We use Spearman rank correlation to discuss whether the return of Taiwan Stock Market has correlation between formation period and test period. Then we adopt one of nonparameter statitics analysis－run test to examine whether the time series of Spearman rank correlation is a random walk. Following are our summaries： 1.The longer period we hold the stock,the better return we acquire. 2.In the first sample (1980 Jan 1 to 1998 Jan 22), Spearman rank correlation. is almost positive, and the hypothesis of run test is significant. We imply buying and holding the winner portfolio is the best strategy. We can prove this by using Jense α. In this case, buying and holding winner can get excess return. 3.In the second sample(1990 Nov 1 to 1998 Jan 22), Spearman rank correlaion is almost negative, and the hypothesis of run test is signficant. We imply buying and holding the loser portfolio is the best strategy. But we can not prove the by using Jense α. As we can not acqure excess return by buying and holding loser portfolio.

當我們利用Shewhart管制圖(Shewhart control chart)或累積和管制圖(Cumulative-sum chart. CUSUM chart)來偵測製程時,通常假設製品係獨立取自一個服從均數μ和標準差為σ的獨立常態分配的管制下進行。但是若產品特性值呈現自相關時,這類管制圖就可能發生誤導的結果。本文利用時間序列模式來解決具相關變數的管制圖問題。並考慮利用非線性時間序列模式及特別原因管制圖(special-cause control chart)來檢視台灣經濟景氣指標是否處於控制中的狀態。並討論特別原因管制圖的連串長度分佈(run length distribution)。在最後的實例分析中,介紹自動控制的觀念。 / Traditionally, in the quality control process, such as: Shewhart control chart or CUSUM chart, it is assumed that the observation process follows an i.i.d normal distribution. If the assumption for independence fails, that is when the process exhibits type of autocorrelation, we need to find a more reliable decision method. In this paper, we will apply the time series analysis and structure changed concept to slove the serial correlation problem. The idea of automatic control can be applied in the explanation of this nonlinear process. Finally, a time series about the monitoring indicators of Taiwan is discussed in detail as an example.

在一般的研究過程中均可能有離群觀測值產生，只要有離群觀測值存在， 就可能對研究結果產生極重大的影響。在統計學上常用的參數估計式中， 有許多極易受離群觀測值影響。因此本研究採用模糊族群分析混合最大概 似估計演算法運用在參數估計上，以去除離群觀測值對分析結果的影響。 本研究主要針對相關係數與迴歸係數的估計進行探討，利用演算法中所求 得之隸屬度，計算穩健相關係數和穩健迴歸係數，以期能正確估計參數值 。

大部的類神經網路均為解決特定問題而設計，並非真正去模擬人腦的功能 ，在本論文中介紹一個模擬人類學習方式的類神經網路，稱為推理類神經 網路（The Reasoning Neural Network），其主要兩個組成為強記（ cram -ming）及推理（reasoning）部份，透過彈性的組合這兩個部份可 使類神經網路具有類似人類的學習程序。在本論文中介紹其中一個學習程 序並用四個實驗來評估推理類神經網路的績效，從實結果得知，推理類神 經網路能以合理的隱藏節點數（hidden nodes）達到學習的目標，並建立 一個網路內部表示方式（internal representation），及具有好的推理 能力（g eneralization ability）。 / Most of artification Neural Networks are designed to resolve spe -cific problems, rather than to model the brain. The Reasoning N -eural Network (RNN) that imitates the way of human learning is presented here. Two key components of RNN are the cramming and t -he reasoning. These components coulds be arranged flexibly to a -chieve the human-like learning procedure. One edition of the RNN used in experiments is introduces, and four different proble -ms are used to evaluate the RNN's performance. From simulation results, the RNN accomplishes the goal of learning with a reason -able number of hidden nodes, and evolves a good internal repres -entation and a generalization ability.

線性迴歸模型中共線性的問題是導致模型不適當的重大原因之一。共線性 的存在不止會影響到參數的估計，使參數的變異變大，還會妨礙我們評估 自變數對模型重要性的能力，甚至會使我們忽略或去除掉重要的自變數。 而變異膨脹因子是診斷線性迴歸模型共線性問題時常用而有效的方法之一 ，但它只是考慮單一自變數的情況。本文則對於模型同時加入一組自變數 時影響原模型共線性的問題，先推導出廣義的判定係數，再利用它推導出 變異膨脹矩陣。再應用這個變異膨脹矩陣發展出六個準則，使得變異膨脹 矩陣有一個單一的指標來對模型的共線性做診斷。最後並以一個例子以實 際的數據，用六個準則對不同的模型做診斷，並嘗試找出各準則的指標。

區域發展差異現象一直以來為國家政策所關注，而近年來台灣地區失業率有逐漸上升的趨勢，各縣市之表現亦大相逕庭，顯示各地區存在失業差異現象。過去研究較少以空間觀點觀察失業相關議題，此外，關於區域差異因素對失業率之影響鮮少納入政府規劃因素。因此，本研究以空間自相關分析方法檢測失業是否具有空間相關性及聚集性，並應用長期追蹤資料（panel data）迴歸模型，以人口、產業、所得、都市化程度及政府規劃因素，分析台灣22縣市1988至2008近二十年來各區域差異因素對失業率之影響，藉由實證結果提出相關都市及產業政策之建議。實證結果發現，台灣失業分佈具有一定程度的空間相關性，且高低失業率在各縣市間亦有聚集現象。再者，依固定效果模型實證結果發現人口數、工業及服務業就業者百分比、都市化程度、工業區面積百分比與失業率間呈現顯著正向關係；經濟發展支出百分比與失業率呈現顯著負向關係；區域固定效果，即排除自變數影響下，各縣市本身區域特質對失業率之影響，結果顯示台北縣及桃園縣之係數為負向，南投縣、嘉義縣、台東縣與花蓮縣之係數為正向；時間固定效果方面，大部分年度皆具顯著性，且係數有由負轉正之趨勢，代表特定時間衝擊會對失業率造成影響。 / Differences in regional development have been a focus on national policies. Recently, there is a increasing trend in the unemployment rate in Taiwan, and it also differs from cities and counties, indicating there exists differences in regional unemployment. Previous research rarely combined unemployment issues with spatial perspective. In addition, the effect of regional discrepant factors on the unemployment rate rarely take government planning factors into account. Therefore, this study uses spatial autocorrelation analysis to detect whether unemployment has spatial correlation and aggregation, and applies panel data regression model with population, industry, income, the degree of urbanization, and government planning factors to analyze the effect of regional discrepant factors on the unemployment rate in Taiwan's 22 cities and counties from 1988 to 2008. According to the empirical results, we come up with some urban and industrial policy proposals. Empirical results indicate that the distribution of unemployment in Taiwan has a certain degree of spatial correlation, and high or low unemployment rate also has aggregation among cities and counties. Furthermore, according to the results of the fixed effects model, population, the percentage of industrial and service sector employment, the degree of urbanization, and the percentage of industrial area show a significant positive relationship with unemployment rate. The percentage of expenditures for economic development shows a significant negative relationship with unemployment rate. Region-specific fixed effect, which exclude the influence of independent variables, is the effect of regional characteristics of counties and cities on the unemployment rate. This result shows the coefficient of Taipei County and Taoyuan County is negative, and the coefficient of Nantou County, Chiayi County, Taitung County and Hualien County is positive. As for time-specific fixed effect, almost all years are significant, and the coefficient has the trend from negative to positive, indicating that a particular time impact will affect the unemployment rate.

研究目的 失眠的過度激發假說是目前最廣為接受的失眠病因之一，失眠者通常可觀察到具有身心過度激發的狀態，其中認知神經過度激發假說更由中樞神經的角度探討失眠者的過度激發現象，且已有許多證據支持此觀點。然而過度激發因素在失眠病程上的影響仍不明確，不論在前置因子或是持續因子的層面，激發因素皆經常被提及與討論。本研究以未失眠但具有高睡眠脆弱特質之族群作為研究對象，企圖模擬失眠者在失眠初發之前的狀態，另加入睡前及早晨的自主神經系統與主觀激發狀態之測量，比較其與低睡眠脆弱特質組在有無壓力誘發狀態下，兩組的睡眠中訊息處理程度、睡前及早晨的自主神經系統激發程度與主觀激發狀態，藉以了解（1）壓力是否會引發個體進入較高的主、客觀激發狀態；(2)睡眠脆弱特質在不同的激發程度下，是否會對於個體的睡前、睡眠中及早晨的激發程度造成影響，以初步推論激發狀態因素在失眠病程中所扮演之角色。 方法 以壓力下失眠反應量表（Ford Insomnia Response to Stress Test, FIRST）區分出高睡眠脆弱特質組（HV）13位（6男、7女）、低睡眠脆弱特質組（LV）14位（6男、8女），年齡為19-32歲之健康成人。每位受試者均需在睡眠實驗室進行3個夜晚之夜間睡眠記錄，包含第一晚的PSG測量以排除個案有其他睡眠疾患，並讓受試者習慣實驗環境；第二晚及第三晚則交互平衡操弄基礎情境或壓力情境，在壓力情境下，受試者被告知將進行即席演講，需在睡前抽出演講題目，並於隔天早晨喚醒後10分鐘內發表一篇內容充實、呼應主題之演說，隨後測量心跳變異率（heart rate variability，HRV）、平均心跳間距（r-r interval，RRI）、主觀身心激發狀態（Pre sleep arousal scale，PSAS）等主客觀激發程度，入睡後進行整夜的ERP（事件相關電位[Event-related potential，ERP]）測量，誘發ERPs之實驗流程以oddball典範為主，並於早晨起床後再次進行HRV、RRI及PSAS之測量。 結果 以2（組別）x 2（情境）之混和設計二因子變異數分析比較各組在不同情境下的主客觀激發程度指標是否有所不同。結果顯示壓力確實能引發受試者進入較高的主客觀激發狀態，包含睡前及早晨有較快的平均心跳速率、較高的主觀身心激發程度，而在NREM睡眠中可發現HV在有壓力的情境下，對外界的訊息處理程度顯著較LV組增加，包含較快的N1與較慢的N350出現，但HV在壓力下亦有較快的P2與較強的P900，顯示對外界訊息的抑制功能上升，且隨著睡眠更深，進入慢波睡眠時，P2及P900亦顯著較LV強，表現出更多的抑制外界訊息能力。 結論 本研究探討睡眠脆弱特質在不同激發狀態下對於睡眠的影響，結果顯示壓力能引發個體較高的激發狀態，然而在未失眠族群中，高睡眠脆弱特質對於認知激發狀態下的睡眠中訊息處理程度雖有提高，但可發現高睡眠脆弱特質組亦有較高的抑制外界訊息能力，而不致於使得激發狀態過度影響其睡眠，此結果部分支持失眠的認知神經過度激發假說，過度激發因素可能在持續因子的部分影響性較大，造成個體產生對睡眠的抱怨。另一方面，本研究結果亦彰顯失眠的高危險群的及早介入預防之重要性。 / Introduction: Conditioned hyperarousal has been theorized to be a major etiological factor in chronic insomnia patients. It has been suggested that insomniacs showed more arousal than non-insomniacs in many psychological and physiological measures, including enhanced information processing during sleep as measured by NREM ERPs. However, the role of hyperarousal on the course of development of insomnia remained unclear, it has been considered as a predisposing trait and/or perpetuating factor in the cause of insomnia. The present study compared arousal levels around sleep onset, during sleep and in the morning between non-insomniac individuals with low and high vulnerability to stress-related sleep disturbance, as high vulnerable individuals were proposed to be predisposed to chronic insomnia. The objectives of the study are therefore to investigate: 1) the effect of an acute stressor on arousal level prior, after, and during sleep, and 2) the differences in stress reactivity between individual with high and low vulnerability to stress-related sleep disturbances. Method: Fourteen healthy individuals scoring low (LV) and thirteen healthy individuals scoring high (HV) on the Ford Insomnia Response to Stress Test (FIRST) were studied. All subjects had to sleep in the lab for three nights: a screening/ adaptation night, then a baseline night and a stress night. The sequences of the later two nights were counterbalanced across subjects. During the stress night, subjects were informed that they would be required to give a speech immediately after waking up. Heart rate variability (HRV), r-r interval (RRI) of EKG and subjective arousal level (Pre sleep arousal scale, [PSAS]) was accessed before lights off and in the morning. Then sleep ERP was recorded during the night. An odd-ball paradigm was conducted to evoke ERPs throughout the night. Result: Mixed two-way ANOVAs were used to compare the differences between vulnerabilities and conditions. Both HV ans LV showed higher subjective arousal level and smaller RRI under the stress condition than the baseline condition. During NREM sleep, HV showed increased information processing under stress condition than LV as shown by faster N1, slower N350. Also, HV showed increased inhibition under stress condition than LV, with faster P2 and higher P900. Stronger P2 and P900 were also observed in HV when reached slow-wave sleep stage, comparing to LV. Conclusion: Both groups showed more arousal under stress condition than baseline condition, indicating an acute stress can lead to a higher arousal level. Moreover, high vulnerable individuals showed increased information processing during NREM sleep than low vulnerable individuals, but also showed more inhibition to prevent sleep from being disturbed by external stimulus. The results suggest that increased information processing in reacting to stress may be a predisposing trait for sleep disturbances. However, sleep may be protected by a compensatory inhibitory process in those who have not developed a long-term insomnia.

隨著網路的發達,各式各樣的資訊和商品也在網路上充斥著,使用者尋找資訊或是上網購物時,有的網站有推薦系統(recommender system)能提供使用者相關資訊或商品。若推薦系統能夠讓消費者所搜尋的相關資訊或商品能夠符合他們的習性時,便能讓消費者增加對系統的信賴程度,因此系統是否能準確預測出使用者的偏好就成為一個重要的課題。本研究使用兩筆資料,並以相關研究的三篇文獻進行分析和比較。這三篇文獻分別為IRT模型法(IRT model-based method)、相關係數法(correlation-coefficient method)、以及矩陣分解法(matrix factorization)。 在經過一連串的實證分析後,歸納出以下結論: 1. 模型法在預測方面雖然精確度不如其他兩種方法來的好,但是模型有解釋變數之間的關係以及預測機率的圖表展示,因此這個方法仍有存在的價值。 2. 相關係數法容易因為評分稀疏性的問題而無法預測,建議可以搭配內容式推薦系統的運作方式協助推薦。 3. 矩陣分解法在預測上雖然比IRT模型法還好，但分量的數字只是一個最佳化的結果，實際上無法解釋這些分量和數字的意義。 / With the growth of the internet, websites are full of a variety of information and products. When users find the information or surf the internet to shopping, some websites provide users recommender system to find with which related. Hence, whether the recommender system can predict the users' preference is an important topic. This study used two data,which are "Mondo" and "MovieLens", and we used three related references to analyze and compare them. The three references are following: IRT model-based method, Correlation-coefficient method, and Matrix factorization. After the data analysis, we get the following conclusions: 1. IRT model-based method is worse then other methods in predicting, but it can explain the relationship of variables and display the graph of predicting probabilities. Hence this method still has it's value. 2. Correlation-coefficient method is hard to predict because of sparsity. We can connect it with content filtering approach. 3. Although matrix factorization is better then IRT model-based method in predicting, the vectors is a result of optimization. It may be hard to explain the meaning of the vectors.

本研究以2009年8月的莫拉克風災中出現的網路災情資訊平台及其行動者為研究對象。探討資訊平台作為民間災難資訊的彙整和即時傳遞，其能夠有效的條件為何？過去災難資訊與網際網路的研究主要探討，其作為新的媒體的傳播特質，因此，本研究除了建立在對資訊平台行動者擁有的技術條件之探究外，主要從「網路動員」的集體行動角度切入，探討該行動是基於何種人際網絡樣貌，而能讓此網路動員得以發生？ 透過次級資料收集和對資訊平台行動者的田野深度訪談發現，災情資訊平台有效性的問題不只是討論行動者擁有社會條件為何，更有趣的是行動者如何從中衍生有效性論述，並建構一套擬似「客觀」有效性標準，作為區隔他者資訊平台進而確立自身正當性的說法。借用Bourdieu象徵鬥爭(symbolic struggle)的分析觀點，對行動者如何進行資訊平台有效性的論述進一步分析。從行動者的有效性論述邏輯中，浮現一個爭奪資訊平台正當性的意見場域。災難情境作為一個突發性的例外狀態，不在政府例行化運作機制可以反應的程度，也因此使其原本作為救災以及災情資訊掌握的正統角色有了被挑戰的機會，而民間災情平台的集體行動則是挑戰此正當性的「異端」，透過網路開放式和平權化的特性，因而得以作到社會性的災情通報、彙整和溝通傳遞的資訊系統。 資訊平台的行動者作為一種網路動員並非僅是匿名而隨機的網友匯集，核心行動者多是屬於網路資訊圈或自由軟體的社群，其共享某些知識、價值或文化氛圍。他們熟悉網路資訊的傳遞或各種網站架構技術，再加上日常以網路資訊為共同興趣的聚會或交流形成不同的社群圈以及相對情感關係更緊密的「小圈圈」。線上、離線社交互動是跨越時、空限制的延續，彼此熟悉的程度高、信任度也高，也因此能協力完成高度動態分工的災情平台架構和維持。其他透過間接關係從網路上召募而來的資訊志工，則是受到災難感的情境影響，較平時更有機會產生對於組織或運作機制的系統信任。而災情資訊平台的有效性，除了建立在在網際網路技術物的開放和平權特性條件外，同時也在於行動者建構有效性論述，讓網路動員持續具有正當性，在災難情境中召喚更多人投入，形成另一股相對於「失靈」政府的公民動員的力量。 / This study aims at discussing the factors of information effectiveness presented in several online platforms built for Typhoon Morakot when it attacked Taiwan. Previous researches which have discussed information flows on the Internet during or after disasters focused on the media effect of the Internet. However, online information platforms built for Typhoon Morakot disaster were not only about the internet technology, but presented a social phenomenon of online mobilization. Based on this observation, this study underlines the discourse and relationship of the key actors ─ the bloggers and engineers, who constructed 4 major information platforms, and explored how these social factors make information platforms possible and effective. The methods of this research are through interview and second-hand data collection, and two results are analyzed and concluded as key factors which contribute to the effectiveness of information platforms. First, not only the actors’ technology or media background play an important role in effective problem of information platform but also their discourses about information effectiveness, which were based on their social conditions, were crucial. The key actors constructed seemingly “objective” standard in their discourse to justify their platforms’ legitimacy for distinguishing theirs from others. Borrowing Bourdieu’s theoretical lens of Symbolic Struggle, this study analyzed the context of actor’s discourses and found different logics of information effectiveness which emerged a field of opinion of discourse for legitimacy completion; at the same time, the government’s failure in dealing with the disasters as the background of the information platform’s appearing is also closely connected to legitimacy competition. The catastrophe that Typhoon Morakot brought to Taiwan was far beyond the government’s routinely mechanism can response to, and challenged government as the only orthodoxy of disaster information and rescue. Hence, civic action mobilized in delivering disaster information on several important internet platforms was the heterodoxy to challenge orthodoxy’s legitimacy. All these mobilization and competition of discourse are possible because of the open and equal-right characters of the Internet. Second, the online mobilization of information platform was not based on people’s random gathering, but based on most of the key actors belong to specific “circles”, such as those from the internet information or open-source communities. In the communities, these people are all interested in internet-related topics and are familiar with online communication technology. Moreover, they became much closer circles by regular meeting and daily communicating on social media and off-line parties for their common interest: internet and information. Their bonds and relationships are formed by intensive on-line and off-line daily practices which brought mutual understanding and trust ─ that is why they could work together and cooperate to keep the platform working.

University of Macau / Institute of Chinese Medical Sciences