經營環境的快速變遷與競爭得日益激烈，企業透過策略聯盟以補強自身的弱勢，或強化整體的戰力，已經是合併與購併之外的另外一項主流趨勢。本研究探討各種策略聯盟因素包括：市場競爭因素、產業因素、公司核心能力等競爭環境的因素，及聯盟關係中的策略配適、執行配適與組織配適的問題，希望透過這些構面的分析，能夠更深入的瞭解策略聯盟的行為，及聯盟關係變化的動態過程。而企業如何因應在策略聯盟關係中可能產生的問題，以及對已經產生的問題如何處理則是我們最關心的課題。本研究也嘗試建立一個一般性的觀念架構，有系統的回答策略聯盟有關的問題。經由對以往文獻的整理分析，以及對四個個案公司的深入訪談，本研究得到以下的結論： 一、現在或未來將互相競爭的廠商較難維持聯盟的關係。 二、若聯盟夥伴對於聯盟的重視程度不同，則聯盟關係不容易維持。 三、由於競爭環境是動態的，所以策略配適也是動態的，同理組織配適與執行配適都是動態的。 四、保持策略聯盟型態調整的彈性，才能使聯盟的型態與動態的策略配適與組織配適、執行配適配合。 五、成功的聯盟經驗可以培養互信，造成更多的聯盟機會。 六、策略配適的調整如果涉及到組織配適的調整，便需要考慮組織能力（capability）的問題。 七、將以往的聯盟經驗制度化，可以提高往後策略聯盟的成功機會。

經過數十年，中國經營環境已經丕變，世界工廠轉變為世界市場。從2004年開始大陸一連串的稅制改革，勞動合同與社會保險法頒布，到2011年『十二五計畫』，影響層面：稅收嚴加徵管、外資優惠取消、產業轉型升級、人工成本飆漲、缺工、再加上金融海嘯，歐債危機衝擊等。經濟全球化與動態競爭，帶來效率提升社會的同時也增加了國家風險的多元化。 中國近年來提出了許多新政策，許多的台商陷入苦戰「面對中國經營風險-轉型與退場」。台商外部面臨幾項經營問題：(1)舊經營模式已深陷挑戰-政策風險：中國重要城市都在實行『騰籠換鳥』與『築巢引鳳』的兩個政策；(2)稅務風險；(3)經營風險；(4)資金問題：台商一切靠自己，政府產業政策、金融機構，融資管道狹隘；(5)家族企業經營瓶頸：永續、接班問題；與(6)如何由家族企業轉型為專業經理人的公司治理。 本個案公司在2004年，最初由於金融機構融資效率問題，所引發一連串的經營者對外觀環境變化及競爭者覬覦的警覺，而希望藉助外力(顧問諮詢)協助，透過組織內部變革改造，應對策略布局及戰術的運用，以及它是如何運用組織變革方式，解決公司治理問題。如何掌握產業演變，選擇適當因應策略，透過變革和創新的策略，使企業保有核心能力產業，永續經營。本個案以實務面分析從化妝品及包材產業概況與個案背景及問題現況說明，並進一步剖析-成長戰略(行業、地域、客戶順序、價值鏈)及組織變革方式、新公司治理，有目標才有策略、戰術等，逐一分析。 而選擇合適的策略為何這麼困難？因為產業形態迥異、外部環境動態競爭變化，導致衝擊不同、策略決策影響管理團隊的價值和優先順序。 根據麥可‧波特(Michael Porter)對於策略的詮釋：1.策略在創造企業獨特且有價值的定位。2.策略是選擇什麼不要做。3.策略是結合外部機會與內部能力的獨特流程和活動。所以，策略是選擇和配適(fit) ，選擇和配適凸顯管理決策重要的觀念-權變性(contingency)。這是一個實務與理論結合印證的案例。

多國企業海外子公司高階主管之選任議題一直是國際企業與國際人力資源管理學者熱衷討論的議題。本研究視信任需求及當地連結需求兩任用需求乃影響多國企業實際任用決策之因素，而職位特質則決定多國企業任用子公司高階主管之任用需求。此外，本研究結合人力資源管理理論及組織理論觀點，將任用需求區分不同情境，探究任用特質對任用結果之影響。最後，本研究探討任用結果與任用需求及任用特質配適情況下，其績效是否較不配適情況佳，以確認本研究理論架構之實用性。 本研究以至大陸投資之臺商為研究對象，經由實證分析證實職位特質對多國企業任用需求具影響力。在任用需求與任用結果之關聯性方面，當信任需求高，多國企業傾向任用外派者，擔任子公司高階主管；而當地連結需求高，則傾向任用地主國籍主管之假說亦得到實證支持。此外，任用特質在不同任用需求下，亦扮演不同角色。在人才取得容易性方面，基本上對任用結果具影響力，尤其對信任需求及當地連結需求均低或一方高一方低的職位；在相對成本方面，當信任及當地連結需求均低的情況下，多國企業傾向任用相對成本較低者；而相對忠誠度則在信任需求及當地連結需求一方高一方低時具相當影響力。最後，任用結果如依據任用需求及任用特質達成配適，則擔任該職位主管之績效較不配適情況佳。 本研究彙整人力資源管理理論、國際企業管理理論、經濟學替代觀點、總體人力供給觀點、交易成本理論及代理理論等相關學說，建立職位特質與任用需求及實際任用決策三部分連結架構。不僅對理論建立上有所貢獻，更對至大陸投資之臺商人才選任上具實務意義。 / Many researchers have been discussing the MNEs’ staffing issue of high-level managers of affiliates. This study tried to explore the effects of demands for employment (includes demand for trust and demand for local connection) on staffing decision, and hypothesized the main factors influencing demands for employment are characteristics of the post. Besides, this study also examined the effects of characteristics of employment in different situation of demands for employment on staffing decision. Finally, this study tried to test if the performances are associated with quality of staffing decisions. This study is based on the sample of Taiwanese firms with investments in China. Results showed that characteristics of the post affect demands for employment. Demand for trust is positive associated with the employment of expatriate; demand for local connection is positive associated with the employment of local manager. Besides, characteristics of employment have different effects on staffing decisions when the demands for employment are different. When the demand for trust and demand for local connection are both low, the accessibility of managers and salary costs have effects on staffing decisions. When only one of the demands is high, the MNEs will consider the accessibility of managers and relative loyalty to as the main issue to make staffing decisions. This study also showed that when staffing decisions considering demands for employment and characteristics of employment resulted in better performance. This study makes a contribution to the research on employment decisions based on the theory of human resource management, international business and economics. Its findings are helpful for Taiwanese firms to make staffing decisions of affiliates.

由於一般投資人在買進或賣出選擇權時，並不會同時買進多個履約價的選擇權，故會造成選擇權隱含波動度的微笑曲線出現有不連續的現象。本文嘗試運用台指選擇權建構一個日內的隱含波動度微笑曲線交易策略，利用曲線配適的方法來捕捉瞬間時點下隱含波動度曲線發生不連續的現象，雖然最後出來的損益並不如預期但還是驗證了台指選擇權市場有多次這種不連續的機會且價格失衡的狀態會回歸正常。 / Option’s implied volatility smile curves discontinuous phenomenon exists when general investors buy or sell options, they won’t buy in every strike’s options. This paper attempts to use Taiwan Index Options (trading code: TXO) to construct a trading strategy based on the implied volatility. We use curve fitting method to capture volatility smile curve’s instant discontinuous. Although we find out that the strategy won’t make a profit, there were several times when TXO market’s implied volatility smile curves were discontinuous, and the market option price will eventually go back to the theoretical price.

本論文基於尋求解釋權變觀點長久以來存在的問題：『為何實證上配適對績效影響一直沒有一個一致性的定論(mixed empirical support)』，因為根據權變觀點的主張『組織效能決定於組織的特徵(例如：策略、組織結構)與組織所處的情境是否配適(fit)，當兩者配適時則組織會產生較佳的績效』，所以企業追求配適，績效將愈高。由於配適概念具有績效意涵，因此配適在許多理論建構過程中，扮演重要的角色，例如：國際企業領域著名的折衷理論(Eclectic theory)，所以當權變觀點的核心主張『配適有助於提升績效』在實證上不一定成立時，則會影響理論的建構與發展。 為了解配適概念在實證上遇到的問題，本論文透過三個研究進行分析。在第一個研究，本論文針對權變觀點的文獻進行系統性的整理，並採用統合分析(meta-analysis)探討配適與績效的關係。研究結果顯示，配適對績效的效果量(effect size)為正，說明權變觀點的核心主張依舊成立，組織追求配適確實可以產生正向的績效。而影響實證結果不一致的原因則來自於配適的定義與衡量方法、衡量配適的變數個數、以及是否採用時間落差(time lag)三項干擾因子，呼應Venkatraman(1989)的主張。 接下來，第二個研究本論文採用質性個案研究的方式，探討配適與績效的關係。研究過程中結合動態能力(Dynamic Capability)的概念，透過企業在不同成長階段的營運活動分析，觀察企業如何追求配適、如何調整與轉換既有的配適構型、以及追求配適對企業經營產生哪些影響。第一個研究發現與企業追求配適有關，企業追求配適的前提，必須先擁有有價值的核心優勢(例如：製造、產品開發)，並以該核心優勢為中心，透過不同價值活動的緊密配合與組合，建立初期的配適構型(configuration)。第二個研究發現與配適的調整與轉換有關，發現為：(1)當企業成功創造初期的配適構型後，企業內部開始產生餘裕資源；(2)隨著企業價值活動的強化，前期的暫時性核心優勢會逐漸轉變為長期性的核心優勢；(3)透過創業家精神與策略更新，企業開始運用餘裕資源構築多核心優勢的配適構型。第三個研究發現與配適對企業經營之影響有關，發現如下：(1)企業建構配適構型時，當價值活動間關係愈緊密、複雜時，愈容易形成阻隔機制，競爭優勢愈能持久；(2)透過阻隔機制(isolating mechanisms)效果的發揮，以及時間壓縮的不經濟(time compression diseconomies)效果，可增加模仿的困難度並拉開與競爭對手之間的距離，創造績效。 第三個研究則承接研究一與研究二的部分結論，透過實證重新驗證配適與績效的關係，同時對於文獻上餘裕資源效果的爭論提出解釋。研究結果發現：(1)當企業內部存在互補的企業專屬資源以及擁有豐富產業經驗的高階管理團隊，則運用餘裕資源創造配適的效率愈高；(2)藉由調整TMT管理團隊的組成方式可以有效避免管理者的代理問題，增加運用餘裕資源創造配適的效率；(3)當企業運用餘裕資源創造配適的效率愈高，則企業運用資產獲利的能力愈強，企業績效也愈高。 總結來說，本論文從實證上配適與績效關係不一致的現象出發，對於實證結果不一致的原因提出說明，並且透過質性個案研究的方式，了解企業追求配適的過程及配適的效果，最後，藉由實證的方式，重新驗證配適與績效的關係，並且為企業如何有效運用餘裕資源提供具體的建議。 / This thesis aims to interpret the long existing question in contingency theory: mixed empirical support, i.e., no consistency can be found in the empirical relationship between fit and performance. This is intriguing, since according to contingency theory, organizational effectiveness is dependent on the fit between an organization’s characteristics (such as strategy and structure) and its existing circumstances, and with such a fit, the organization will have a better performance. Consequently, firms that pursue fit will achieve better performances. Since the concept of fit includes implications on performance, fit plays an important role in the development of many theories, e.g., the well-known eclectic theory. Hence, when contingency theory’s core proposition of fit is conducive to performance becomes fallible, overall theory construction and development will be affected. To further understand the fit issue, three studies are conducted in this thesis. For the first study, contingency theory literature was systematically studied and meta-analyzed with a special focus on the relationship between fit and performance. The findings show that fit has a positive effect size on performance which supports the core proposition of contingency theory in which organizational pursuit of fit does lead to positive performance. The reason for mixed empirical supports originates from three interference indicators of fit measurement methodology, number of variables, and whether the use of time lag. This finding echoes Venkatraman’s (1989) viewpoint. Next, a second study was conducted using qualitative approach to further explore the relationship between fit and performance. By integrating the concept of dynamic capability into the study, the researcher, by analyzing business operation activities in different stages of firm growth, observed how businesses pursued fit, how existing fit configurations were adjusted or changed, and what effects were created through the pursuit of fit in a firm. Three major study findings were identified. Firstly, in terms of how businesses pursue fit, a pre-requisite is that businesses must possess valuable core competences (e.g., manufacturing, R&D) and, by closely combining and coordinating different value activities to these core competences, initial fit configurations are built. Secondly, in terms of adjusting and changing fit, the findings include: (1) with the business’ initial successful fit configuration, slack is produced within the business; (2) as the business strengthens its value activities, previous temporary core competences will gradually transform into long-term core competences; and (3) through entrepreneurship and strategic renewal, the business will utilize its slack create a fit configuration of multiple core competences. Lastly, effects of fit on business management includes: (1) in the process constructing a business’ fit mechanisms, as the relationship between value activities become closer and more complex, isolating mechanisms are more easily formed, leading to more sustainable competitive advantages; and (2) by capitalizing on isolating mechanisms and time compression diseconomies, imitation become more difficult and the distance between competitors are widened, thereby creating performance. The third study adopted the findings of the previous two studies to empirically re-examine the relationship between fit and performance, while also proposing an explanation to the slack resource debate found in past literature. The research findings include: (1) when a business possesses complementary proprietary resources and highly experienced top management team (TMT), it enjoys a higher success rate of using slack resources to create fit exists; (2) agency costs can be reduced and increase in the efficiency of slack resource utilization to create fit can be achieved by adjusting the configuration of the TMT; and (3) with a higher rate of fit achievement through slack resource utilization comes stronger abilities to generate profits from business assets as well as a higher performance rate. In conclusion, this thesis started off by providing an explanation to the empirical inconsistency between fit and performance. Moving along, the researcher then used the qualitative case study research method to explore the process of businesses’ pursuit of fit and the effects of fit. Lastly, with an empirical study, the relationship between fit and performance is re-examined and specific suggestions are provided on effective business utilization of slack resources.

21世紀「知識」成為各國經濟發展之主要驅動力，企業更多採專案型組織運作以靈活應變，如何有效管理知識工作者也使企業文化愈受重視。專案型組織因知識工作者增加、多角化跨入新業務型態而有文化轉型需求。本研究欲探討專案型組織於傳統營建工程、知識密集服務、複雜產品系統三種業務類型下之配適文化與轉型模式。藉由蒐集個案公司Kyowa Exeo和IBM官方資料與高階主管談論文化之內容進行文化元素篩選，經競值架構特質表檢驗後，得出應變型文化、家族型文化、市場型文化、階層型文化四種文化類型之佔比，依此繪製舊文化暨新文化之文化剖面圖以進行文化配適與轉型討論。本研究貢獻為專案型組織分類、專案型組織文化情境配適表與文化轉型模式，並確認「家族型文化」於三類專案型組織配適文化中皆為重要元素。後續研究可繼續完善專案型組織文化情境配適表，驗證家族型文化在知識經濟時代對於專案型組織之重要性。 / In the 21st century, “Knowledge” becomes the driving force of economic development all over the world. More and more enterprises choose to change their structure to project-based organization in order to achieve flexibility. Corporate culture is getting more important for enterprises to manage knowledge workers. The demand of culture transformation in project-based organization is derived from the phenomenon of booming knowledge worker population and the strategy of diversification into new business. This study aims to explore the most suitable kinds of organizational culture for three different types of project-based organization, including traditional construction, knowledge-intensive business service, and complex product and system, and discuss the process of the culture transformation. The initial data bank of cultural elements is selected from official information, culture-related comment from senior managers (Kyowa Exeo and IBM). These elements are sorted into four kinds of organization cultures by the characteristic table of Competing Values Framework: Adhocracy culture, Clan culture, Market culture and Hierarchy culture. Two cases are studied in details by grouping their cultural elements in accordance to the four cultural categories. The percentage of each culture of Competing Values Framework is calculated and the culture profile of initial culture and new culture are drawn for in–depth discussion of cultural fit and culture transformation. The contributions of this research are the classification of project-based organization, and their most suitable cultures and culture transformation model. Besides, “Clan culture” is a critical element towards all three types of project-based organization. Follow-up research can improve the effectiveness of cultural fit table of project-based organization and verify the significance of Clan culture for project-based organization in the era of knowledge economy.

近年來，行銷領域所探討之調節焦點理論與調節配適理論，是有關於消費者心理的研宄，主要是強調，當消費者本身的長期目標導向和所採取的手段方法達到配適時，可以使消費者「感覺對了」，因而產生好的態度反應。同理，當廣告所傳遞的訊息焦點和消費者本身的長期目標導向配適時，也就能使消費者對標的物產生好的態度反應。 本研究以調節焦點理論與調節配適理論為基礎，觀察台灣和日本的消費者，旨在探討文化背景的不同，是否會影響消費者的長期目標導向？對調節配適的效果又會有怎樣的影響？而消費者自我監控程度的不同，又會對調節配適效果發生怎樣的調節作用？ 而本研究結果顯示： 一、 在促進廣告訊息焦點下，當消費者長期促進導向程度越高，越能提升消費者的態度反應，然而在預防廣告訊息焦點下，消費者長期預防導向程度越高時，則無法看出較佳的態度反應。 二、 日本的男、女消費者在預防長期目標導向程度上的差距，大於台灣的男、女消費者差距。 三、 在促進廣告訊息焦點下，消費者的促進導向程度越高，越能提升好的態度反應，此效果在日本的消費者上更明顯 四、 在促進（預防）廣告訊息焦點下，消費者的長期促進（預防）導向程度越高，對產品態度和廣告態度有正向（負向）的提升效果，然而當消費者自我監控程度越高會越弱化該效果。 / Regulatory focus theory and regulatory fit theory are talking about research of consumer’s behaviour in marketing related field in recent years. Two theories emphasise that when consumer’s long-term goal orientation fits methods they take, consumer would feel “that is right” and then positive attitude reaction is made. Meanwhile, when messages from advertisement fit consumer’s long-term goal orientation, consumer would have positive attitude toward the object of advertisements. This research is based on regulatory focus theory and regulatory fit theory to observe consumers in Taiwan and Japan. It discusses does differences of culture background affect consumer’s long-term goal orientation or not. How does culture background influences outcomes of regulatory fit theory? What kind of results based on regulatory fit theory would be made according to differences of consumer’s self-monitoring? The results of the research are in the following: First, in promotion focus advertisement, when the extent of consumer’s chronic promotion goal orientation is higher, the consumer attitude toward the object of the advertisement is more positive. However, in prevention focus advertisement, though the extent of consumer’s chronic prevention goal orientation is higher, consumer did not show more positive attitude toward the object of advertisement. Second, the difference in prevention goal orientation between male and female consumer in Japan is bigger than the difference in prevention goal orientation between male and female consumer in Taiwan. Third, in promotion focus advertisement, when the extent of consumer’s chronic promotion goal orientation is higher, the consumer attitude toward the object is more positive. This situation is more obviously in Japan’s consumer than in Taiwan’s consumer. Finally, in promotion (prevention) focus advertisement, when the extent of consumer’s chronic promotion (prevention) goal orientation is higher, the consumer attitude toward the object is more positive (negative). However, this result will be more unobvious when the extent of consumer’s self-monitoring is higher.

在線性模型中以計算容易，解釋方便為著稱，但是比須加入許多嚴格限制 ，而對於事後之模型檢測亦要花費番功夫。，而可加性模型只要函數給定 ，backfitting 演算法收歛即可。可加性模型除了保留線性模型的加法性 及解釋能力外，尚且提高了估計準度。在美、日、中、英、德五個國家的 保險市場中，雖然判定係數的提升亦大有斬獲 (0.85->0.9957)，然而在 台灣我們根據實證 一、提升統計應用水準，大幅提高模型變數的解釋能 力，模型內MSE(Me Square Error)大幅降低。(見表5-1、表5-2、表5-3、 表5-4、表5-5、表5-6、二、維持了線性模型方便的解釋能力。三、提升 估計水準，用以比較二種模型之優劣時，採1991年保費收入之實際值與估 計值之比較(見表 5-3，表 5-6，表 5-9，表 5-12，表 5- 15)，可發現 線性模型誤差率與可加性模型誤差率的比值美國為2倍、日本為12倍、臺 灣為4.55倍、英國為2.95倍、德國為2.95倍。四、函數以圖形方式表示顯 而易見。可加性模型所做的保費收入估計模型 / An Application of Insurance in Additive Model：United States's, Japan's,Taiwan's,England's and germnany's Life Insurance Model between Premiums and Macro-variables comparison.

策略的目的是在特定的競爭環境中，憑藉企業的特質條件為它創造競爭地位或發展的方向，也就是創造具競爭性的差異優勢，使企業得以順利發展和持續成長。在競爭的環境中，組織能耐常會隨著時間經過而演化；演化的方式會隨著技術本身的特性、外部市場競爭強弱、與內部的組織與管理特性的差異，而有所不同。除此之外，體制環境會影響整個產業內的創新速率，因而對廠商的能耐演化造成影響。但是在環境急速變動的情況下，組織能耐要完全由內部產生不但不可能，而且其速度亦嫌過於緩慢，再加上現代企業的專業分工網絡，企業必須與客戶、供應商、甚至競爭同業合作，以獲得相關的資訊與技術；在企業的發展歷程中，如何有效提升內部經營管理及促進組織之間的知識交流與能耐移轉，便成為組織管理的重要課題。 本研究以一家台灣本土醫藥公司，在台灣生技製藥產業的架構下，創業、轉型、成長的發展歷程，仔細描述影響企業發展的關鍵因素 ─ 企業策略轉變、環境變動、能耐演化，以及企業內部管理提升，彼此之間如何相互配適，並塑造出企業的獨特發展路徑；茲藉由個案公司過去的回顧，描繪其成長的軌跡，作為其未來發展路徑的參考。 / Under the favorable government policy support and a well-established regulatory environment, there are more and more new start-up companies established in Taiwan biotechnology and pharmaceutical industry in the past dacade. However, most of the new emerging companies are still facing very difficult situation. New drug discovery is one kind of long-term time-consuming and heavily cash-investment-needed business. Besides, Taiwan is a small market in the world. The market potential can not afford to develop a R&D based local pharmaceutical company. However, biotechnology and pharmaceutical industry is a very diversified and versatile industry. Under such circumstances, how does a biotech and pharmaceutical company make use of the limited resources and scarce capital assets to identify the niche market, create a new business model, develop the corporate competence, and construct the internal operation to strengthen the core business and secure a sustainable growth in the industry? Besides, due to the evolution of the modern tools including genomic science, bioinformatics, high-through-put screening machine, and gene therapy, the speed of new drug discovery becomes much faster and much more efficient, but the product life cycle also becomes much shorter. How does a local company play in such a highly competitive, technically professional, and dramatically changed environment? This study tracks the growth path of a local pharmaceutical company to show how the key factors, which are, environmental uncertainty, the development of core competence in the firm, and the choice of a successful strategy by top management and the organization, can be manipulated in the entrepreneurial firm that grows rapidly and formalizes its structure and internal operation. The growth path of the company in the past years could be interpretated as the mutual interactions (dynamic fit) of those key factors. Evenmore, the interaction consequences influence the strategic intent to confront the changing environment, and facilitate the practice of the law and the establishment of a government policy. Besides, in order to improve the whole healthcare system in certain medical care, the company develops a new operation model to run the specific business. Traditionally, most pharmaceutical companies are pursuing market-oriented product management, instead of sales-oriented business management. Nowadays, most multi-national firms are actively involved in disease management to expand the market share of certain disease. However, how to integrate the healthcare system and strengthen individual disease management under the specific healthcare system has become a new operation model of a pharmaceutical company to a specific market segment. The company has to work together and closely with the stakeholders, such as health authorities, medical societies, patient associations, healthcare personnel, and the patients themselves to improve the whole healthcare system and even the policy of the law, regulatory, social, and welfare system in the specific medical care, as well.

分析具有巢狀誤差結構的迴歸模式時，惹忽略隨機誤差項之間的相關性，而採用最小平方(OLS)估計量所導出的標準 F 統計量（以 F^S表之）進行檢定，會導致過大的型 I 錯誤機率；若將隨機誤差項之間的相關性納入考量，而採用廣義最小平方(GLS)估計量所導出的 F 統計量 （以 F^GLS表之），則計算上會較為繁雜。因此我們藉由轉換方式，將模式轉換成隨機誤差項之間彼此獨立的新模式後，再以 F^S 進行檢定，其結果與直接以 F^GLS 檢定相同，且可使計算較為方便。由於模式轉換所需的轉換矩陣為母體變異數的函數，因此當母體變異數未知時，我們以 Henderson 的常數配適 （fitting-of-constants）方法來估計之。藉由模擬結果得知，若各段的觀察個數相等，則不論巢狀誤差結構為二段式(two-stage)或三段式(three-stage)，廣義最小平方估計量(GLS)均較最小平方估計量(OLS)表現穩定，且 F^GLS 在檢定力及實際顯著水準方面的表現也都比 F^S 好。 / When analyzing the regression model with nested-error structure, if the correlations between errors are ignored, and conduting the model adequacy test by the standard F statistic (F^S) led from the ordinary leastsquares estimator (OLSE) , then the type I error rate will be inflated. However, if the corrlated structure is considered and the model is tested by F^GLS led from the general least-squares estimator (GLSE) , the calculation will be more complicate. The model can be transformed to a new model with independent random errors and then, tested by F^S . The result is the same as the one by F^GLS , also it is more convenient for calculation. Since the transformation matrix is a function of variance components, we estimate variance components by Henderson's fitting-of-constants when they are unknown. Through simulation, it is concluded that if the observations in each stage of nested-error structure are the same, the GLSE is more stable than the OLSE in both two-stage and tree-stage structures. Also, the power and the sizes of F^GLS will perform better than those of F^S .