隨著市場競爭環境大大改變後，從以往的規模經濟生產型態轉為降低成本、提升品質、縮短時間、增加彈性的大量客製化(Mass Customization)的生產型態，組織的層級與規模隨業務需要逐漸擴大，導致對於整合企業資源、企業流程和資訊系統的需求日益增強。不但必須了解企業的所有資源與營運狀況，還需將所有資源加以整合，以能即時提供對企業有利的資訊供決策之用。而企業經營面對的競爭也是全球性的，更快速地反應市場及客戶需求，或是更流暢地與上、下游廠商溝通，都是企業必備的條件，但這樣的理想便需要透過作好組織內部的企業資源規劃(Enterprise Resource Planning，ERP)來達成。 ERP系統的導入對於企業而言是一種新的風險，企業應分階段導入。在導入的過程中，影響成功的關鍵因素又有許多項，在各階段所要注意的因素是哪些，影響企業在分配資源時的策略規劃。本研究將導入ERP 系統的過程整理為五個階段，以及十六項導入ERP 系統的關鍵成功因素(Key Success Factors) 。希望探討在各階段所需重視的關鍵成功因素，能協助企業更清楚地掌握這些因素，使得導入的過程較為順利。 因此，本研究的研究主題有下列三點： (1) 探索企業在導入ERP 系統的過程中，各階段所重視的關鍵成功因素為何？ (2) 上述的關鍵成功因素的在各個階段的實務作法為何？ (3) 導入ERP 系統的過程，以流程分析的方法建立模型，並了解在各階段中關鍵成功因素所影響的導入活動為何？透過文獻探討本研究將初步整理出各階段之關鍵成功因素，並採用個案研究方法進行資料蒐集及分析。

本研究主要探討台灣上市櫃公司從事首次現金增資之決策受何種公司特徵所影響，並進一步探討進行其首次現金增資的宣告效果影響因素。 本研究針對1981年至2010年共30年期間於台灣上市上櫃之公司其首次現金增資之情形做為探討對象，採用Cox-proportional Hazard Regression檢定影響上市櫃公司進行首次現金增資時程之公司特徵。實證結果顯示，營收成長率越高、規模越大且獲利能力較差的公司會傾向越快進行首次現金增資。同時也針對上市櫃年度其市場情形加以探討，發現於市場處於熱市時上市櫃的公司傾向越快進行首次現金增資，顯示市場時機也會影響公司進行首次現金增資的決策。此外，對其首次現金增資之宣告效果進行迴歸分析同時以Heckman Two-Stage Model方法考慮樣本選擇偏誤之修正，結果發現規模越大的公司宣告效果越差而負債比率較大的公司宣告效果越佳。然而上市櫃後進行首次現金增資之時程與其增資宣告效果間則無顯著關係。 / This study examines how fast companies have their first seasonal equity offerings after their IPOs and further analyses the announcement effects of first SEOs. First, we adopt Cox-proportional Hazard Regression Model to see what firm characteristics make IPO firms decide to conduct first SEOs shortly after their IPOs. Using a sample of IPO firms in Taiwan from 1981 to 2010, we find firms that are larger, less profitable and higher growth potential would conduct their first SEOs faster. Also, market timing plays an important role for SEO decisions. Moreover, the announcement effect of their first SEOs shows that elapsed time to conduct first SEOs after IPOs has no influence on the cumulated abnormal returns. By correcting sampling bias, Heckman Two-Stage Model is adopted to reveal better explanation of the results.

本文旨在評估所有本國銀行自 1999 年至 2011 年的績效，以檢驗我國兩次金融改革的成效。研究方法主要採用 Olley and Pakes (1996) 的三階段模型，再者運用差異中之差異法 (Difference in Difference，DID)。有別於相對於過去文獻中使用非計量的方式，或是以計量方式評估但卻未考慮到銀行進出的情況，本文考量因新設或是合併而解散所造成的銀行家數變化影響，並試圖歸納金融改革對於整體本國銀行之成效，以及對於同一本國銀行的生產力提升是否有所助益。

雖然人力資本在理論上的重要地位早已確立，但是，因為人力資本的衡量不易周延精確，使得其實證研究難有突破性的發展；所以，本論文嘗試透過具備個體基礎的理論架構，使用「人力運用調查」的原始資料進行實證分析，希望能進一步瞭解人力資本的性質、勞工流動的成因及這兩者如何影響個人的薪資與整體的成長。而在編排上，本論文則是由三篇可分割獨立的論文所組成。 第2章的重點是從同質人力資本的角度討論人力資本的衡量問題：基於薪資可以反映勞動生產力的概念，本章嘗試使用各個勞工與基礎勞工間推估預期薪資的比率做為代表人力品質之權數，以建構較完整的台灣人力資本指標；從成長會計分析及總合生產函數迴歸估計的實證結果來看，考量人力品質提升的勞動投入約可解釋18% 至35% 的經濟成長，遠高於實際工時的15%；惟近年來台灣人力品質的提升似乎逐漸減緩，不利於後續的經濟成長。 第3章的重點是使用多項式logit模型討論勞工的流動現象，而且其估計結果亦成為第4章必需的實證基礎：鑑於台灣的產業結構一再歷經巨幅的改變，本章將勞工是否異動視為共包括「不換工作」、「換工作但不換產業」及「換工作又換產業」三個選項的決策問題，並援引非巢式logit模型及巢式logit模型對其進行分析。從總括值迴歸係數的檢測來看，巢式模型與隨機效用理論是互不相容的，只有非巢式模型具有較完整堅固的個體基礎。 第4章的重點是從異質人力資本的角度討論產業特定型人力資本是否存在的問題：因為台灣現有的資料庫缺少產業年資等相關資料，所以，本章擬將重點置於轉換工作者，研究轉換產業是否會影響其現職前一般經驗與現職工資之間的關係，以間接分析產業特定型人力資本在台灣的存在性及重要性。從實證結果來看，一般而言，產業特定型人力資本也許並不是非常重要，但應該仍是存在的，亦即仍會對勞工在不同產業間的重新配置產生一定的影響。

本文係針對臺灣50指數期貨與基金於2003年6月30日上市之後，臺灣期貨及現貨市場報酬率間領先落後關係與波動性的變化來進行探討。研究分為兩部份，第一部份是觀察臺灣50指數期貨與現貨之間的關聯性，並探討臺灣加權股價指數、金融保險類股股價指數及電子類股股價指數期貨與現貨市場間的變化；第二部份是採用可模擬現貨走勢的臺灣50指數基金、國泰金及臺積電的股價來做為現貨的替代變數，觀察其與期貨之間的關連性是否與第一部份的結果類似，若是實證結果極為相同，則相關機構與一般投資人將可運用各期貨與其標的指數中市值最大的股票來進行套利操作。此外，本文在進行模型估計時，首度採用一階段估計法，來聯合估計雙變量GARCH模型中的條件平均數方程式與條件變異數方程式，以避免過去相關文獻將兩條方程式個別估計時所造成的估計誤差。 實證結果所獲得的重要結論如下：首先，臺灣期貨市場的發展仍未趨成熟，並不具有價格發現的功能，在考慮風險溢酬方面，僅有臺灣50指數期貨與現貨的投資人會在報酬率之外，額外要求用以補償的風險溢酬，再者，臺灣50指數期貨與基金的上市，並沒有對臺灣現有的期貨與現貨市場造成顯著的影響，然而，替代變數並不能完全取代現貨指數，但相較之下，國泰金在臺灣50指數期貨與基金上市之後的那段期間模擬成效最好。 / This paper investigates the change of lead-lag relationship in returns and volatilities in Taiwan futures and spot markets after the introduction of Taiwan 50 Futures and Taiwan Top50 Tracker Fund (TTT) on June 30, 2003. The study divides into two parts. The first part examines the relationship between Taiwan 50 Futures and spot markets, and also discusses the change of Taiwan Stock Exchange Capitalization Weighted Stock Index, Taiwan Stock Exchange Banking and Insurance Sector Index, and Taiwan Stock Exchange Electronic Sector Index in futures and spot markets. Another part uses the stock price of TTT, Cathay Financial Holding Company and Taiwan Semiconductor Manufacturing Company as the substitutive variables of spot index and goes a step further to examine the relationships between them and futures individually. Additionally, this research used One-Pass Method for first time to estimate jointly the conditional mean equation and conditional variance equation of Bivariate GARCH Model to avoid estimating error in previous relative studies with Two-Pass Method. The major empirical results are as follows: first, the development of Taiwan futures market is incomplete. The futures market does not play the price discovery role to the spot market. Second, under the consideration of risk premium, only investors in Taiwan 50 Futures and spot markets would ask for compensated risk premium excepting returns. Third, the opening of Taiwan 50 Futures and TTT does not influence significantly Taiwan futures and spot markets. Last but not least, these substitutive variables can not replace spot index perfectly. However, comparing with others, the stock price of Cathay Financial Holding Company is the very model of Taiwan Stock Exchange Banking and Insurance Sector Index after the introduction of Taiwan 50 Futures and TTT.

科學技術進步下，產品生命週期不斷縮短，不少企業藉縮短新產品規劃階段以及簡化的前置作業，回應必須快速推出新產品的壓力，但學者研究調查中持續發現，輕忽新產品設計與開發最起始階段是導致新產品失敗的主要原因，因此本研究將研究重點放在新產品開發流程之前段新產品策略與規劃工作上。 本研究將新產品開發流程一切為二，「前段」涵蓋全面發展階段之前的產品構想、初步調查、細部調查等新產品開發階段，「後段」則包括全面發展階段在內的產品測試與確定、全面生產與上市等新產品開發階段，而Cooper(2000)在前段與後段之間設立一個重要的檢核關卡，前段須產出明確的「新產品定義」相當於科技產品之規格，以及「新產品定位」也就是新產品對消費者之訴求重點後才能進入後段流程，因此本研究期望使此重要關卡所需的最後「新產品定義與定位」產出，能是一個周延考慮各面向因素的最佳結果，因此本研究提出之解決方法是納入前段所有需考慮的新產品策略因素以及可行性因素，加以整理並建立「新產品定義與定位評估架構」，提供企業在決定「新產品定義與定位」時能夠透過客觀檢核架構，進行新產品推入市場後成功率的評估，甚至能將之運用在各新產品方案之間的選擇，例如：越符合架構各面向因素的新產品方案，代表較高的產品成功率。 本研究選擇決策中心在台灣的「台灣自有品牌企業」，鎖定產品生命週期短且汰換率高之特性的「手機產品」，並以對企業與市場而言皆為新產品的「智慧型手機」為研究對象；本研究研究目的為希望了解台灣自有品牌手機公司實際進行新產品開發流程的情形，並找出妥善評估「新產品定義與定位」的衡量架構與指標，並進行整體與跨公司之各因素指標權重比較，期望結果可提供台灣自有品牌手機業者一個可遵循的「新產品定義與定位評估架構」以及可了解企業本身對新產品注重之重點的具體新產品管理方法；本研究方法為整合專家訪談、學者文獻和產業研究報告，建立「新產品定義與定位評估架構」，並使用層級分析法(AHP)將架構因素設計成問卷，請五家公司各一位有權決定新產品全面發展與否的高層主管，依據過去新產品專案管理經驗透過因素之兩兩比較，得到各層級之各因素在企業做新產品評估時的權重。 研究結果發現台灣自有品牌手機公司在第一層級指標中首重「新產品市場潛力與需求確認」與「新產品策略發展競爭分析」，並對「新產品技術開發與設計可行性」最不重視；策略夥伴(通路商/電信商)商品趨勢預測、新產品推出市場後的獨特性與優越性、機構與ID(工業)設計能力、新手機專案如期完成，都是第二層最被重視的指標；現有產品線之影響、目標市場銷售成長潛力、功能需求等則為第三層企業評估重點。 本研究相信新產品之表現好壞不僅是上市之行銷企劃結果，更來自於最起始新產品初生時企業所做的規劃階段與前置工作品質，透過「新產品定義與定位評估架構」將專家在做決策時的內隱經驗與知識作架構化，更透過層級分析法(AHP)的量化分析找出各指標權重，以客觀周延架構與具體權重改善決策者過去依主觀經驗決策情形，並提供企業一套有效產出「新產品定義與定位」的思考過程，更可進一步作為最佳成功率方案選擇的新產品管理方法。 / With rapid leaps in technology, product life cycle has been shortened in the past several years. Responding to this change some firms tried to simplify the preceding operation in the planning stage of the new product development process in order to speed up the lead time for launching new product. However some academic researches point out that the fewer firms do in the beginning stage of new product development process, the higher failure risk firms will take finally. For considering the importance of the start stage of new product development process, this thesis focuses on how to plan a new product properly and effectively. This thesis divides the new product development process into two parts. One is the former phase including “discovery stage”, ”scoping stage”, and “build business case stage”. The other is the later phase covering “development stage ”,”testing and validation stage”, and “launch stage ”.The Scholar, Robert G. Cooper(2000) created a method to manage the whole process called “stage－gate”. He mentioned “gate three” played a meaningful role between former and later phase because firms have to make commitment to the new product and put in real resources after former phase. In other words, “gate three” plays a role as a serious gatekeeper to make sure a well-defined and clearly-positioned new product. The definition and position of the new product is the output of former phase and means “gate three”. To have a sound definition and position of the new product, this thesis suggests a framework involved in all factors that are under consideration in former phase. Firms could adopt the framework when they have to create or evaluate a new product. This thesis also suggests that following the framework to evaluate a new product could be more objective and easily-obeyed, and most importantly lower the failure risk of the new product. This thesis takes “Taiwanese own brand company” as the object of study is because it is more feasible to contact with the core of the people who are the decision maker of a new product. Mobile phones are suitable to be the product of the study on account of facing the intense pressure from product life cycle shortened and high changing usage rate. Moreover this thesis chooses a fresh and novel product for consumers and firms, “smart phone”, as the target product. The purpose of this thesis is to know more how “new product development process” being implemented in Taiwanese own brand company, collect the factors considered in the process, and organize all the factors in a hierarchy framework. This framework works as a guidebook to evaluate new product definition and positioning. The method used in this thesis can provide more information such as quantification of importance percentage of some indexes. This study recommends that firms revise and adjust the percentages by comparing each other within five companies separately. To set up “ the new product definition and positioning evaluative framework ”, this research integrates the expert opinions of interviews with professors, academic researches, and industrial research reports. The concept of questionnaire is based on “Analytical Hierarchy Process, AHP” and designed for continually comparing the importance of different two factors for calculating the importance percentage. The people answering questionnaire are the senior managers who are responsible for making final decision and decide a new product is qualified for “gate three” and enter “development stage”. This thesis believes a successful performance of a new product launch is partly based on the marketing communication plan but mainly comes from an entire consideration of new product plan in the beginning of the process. By way of evaluating the definition and positioning of new product with hierarchy framework, helps decision maker to remove subjective opinion and conclude the decision more objectively. The most important contributions of this study are not only transferring latent thinking process to a easily-followed framework and output meaningful quantification importance percentage, but also the percentage can further be used to calculate points for choosing the best-fit new product on the selecting list. The thesis hopes the process of this research method to be a good new product management method and improve the success of new product development effectively.

本論文主要由三大研究主題組合而成：第一個主題是依照中國金融體系的現況，針對國有銀行、政策性銀行、股份制商業銀行及城市商業銀行等四種不同類型銀行的獲利績效進行比較實證研究。其中的股份制商銀與城市銀行，其資本組成除少數仍有國務院持股（即中央政府持股）外，股東成員擴及地方政府、國有企業及民間企業，股本結構明顯較國有商業銀行及政策銀行多元化。不同的股本結構，尤其是官股比例（政府持股比例）是否對各家銀行的獲利能力產生影響，是本文主要研究興趣所在。本文採用Bankscope資料庫，涵蓋1997至2004年中國大陸49家銀行的財務及股東資料。結果發現：銀行股權結構中，中央政府持股比例越高，銀行獲利表現越差，地方政府持股的影響則較不明顯；而四類銀行中，股份制商銀與城市商銀的表現遠優於國有銀行及政策銀行。但1999年以後中國國有銀行的財務整頓措施的確使得國有銀行的相對表現有所提升。 鑑於外商銀行大舉進入中國金融市場，勢必對中國銀行帶來更多的競爭壓力，本論文第二個研究主題進一步將研究範圍擴及至世界資產排名前一百大的銀行，企圖比較中國銀行與世界百大銀行經營績效的差異。在這個主題中，延續前一主題「股權結構」的重要性，除了官股比例，同時考慮外資持股及本國人持股，分析三類持股對績效的影響，又鑑於總體面的政府治理因素可能對股權與銀行績效的關係產生變化，本研究也將政府治理變數，包括文獻中經常提到的證券市場內線交易情況、政府政策透明度及政府貪污情況等因素納入考量，比較這些因素對中國銀行與百大銀行影響有何差異。實證結果如下：對中國銀行及世界百大銀行而言，政府持股對銀行獲利的影響是負向的，而外資持股的影響則恰相反，開放程度愈高、銀行自由度愈高越有利於銀行績效提升。中國政府越無貪污情況時，越有助於外資持股對銀行績效的正向影響。對世界百大銀行而言，政府越無貪污情況時，越有助於外資持股對銀行績效的正向影響。而政府政策透明度越高，越有助於政府持股與本國人持股的正向影響。 第三個主題探討我國上市櫃公司不同的對外與大陸投資決策對母公司獲利性的影響。本文將投資決策對公司獲利的影響視為內生，也就是投資決策受公司特性因素的影響。同時，我們進一步假設公司的投資決策是分兩階段完成，第一步會先決定是否進行海外投資，一旦確定後，再決定是否赴大陸投資。因為有兩層的投資決策，本文以延伸的Heckman’s Two Stage Method進行估計。 實證結果顯示，在投資決策的影響因素方面，對第一層赴海外投資而言，規模愈大、國際化程度愈高、愈勞力密集的公司愈傾向赴海外投資；對第二層赴大陸投資的決策，影響因素也類似，只是公司規模不再是重要影響因素。至於獲利的影響因素方面，第一類「赴大陸投資的公司」與第二類「未赴大陸但赴其他國家投資的公司」的利潤型態較類似，長期負債對獲利都有負向顯著影響，總資產也傾向負向影響，至於第三類「未從事任何海外與大陸投資公司」的利潤型態則與前兩類不同，總資產與研發支出都呈現顯著負向影響。而三類公司的績效比較部分，第一類公司的平均預期資產報酬率雖若高於第二類，第二類公司又高於第三類公司，但三類公司兩兩之間平均預期資產報酬率的差距並未達統計上的顯著性。 / This dissertation contains three main parts. The first part studies the effects of government owned share on Chinese banks’ performance. After a series of financial reforms in the 1990s, joint stock commercial banks and city commercial banks started to boom and play an increasingly important role in China’s banking industry which had previously been monopolized by four state-owned commercial banks. These two new bank-types are considerably more diversified in that the primary shareholders include the central government, local governments, state-owned enterprises and private enterprises, not just the central government. Using 49 Chinese banks’ financial data retrieved from Bankscope, this part examines the effect of different ownership structures, in general, and government-owned-shares, central vs. local, in particular, affect the profitability and risk of banks in China. It also compares the profitability of four types of banks, namely state-owned banks, policy banks, joint-stock commercial banks and city commercial banks. We conclude that, without equivocation, the higher the ratio of state-owned shares is, the worse is the profitability of the bank. And we also note the profitability of joint-stock commercial banks and city commercial banks is much better than that of state-owned and policy banks. In light of the ever-growing foreign competition facing Chinese banking industry, the second part expands the sample banks to World’s top 100 banks and studies the differences between Chinese banks and foreign banks from the respects of ownership structure, government governance and bank regulations. Our empirical results reveal that for both Chinese banks and top 100 banks, government owned share has a negative effect on banks’ profitability, while foreign owned share has an opposite effect. For both of them, the more the foreign institutions have access to the banking market and the more freedom the banking industry enjoys, the better the bank performs. For Chinese banks, lesser corruption helps strengthen foreign share’s positive effect on banks’ performance. Furthermore, higher transparency would increase the positive effect of government owned share and domestic owned share. The third part studies the profitability of Taiwan’s listed companies with and without investment in China. Unlike past studies which deal with the decision of investment in overseas and China as exogenous, the decision is endogenous in this paper. That is, the decision making is based on the firm’s characteristic factors. We further assume that there are two hierarchy decisions made by firms when they decide in investing in overseas and China. The first decision is whether it should invest overseas. Once the first decision is made, the next one is whether a firm should invest in China. This two decision model, which allows us to extend Heckman’s two-step method, is referred to as an extended-Heckman method in this paper. Our empirical results regarding the determinants of investing overseas and China are as follows. With respect to the investment in overseas, firm size and export ratio show positive influence on the decision of investment, while capital labor ratio shows negative effect. Next, with respect to the investment in China, determinants are similar except that firm size is no longer significant. Our results regarding the profit performance reveal that for ‘the firms with investment in China’ and ‘the firms without investing in China, only investing other countries’, long term liability ratio has a significantly negative impact on profitability, whereas total asset, R&D expenditure show a negative effect on profitability for ‘the firms without investing overseas, nor investing in China’. As for the performance comparison among firms of these three investment types, the differences are insignificant. This result implies that there are still considerable individual differences among the firms of the same investment type.

數位電視（Digital TV，DTV）是指一種把影像、語音等聲光的類比訊號換成數位訊號，然後傳遞至視聽消費者端之電視技術。它也可以代表一種能夠接收上述數位訊號、並且無失真地還原成和送出時相同品質的一種電視產品。由於數位電視具有高品質的影像、音響效果，同時提供具附加價值的資訊服務，如透過數據、電子節目表單、在家購物等方式，可帶動旅遊、交通、娛樂、文化產業的發展，對於台灣中長期民生與科技發展極為重要。 各國關閉類比電視頻道的時間已近，產經分析人士咸信未來數年內各國的消費者都將面臨換機或是增購訊號轉換器的處境，因而引發龐大商業機會。由於數位電視市場可望能為台灣平面顯示器產業延長榮景，且其所帶動週邊如STB、以及家用或車用電器、數位內容產業等，創造大量就業人口，在台灣進入另一波數位革命的階段的起點時，它具有極高探討價值。此外，由於積極加入此領域的廠商數目繁多，而數位電視既是充滿機會、又充滿技術與規格艱難險阻的產業，究竟是具備如何條件、訂定怎樣的目標、運用甚麼策略的企業，才能在這個國際化的產品市場上佔有一席之地，是本論文援用大量數據並深入分析的重點。 從本研究所收集資料來分析可以發現，普騰電子以衍生成數家獨立事業群之策略，成功發揮品牌與代工交替運行之優勢，精準掌握電視產品與車用影音電子產品，在台灣形成一種具有特色之企業生存之道。普騰在延續過去技術基礎與成功模式的同時，兩岸與全球之競爭態勢已非同日而語，因此建議其適度放棄非核心家電，進攻利基型如車用數位影音與數位看板之產品，以儘早達成產業升級之目標。 / Digital Television (DTV) is the apparatus and technology that may convert analog video and audio to digital signals and send them to television viewers. It is also a type of display device that may present the image with high fidelity to the original recorded data. With the high quality on image and audio performance and the potential on providing value-added services like on-line personal data transmission, interactive program selection and shopping-at-home, DTV may launch enormous opportunity on developing tourism, transportation, entertainment, and culture industry. It will produce important impacts on the middle and long-term economic and technological development of Taiwan. Most of the countries are facing the fact that their deadlines of closing analog TV channels are coming. Meanwhile, most of the economy analysts believe that the purchase of new TVs or signal converters by customers will give big business opportunities in the coming years. DTV is a worthwhile research topic because of its particular role on elongating the prosperous status of flat-panel display industry and raise customers’ requirement on AV peripheral products like set-up boxes, home or vehicle electronic devices, and digital contents. It means a lot of facets especially when either Taiwan or the industry is entering a new era of digital revolution. Furthermore, DTV industry is a field that appears to be very promising but actually is highly competitive, crowded with aggressive competitors, and full of technology and product specification barriers. For a company that joins this game, what on earth the qualification to be required, the proper goal to be set, and the strategy to be adopted by the company, are within the focus of this study and will be discussed on the basis of large amount of explored data. The DTV explored by this study contains the fixed and mobile AV devices that may display images from wireless broadcasting stations, cable TV stations, satellites, and IPTV. The applications on displays on vehicles, mobile phones, anddigital signage devices are also covered in the discussion. The study raises a well-know Taiwan company, Proton, as an example to see the Proton’s advantages to DTV markets based on applying the analyses models proposed by Poter, Kotler, and Slywotzky to analyze the structure of the company, product features, and marketing strategies. A number of suggestions for its future development are drawn from the analyse results.

本文主要在探討自變數存在有測量誤差時，邏輯式迴歸模型的估計問題，並設計實驗使得測量誤差能滿足遞減假設，進一步應用序貫分析方法，在給定水準下，建立一個信賴範圍。 當自變數存在有測量誤差時，通常會得到有偏誤的估計量，進而在做決策時會得到與無測量誤差所做出的決策不同。在本文中提出了一個遞減的測量誤差，使得滿足這樣的假設，可以證明估計量的強收斂，並證明與無測量誤差所得到的估計量相同的近似分配。相較於先前的假設，特別是證明大樣本的性質，新增加的樣本會有更小的測量誤差是更加合理的假設。我們同時設計了一個實驗來滿足所提出遞減誤差的條件，並利用序貫設計得到一個更省時也節省成本的處理方法。 一般的case-control實驗，自變數也會出現測量誤差，我們也證明了斜率估計量的強收斂與近似分配的性質，並提出一個二階段抽樣方法，計算出所需的樣本數及建立信賴區間。 / In this thesis, we focus on the estimate of unknown parameters, experimental designs and sequential methods in both prospective and retrospective logistic regression models when there are covariates measured with errors. The imprecise measurement of exposure happens very often in practice, for example, in retrospective epidemiology studies, that may due to either the difficulty or the cost of measuring. It is known that the imprecisely measured variables can result in biased coefficients estimation in a regression model and therefore, it may lead to an incorrect inference. Thus, it is an important issue if the effects of the variables are of primary interest. When considering a prospective logistic regression model, we derive asymptotic results for the estimators of the regression parameters when there are mismeasured covariates. If the measurement error satisfies certain assumptions, we show that the estimators follow the normal distribution with zero mean, asymptotically unbiased and asymptotically normally distributed. Contrary to the traditional assumption on measurement error, which is mainly used for proving large sample properties, we assume that the measurement error decays gradually at a certain rate as there is a new observation added to the model. This kind of assumption can be fulfilled when the usual replicate observation method is used to dilute the magnitude of measurement errors, and therefore, is also more useful in practical viewpoint. Moreover, the independence of measurement error and covariate is not required in our theorems. An experimental design with measurement error satisfying the required degenerating rate is introduced. In addition, this assumption allows us to employ sequential sampling, which is popular in clinical trials, to such a measurement error logistic regression model. It is clear that the sequential method cannot be applied based on the assumption that the measurement errors decay uniformly as sample size increasing as in the most of the literature. Therefore, a sequential estimation procedure based on MLEs and such moment conditions is proposed and can be shown to be asymptotical consistent and efficient. Case-control studies are broadly used in clinical trials and epidemiological studies. It can be showed that the odds ratio can be consistently estimated with some exposure variables based on logistic models (see Prentice and Pyke (1979)). The two-stage case-control sampling scheme is employed for a confidence region of slope coefficient beta. A necessary sample size is calculated by a given pre-determined level. Furthermore, we consider the measurement error in the covariates of a case-control retrospective logistic regression model. We also derive some asymptotic results of the maximum likelihood estimators (MLEs) of the regression coefficients under some moment conditions on measurement errors. Under such kinds of moment conditions of measurement errors, the MLEs can be shown to be strongly consistent, asymptotically unbiased and asymptotically normally distributed. Some simulation results of the proposed two-stage procedures are obtained. We also give some numerical studies and real data to verify the theoretical results in different measurement error scenarios.

藝術欣賞二階段模型所發現的第二階段美感提升現象，若根據流暢性理論加以解釋，為單純曝光造成流暢性提升而導致的結果，未涉及認知處理歷程的影響，然而情緒評估理論以及Leder等人（2004）的美感經驗與評價歷程神經模型，都強調美感經驗為認知與情感的交互作用。針對上述兩類不同的理論觀點，本研究的目的在於探討認知涉入在美感歷程中的重要性，同時亦嘗試瞭解美感經驗中認知與情緒的關係。本研究讓參與者欣賞不同時代、流派與國家的具象藝術畫作，共分成三個實驗。實驗一收集美感相關情緒詞彙，發展美感情緒量表；實驗二與實驗三延伸Locher等人（2007）之實驗設計，分別收集美感偏好與美感情緒的資料，包含顯性與隱性指標，欲從美感提升現象中檢驗認知涉入對兩種美感歷程產物的影響力。實驗二關心美感偏好隨時間的變化，結果顯示認知涉入有助於偏好的提升，而隱性偏好亦有相似的趨勢；實驗三則發現美感情緒並沒有隨呈現時間增加而提升，而認知涉入的影響力也較不明顯，臉部EMG測量則未能反映出隱性美感情緒。本研究也發現，國畫較西畫更顯著地出現美感偏好或情緒的提升現象且較受認知涉入影響，此外，主觀偏好與不偏好的西畫在美感偏好與正向情緒類別之結果中，皆有類似適應的效果，其中主觀偏好畫作隨時間增長而正向情緒減少、負向情緒增加。綜合而言，本研究結果支持認知涉入為美感偏好提升之要素，但是無法確認認知與情緒兩者之間的互動關係，此外，藝術欣賞的第二階段不只有美感提升的現象，亦有美感下降的現象。 / The increase of aesthetic preference over viewing time was found in the study of the two-stage model of art appreciation. This phenomenon could be interpreted by mere exposure effect on improvement of fluency, not involving the influence from the cognitive processes. However, some theories (Silvia, 2011; Leder et al., 2004) emphasized the interaction between cognition and emotion in aesthetic experience. Based on these two kinds of theoretical perspective, the purpose of this study is to explore the role of cognitive involvement in aesthetic processes, and to understand the relationship between cognition and emotion in aesthetic experience. There are three experiments in this study, using the figurative art paintings from different era, genre and countries as the material. In Experiment 1, the emotional adjectives were collected to develop the scale of aesthetic emotion. In Experiment 2 and 3, the effects of cognitive involvement on aesthetic preference and emotion were tested, respectively. We extended the experiment design from Locher et al. (2007) to manipulate the degree of cognitive involvement additionally, with both the explicit and implicit indexes measured. Overall, the results showed that cognitive involvement helped the increase of preference, but not of emotion, because there was no increase of emotion founded. In addition, the effect of cognitive involvement in Chinese paintings was more obvious than that in West paintings. We also found that there could be adaptation effect in aesthetic process. In conclusion, the importance of cognitive involvement in preference increase was supported. But we cannot confirm the interaction between cognition and emotion. In addition, not only the increase of aesthetic preference and emotion, but also the decrease of them could be found in the second stage of art appreciation.