本研究探討Banker and Chen (2006)建構之CVCS模型與本研究建構之CVCS’模型之盈餘預測準確度與資訊內涵，並以ROE模型、OPINC模型、CASHFLOW模型與分析師盈餘預測作為判斷CVCS模型與CVCS’模型是否具有盈餘預測準確度與資訊內涵之比較基準模型。盈餘預測準確度之實證結果顯示：(1)CVCS模型之盈餘預測準確度低於ROE模型、OPINC模型與CASHFLOW模型之盈餘預測準確度；(2)CVCS’模型與ROE模型、OPINC模型、CASHFLOW模型之盈餘預測準確度並無差異；(3)CVCS模型之盈餘預測準確度低於分析師盈餘預測之盈餘預測準確度；(4)CVCS’模型之盈餘預測準確度低於分析師盈餘預測之盈餘預測準確度。資訊內涵之實證結果顯示：(1)CVCS模型之資訊內涵高於ROE模型、OPINC模型與CASHFLOW模型之資訊內涵；(2)CVCS’模型之資訊內涵低於ROE模型、OPINC模型與CASHFLOW模型之資訊內涵；(3)CVCS模型之資訊內涵低於分析師盈餘預測之資訊內涵；(4)CVCS’模型之資訊內涵低於分析師盈餘預測之資訊內涵。 / This study examines the forecast accuracy and the information content of CVCS model, proposed by Banker and Chen (2006), and CVCS’ model, constructed by this study. To evaluate the performances of these two models, this study uses ROE model, OPINC model, CASHFLOW model and analysts’ consensus forecasts as the benchmarks. The results of forecast accuracy show (1) the forecast accuracy of CVCS model is less than that of ROE model, OPINC model, and CASHFLOW model, (2) the forecast accuracy of CVCS’ model is not different from that of ROE model, OPINC model, and CASHFLOW model, (3) the forecast accuracy of CVCS model is less than that of analysts’ consensus forecasts and (4) the forecast accuracy of CVCS’ model is less than that of analysts’ consensus forecasts. The results of information content show (1) the information content of CVCS model is greater than that of ROE model, OPINC model, and CASHFLOW model, (2) the information content of CVCS’ model is less than that of ROE model, OPINC model, and CASHFLOW model, (3) the information content of CVCS model is less than that of analysts consensus forecasts, (4) the information content of CVCS’ model is less than that of analysts consensus forecasts.

本研究從損益表角度切入，驗證分析師盈餘預測之修正與未預期盈餘組成項目變動之關係，是否有助於分析師預測公司未來盈餘的波動。實證結果顯示，分析師在不同時間點所做的預測修正與未預期盈餘組成項目變動顯著相關。分析師預測公司當期及次期盈餘時，會考量其未預期盈餘組成項目。此外，分析師預測修正與未預期盈餘組成項目之關連性與兩者之時距呈反向關係，亦即次期盈餘預測之修正與當期未預期盈餘組成項目之關係顯著較低。再者，分析師對當期（以月份為基礎）盈餘的累積預測修正與上一期的未預期盈餘組成項目息息相關，且隨著時間的推移，二者之關連程度愈趨明顯。整體而言，損益表盈餘組成項目之變動對分析師在不同時間點所做之盈餘預測，具有價值攸關性。 / This study examines whether earnings components can help financial analysts predict firms’ earnings by investigating the association between analysts’ forecast revisions and firms’ unexpected changes in earnings components. Our results show that analysts’ forecast revisions made in different time horizons are consistently associated with unexpected changes in earnings components. Financial analysts are able to incorporate current-year unexpected earnings components into their current and future earnings forecasts even before firms officially release this information. Current-year’s unexpected earnings components are, however, not fully incorporated into analysts’ forecasts of future earnings. Analysts appear to wait for more information releases regarding firms’ future earnings and delay their revisions of future earnings forecasts. This is consistent with the evidence that the cumulative revisions of current earnings forecasts are generally associated with its prior-year’s unexpected earnings components, and the association appears to be stronger as time progresses. Overall, this study provides evidence suggesting that earnings components do have value relevance and can help financial analysts identify firms’ earnings changes over time.

本研究主要探討公司設置獨立董監事及其專業性，對於分析師進行公司盈餘預測時是否會產生影響。由於上市櫃審查準則的規範，本研究將樣本分為兩群，第一群樣本為受此準則規範，須強制設置獨立董監事之IPO公司，第二群樣本為不受此準則規範之上市櫃公司，以研究透過獨立董監的設置，是否會對分析師行為產生影響。 研究結果發現，獨立董事的設置有助於降低分析師預測離散度，尤其是具有專業背景之獨立董事，對於降低分析師的預測誤差及預測離散度有顯著影響；在獨立監察人方面，僅具專業背景之獨立監察人對於提升分析師跟隨人數有顯著影響。另外，亦發現受規範公司樣本對於分析師預測行為之影響力明顯大於不受規範公司樣本，本研究推論其原因為國內除了新上市櫃有因應法規之需求而設置獨立董監事外，一般上市櫃公司並無強大誘因促使其設立獨立董監事，造成自願設置之樣本數量過少，而導致其實證結果不顯著。 / This study investigates the effect on the forecasting behavior of analysts through employing independent directors or independent supervisors and their professional background. According to the listed examination criterion of TSEC and OTC, the samples are classified into two groups: companies regulated by the law and non-regulated companies. The empirical results suggest that independent directors contribute to reducing forecasting dispersion of analysts. Furthermore, independent directors who have professional background contribute to reducing forecasting dispersion and forecasting error of analysts. In terms of independent supervisors, only people who have professional background are positively related with analyst following. The results also show that regulated companies have more significant influence on analysts than non-regulated companies do, indicating that in response to the listed examination criterion of TSEC and OTC, regulated companies have to employ independent directors and independent supervisors. On the other hand, there is no motive for non-regulated companies to employ independent directors and independent supervisors, resulting in no significant impact on forecasting behavior of analysts.

點預測為目前使用最多之預測陳述,其效率評估亦多以最小平方和誤差(minimum of sum of square errors)為主。每日或月的經濟或財金指標預測是點預測最常見的例子。但是隨著區間時間數列真正需求與軟計算(soft computing)科技的發展,區間計算與預測愈來愈受重視。本文提出幾種區間時間數列預測的方法,並研究其效率評估。在第三章,我們定義區間誤差和,並將其對應到實數值,以便用傳統的方法計算。最後我們以影響經濟作物的天氣預測,作實證研究分析。考慮在無參數條件下,幾種預測方法作效率評估與準確性探討。天氣預測是區間預測的例子,建立合適的的區間預測方法與效率評估,對各研究領域將會有莫大的幫助。 / Currently, the most use of forecasts is the point forecasting, whose efficiency evaluations are major in the least squares and error (minimum of sum of square errors). The common examples of the point forecasting are daily or monthly economy index or financial estimation. But along with the real demand of interval time series and the development of soft computation (soft computing), the interval computation and the forecasting are more and more important. This article provides some interval time series forecasting methods, and studies the efficiency evaluation. In chapter 3, we define sum errors of interval and correspond them to the real numbers, so as to compute with traditional way. Finally, we decide to use the weather forecasting which can affect the cash crop to be the empirical study analysis. Consider some forecasting methods under the non-parameter condition to be the efficiency evaluations and the accurate discussion. The weather forecasting is an example of interval forecasting. It will be more helpful of each research area if we establish the appropriate interval forecasting method and the efficiency evaluation.

本研究探討分析師在進行盈餘預測時是否會考慮會計師的審計品質。不同於過去文獻，本研究除了測試「品牌層級」的審計品質（brand-name level audit quality）與「事務所層級」（firm level audit quality）的審計品質外，利用我國簽證制度進一步檢視分析師盈餘預測之品質是否因會計師個人層級之審計品質 (individual-level audit quality) 的差異而有所不同。本研究以Heckman (1979) 之兩階段模型來控制會計師選擇內生性的問題，進行實證分析。實證結果顯示：(1) 四大會計師事務所對於分析師預測準確度具有正面影響，但侷限於小規模公司，呈現顯著正相關。(2) 四大事務所彼此之審計品質對於分析師預測準確度與離散程度之影響，並無顯著之差異，但整體來說，資誠會計師事務所之表現最佳，而小規模公司中，安永之表現較差；大規模公司中，勤業眾信之表現較差，此與一般市場所認知者不同。(3) 當分析師盈餘預測之對象為小規模公司時，審計品質最差的個別會計師會降低（提高）分析師預測準確度（離散程度）。反之，測試對象為大規模公司時，審計品質最佳的個別會計師會降低分析師預測準確度但，審計品質最差者，與本研究預期不符。結果顯示我國之分析師在進行盈餘預測時，會考量個別會計師之審計品質。 / This paper investigates the association between audit quality and properties of analysts’ earnings forecasts. Three levels of audit quality are identified and examined: brand-name level (proxied by a dummy Big 4), firm level (proxied by four dummies DT, PWC, KPMG, and EY), and individual-level (proxied by the average of the absolute values of discretionary accruals for all companies audited by the same auditor, grouped by quartiles). After separating sample companies into big, medium, and small sizes, the empirical results document several important findings. When audit quality is measured at the brand-name level, Big 4 improve analysts’ forecast accuracy for small companies only. However, Big 4 do not decrease analysts’ forecast dispersion. When the audit quality is measured at the firm level, analysts seem to regard EY and DT as of relatively low audit quality when small and big companies are the forecast targets, respectively. When the audit quality is measured at the individual level, auditors who are deemed to have the lowest audit quality (i.e., in the fourth quartile) are associated with less forecast accuracy and greater forecast dispersion in small companies. In contrast, auditors who are deemed to have the highest audit quality (i.e., in the first quartile) are associated with lower forecast dispersion in big companies. Taken together, the empirical results indicate that audit quality affects analysts’ forecast properties. More importantly, analysts are able to identify individual auditor’s audit quality and react accordingly.

中華民國第十任總統選舉結果於民國八十九年三月十八日揭曉，這場眾所矚目的選舉終告落幕，然而對選舉研究工作者而言卻是新的開始。選舉預測居選戰中重要的一環，也是研究選舉的學者關心的問題，更提供了一個驗證選民投票行為理論的絕佳機會，近來國內相關論述已有相當成果。但由於它在投票結束，便有答案，其挑戰程度不言而喻。因此，如何結合理論、方法及事實三者為一體的努力，對選舉預測更是別具意義。 本篇研究之範圍，是以公元2000年總統大選為例，對選舉預測工作做更深層的探討，且檢驗邏輯斯預測模型（Logistic Regression Model）及模糊統計（Fuzzy Statistics）分析在本次總統選舉的預測力，考量本次總統選舉中各項可能影響選情的因素，進一步建構選舉預測模式，然而兩種預測模式的初步預測結果並不佳，經過棄保效應的可能性調整後，預測誤差已大幅降低，其中模糊統計（Fuzzy Statistics）分析預測結果經棄保效應調整後，與實際開票結果相當接近，因此與邏輯斯預測模型相較，模糊統計分析的應用對未表態選民投票意向的預測力較佳。一套完整的選舉預測模型研究，應包含問卷設計、抽樣訪問、資料處理、加權除錯、模型設計與預測評估等整套研究流程，然而在本次總統大選中，由於三強激戰，影響選情因素相當複雜，最後此兩種選舉預測模式皆無法獲致精確的預測結果。因此，我們期待選舉預測模型的建構，能突破主客觀環境的侷限，進一步達到「準」與「穩」的要求。 / With the successful staging of the 2000 presidential elections in Taiwan, scholars have been presented with a new opportunity to test their theories. Electoral predictions are an important field within the study of elections and have been among the most keenly studied questions over the past few years. Unlike many other research topics, there is an absolute standard for election predictions: the election results. Thus, combining theory, methodology, and facts to obtain a meaningful result is no simple task. This thesis attempts to predict the 2000 presidential election using both a logistic regression model and a fuzzy statistics model. After constructing models which includes all kinds of different variables that might influence the electoral outcome, we find that neither the logistic regression model nor the fuzzy statistics model is particularly accurate. However, after accounting for the effects of strategic voting, model error decreases dramatically. In particular, after including provisions for strategic voting, the fuzzy statistics model is improved to the point that its predictions are extremely close to the actual outcome. Thus, we show that the fuzzy statistics model is superior to the logistic regression model in analyzing the vote choices of undecided voters. Research on electoral predictions should include such aspects as questionnaire design, sampling, interviewing, data processing, weighting, data cleaning, model design, and evaluation of the prediction. However, because this election featured a particularly intense three way race, the factors affecting the electoral outcome were both numerous and intertwined in complex ways. Unfortunately, it is impossible to evaluate our electoral predictions of the two models precisely. We hope that in the future, election prediction models will be able to break through these environmental limitations and achieve more accurate and stable predictions.

範例學習(Learning-from-Example, LFE)技術的發展，在人工智慧發展領域中，已成功地突破關於知識萃取的瓶頸，並廣泛地應用到諸多評估或預測模式以及專家系統的建立。在本研究中，以台灣上市公司歷年來的財務報表資訊，進行企業盈虧的預測，並探討判斷個案申出現資訊遺漏與雜訊時，對範例學習系統在企業盈虧預測所產生之影響。主要的影響分別為預測績效的衰減(attenuating)與干擾(disturbing)兩類。本研究並藉由「資料預先處理轉換」及「修正系統演算法」兩方面著手，來避兔或減少上述現象發生時，對範例學習系統在企業盈虧預測績效所造成之影響。 因此本研究主要以民國七十五年到八十四年期間，共十五項大小產業之股票上市公司財務報表及股價報酬等資料作為研究樣本，整體市場共計有3199筆樣本資料。而研究的進行可分為實驗設計階段以及實証資料測試階段。 實驗設計階段中，將探討當建樹或預測之資料含有資訊遺漏與雜訊時，對企業盈虧預測範例學習系統所造成之衰減與干擾效果。在資訊遺漏之探討下，分就「資料預先處理轉換」及「修正系統演算法」兩方面，評比了「線性內插法」、「迴歸預測法」、「獨立分群法」及「多重線索分割法」等四種之遺漏值解決方案，在區別能力及預測績效上之差異性；在雜訊之探討，則了解到雜訊對範例學習系統究竟會造成多大之干擾效果，並進一步測試雜訊過濾器是否能降低部份之干擾效果。 而接下來的實証資料測試階段，則以實証資料測試上述各種模式及方法，而獲得之結果將和實驗設計階段之結果作一比較對照，以符合實務應用之狀況。而根據研究結果顯示，主要可獲得下列結論： 一、分就：1. 建樹資料含遺漏或雜訊，2. 預測資料含遺漏或雜訊，3. 建樹及預測資料同時含遺漏或雜訊，三種情況考量。則第2種情況下對範例學習系統所造成之衰減或干擾效果相對較大，第3種情況次之，第1種情況較無影響。 二、在資訊遺漏之探討下： （一）、「迴歸預測法」及「多重線索分割法」最能避免衰減效果之發生，但前提是必需存在高度相關之替代線索。 （二）、最為簡便也最常被使用之「線性內插法」，並無法有效排除遺漏值所造成之衰減效果，而這和財務比率線索不具備單調性(Monotonicity)之原因有關。 （三）、對於遺漏值之處理若是採取整筆刪除之作法，則對系統之預測績效而言（命中率）可能造成較大之衰減效果，因為其可能破壞學習樣本資料之代表性。 （四）、在無高度相關替代線索，或者是系統之例子資料庫含有計質性(Qualitative)線索時，可以「獨立分群法」來降低遺漏值之衰減效果。 三、在雜訊之探討下： （一）、雜訊對範例學習系統之干擾效果是存在的，因此在蒐集處理樣本資料之過程中，即應小心避免雜訊混入其中。 （二）、雜訊過濾器能否排除影響樣本代表性之極端值，就結果看來並不能獲得一致之結論；或者是對極端值取捨之界限定義應為何？則有待更進一步之研究。

投資的獲利多寡並不單單基於預測的準確性，信心度的大小亦攸關獲利的結果。因為信心度愈大，則投資人將會提高投資的金額，而獲得更多的利潤。反之，雖然預測的結果是準確的，但若信心度很小，則投資人將不敢投入較多的金額，如此一來所獲得的利潤就有限了。本文嘗試著應用信心度函數來輔助說明多變量模糊時間數列預測結果，亦即預測模式對預測結果的屬性所具有的信心程度。最後利用多變量模糊時間數列模式，結合加權股價指數的收盤價及成交量兩個變量，針對台灣加權股價指數進行預測及衡量預測屬性的信心度。相信這對於風險控管及提高投資報酬深具意義。

從過去的研究顯示，預測市場(prediction market)已有良好預測準確率，但該準確率是事後、總體的機率概念，而非更有實際參考價值：事前、個別合約之鑑別預測。故本文先以建構4個選舉預測市場準確度的鑑別模型，在選前針對每一個選舉合約的交易價格進行鑑別，模型的鑑別資訊來自於，預測市場在選前一天提供選舉合約的40個原始自變數。我們的研究顯示：Logit鑑別模型最能在「選前」精準判斷，並可分辨哪些選舉合約的價格，在未來將符合「最高價」準則。本文前半部先以：2008年總統選舉、2009年縣市長選舉及2010年五都市長選舉，做為樣本外測試的樣本，使用原始自變數的Logit模型，其預測力均高於其他3個鑑別模型。Logit模型樣本外的鑑別正確準確率為100％，但是，Logit模型對於鑑別未正確預測組的預測能力仍須改善。最後，本文再使用全部「非選舉」和選舉類別的合約，成功建構預測市場的最適價格門檻，作為判定預測事件是否發生的標準，可將事件發生的機率預測（probabilistic forecasting），轉換成事件發生與否的類別預測（categorical forecasting），作為公共政策與企業決策的重要依據。

協同規劃、預測與補貨（Collaborative Planning, Forecasting and Replenishment; CPFR）是協同商務中一個新發展的應用實務，主要強調供應鏈上買賣雙方協同合作流程的概念，以提升供應鏈上流程的處理效率。企業需要利用協同合作所獲得之即時資訊來進行預測，減少不確定性因素之影響，提高預測之準確性。CPFR流程下協同預測階段分為銷售預測與訂單預測，兩者之預測項目與目的並不相同且所需要之資訊亦有所差異。銷售預測著重在市場需求部份的預測；訂單預測則是依據銷售預測、存貨狀況與生產面因素來做實際訂單之預測。由於訂單預測作為下個階段之實際補貨的參考，其預測準確性的要求就格外重要。然而研究文獻多偏向CPFR流程架構與導入效益等管理議題，雖有少數針對預測模型之研究，但亦以企業內部銷售預測為主，並未有文獻提出跨企業之協同訂單預測模型，故CPFR流程下訂單預測方法之研究探討有其必要性。本研究以CPFR流程中接續銷售預測之訂單預測階段為研究主題，蒐集近年來國內外研究CPFR與訂單預測之相關文獻為基礎，歸納出協同合作下訂單預測所須具備之屬性與影響因素，並作為模型解釋變數，透過時間序列、多元迴歸與演化策略法（Evolution Strategies）的結合，建構一個統整供應鏈上、下游協同資訊與符合CPFR流程下訂單預測特性之預測模型。最後以國內某製造業公司與其顧客（一國際大型零售商）之訂單資料進行模型驗證，與單純使用時間序列方法或統計迴歸分析的預測結果作績效評比，實驗顯示本研究所提出之訂單預測方法較傳統使用單一時間序列或統計回歸方法之預測結果佳。 / Collaborative Planning, Forecasting and Replenishment (CPFR) is nowadays a practice of collaborative commerce, emphasizing buyers and sellers’ coordination for the efficiency of the process in supply chain. Enterprises utilize instant information obtained from coordinate processes to forecast in order to reduce the influence of the uncertain factor and improve forecasting accuracy. The stage of the collaborative forecasting in CPFR process is divided into sales forecasting and order forecasting which make differences on forecasting objective, subject, and information needed. Sales forecasting focuses on the prediction of the market demand; order forecasting is the prediction of the real orders according to sales forecasting, stock state and productive factor. The accuracy of order forecasting is extremely important because it is regarded as the reference of the replenishment at next stag. The literatures about CPFR mostly probe into manage topics like benefits of implementation or process structures though there are some researches on the forecasting model which mainly discuss sales forecasting inside enterprises. Therefore, it is necessary to investigate into the coordinative order forecasting model under CPFR process. This paper regards order forecasting following sales forecasting in CPFR as the theme. Besides generalizing the necessary parameter of order forecasting based on literatures review, the research presents a hybrid forecasting model which considers coordinative information and order forecasting requirements. It integrates the time series model, regression model, and use evolution strategies to determine its coefficients efficiently. The validity of the forecasting model is verified by experiment on order datum from one manufacturer in Taiwan and its international retailer. The results show that the order forecasting model has better forecasting performance than not only the time series model but also the ordinary regression model.