本研究認為，在調查訪問中，選民是否表態並不是隨機產生的，一旦不表態的選民是因為某些因素而導致其不表態，只以表態者所建立的模型便存在選樣偏誤的問題。因此本研究便是希望經由處理「選樣偏誤」的問題之後，可以得到一個足以代表母體的正確投票模型，筆者將之稱為「選樣偏誤模型」，再利用「選樣偏誤模型」中校正後的參數估計值去推估未表態選民的投票意向，以得到更準確的選舉預測結果。 針對五次選舉（2001年台北縣長選舉、2002年北高市長選舉、2000年及2004年總統選舉）所進行的研究結果發現，當我們未校正選樣偏誤時，我們可能高估給予不同候選人較高評價者之間的差距、藍綠政黨認同者之間的差距、統獨支持者之間的差距；同時也高估了政府首長施政滿意度與省籍的影響。因為願意回答自己投票對象的受訪者，往往是政治偏好相當確定且較強烈的選民，當我們在建構模型時，若只掌握了這些政治偏好較強或較確定的表態者，而忽略政治偏好較弱或較不明確的不表態者，我們極可能高估自變數對應變數的影響。 整體來說，本研究所設定的選樣方程式能夠在勝負差距較小的選舉中，掌握到影響選民是否表態的因素，進而使得選樣偏誤模型發揮校正的功能，在勝負差距較小的選舉中，選樣偏誤模型所預測的候選人得票率，比傳統probit模型來得準確，四個模型的預測得票率與實際得票率的誤差，最小為0.59%，最大也只有1.16%而已。

本研究欲探討分析師推薦對管理當局所釋出資訊量之關聯性，當分析師越強力推薦公司時，公司的管理當局將願意提供較多的資訊給分析師做為預測的依據，則分析師對公司盈餘的預測也越準確。研究結果發現給予公司較佳推薦的分析師，預測準確性確實比給予公司較差推薦的分析師高。 之後再利用台灣證券暨期貨市場發展基金會設立的資訊揭露評鑑系統，探討資訊較為透明的公司，因為管理當局自願提供較多的資訊，即便分析師強力推薦，可能也無法得到額外的資訊，所以分析師推薦的效果應比資訊揭露較不透明的受評公司差。實證結果發現資訊揭露較透明的受評公司，分析師的推薦效果確實比資訊訊揭露較不透明的受評公司差。 / This thesis examines directly whether that managers provide more (less) information to analysts with more (less) favorable stock recommendations, based on the Barron et al. model (1998). Prior study documents the relative forecast accuracy of analysts before and after a recommendation issuance under the assumption that increases (decreases) in management-provided information will increase (decrease) analysts’ relative forecast accuracy. In contrast, this paper directly measure amount of information based on Barron et al. model (1998), and examine whether amount of information varies between pre- and post- a recommendation. Contrary to our prediction, the results show no significant difference in amount of information after and before recommendation issuance. However, we do find that analysts issuing more favorable recommendations experience a greater increase in their relative forecast accuracy compared with analysts with less favorable recommendations. In addition, we also find that the association is smaller for firms with higher information transparency than those with lower information transparency. The information transparency is measure by whether firms are listed in Taiwan Securities & Futures Information Center’s Information Disclosure and Transparence Ranking System (therefore TSFIC).

人口推估(Population Projection)涉及國家的政策及規劃，精確的結果可協助國家適時制訂政策，提高國民福祉。臺灣現在使用的方法為人口變動要素合成法(The Cohort Component Method)，可算是情境推估(Scenario Forecast)的一種，其起源可追溯至1920年代(Whelpton, 1928)，參酌專家意見之後，使用高、中、低三種推計來描述其變動範圍。除了情境推估外，近年在人口變動要素合成方法上發展出的新方法大致可以分成三種：一為隨機推估(Stochastic Forecast Method)、一為模擬情境(Random Scenario Method)、一為推估誤差(ex post Method)，美國及聯合國已經不單單依賴專家提供的傳統高、中、低推計，轉而使用這些新的推估方法。 由於近年來生育率快速降低、平均餘命延長以及外籍新娘增多等因素，大為提高人口推估的難度，因此本文將機率的概念併入人口推估中，以預測區間（Prediction Interval）來捕捉人口各項特性的可能變動範圍。除了回顧幾種在人口變動要素合成法中發展出的隨機推估方法及合併專家意見的方針外，也使用區塊拔靴法(Block Bootstrap)電腦模擬，進行臺灣、美國、日本、法國四個國家的人口推估。另外，本文也採用以Stoto(1983)提出的預測誤差估計，評估區塊拔靴法和人力規劃處推估結果之異同，以提供使用專家意見與隨機方法的參考。最後則是比較臺灣以北中南東小區域推估和臺灣整體的推估結果，並合併專家意見進行臺灣地區人口推估。

本論文採用了由Box and Jenkins(1976)所提出的ARIMA模型，以及由BOX and Tiao(1975)所提出的Intervention Model，去配適台灣的失業率型態，以及比較其預測的結果。 結果顯示出台灣的失業率具有季節性的型態，亦即台灣的失業率並非僅僅受到月分之間的相關，年分之間也有所關連。是故，當本論文在預測失業率的水準時，也考慮到此一因素，加入季節性的ARIMA模型對台灣的失業率加以預測。另外，時間序列的資料常常受到外生因素的干擾。對於失業率來說，政策上的改變將會影響失業率本身的結構，因此利用介入模式預測失業率，可以得到一組較精確的預測值。介入模式的事件有以下五個，分別是解嚴、六年國建、台灣引進外勞、中共飛彈試射、新十大建設。前四個事件的確影響了失業率的結構，不過第五項，也就是新十大建設並沒有顯著影響失業率的結構。理由可能是新十大建設的內容並不能合宜的解決經濟上與社會上的問題，以及這些建設尚未完工，以致無法達到期預期的效果。 比較兩模型的預測結果時，採用了MPE、MSE、MAE、MAPE作為模型評估的準則，結果指出介入模式的預測結果比起季節性ARIMA的預測結果來的有效率。 / This article adopts the ARIMA model, which was first introduced by Box and Jenkins (1976), and the intervention model, which was developed by Box and Tiao (1975), to fit the time series data for the unemployment rate in Taiwan, and thus to compare the results of the forecasts. The results reveal that there is a seasonal effect in the data on the unemployment rate. This indicates that the unemployment rate figures are not only related from month to month but are also related from year to year. When forecasting the level of unemployment, we should examine not only the neighboring months but also the corresponding months in the previous year. Time series are frequently affected by certain external events. In the discussion on the unemployment rate, the policies implemented by the government as well as military threats indeed influence the structure of the series. By making a forecast using the intervention model, we can evaluate the effect of the external events which would give rise to more accurate forecasts. In this study, there were five interventions included in relation to the unemployment rate series, which were as follows. First, the lifting of Martial Law in February 1987. Second, the Six-year National Development Plan launched in June 1991. Third, the hiring of foreign labor in Taiwan, which took effect in October 1991. Fourth, the threats of missile tests from the PRC in Feb 1996. Fifth, the ten new construction programs launched in November 2003. The first four events were indeed found to give rise to a structural change in the unemployment rate series at the moment when they occurred. This result might also have implied that not all of the actual effect of expansionary policies could have exactly decreased the unemployment rate, and therefore have solved the economic and social problems simultaneously. When we refer to the comparison of the above two models, the ultimate choice of a model may depend on its goodness of fit, such as the residual mean square, AIC, or BIC. As the main purpose of this study is to forecast future values, the alternative criteria for model selection can be based on forecast errors. The comparison is based on statistics such as MPE, MSE, MAE and MAPE. The results indicate that the intervention model outperforms the seasonal ARIMA model.

隨著中國經濟快速發展，許多中國企業選擇海外上市以因應全球化的潮流，雖然海外上市必須遵守當地交易所設定之規範與要求，但也讓企業享受到外部融資、提高股票流動性、增加知名度、改善公司治理水準等好處。本文則以上市地點之資訊環境作為判斷指標，探討中國企業以香港、美國、新加坡作為海外上市地點是否由於當地擁有良好的資訊環境。樣本期間為2007年，將分析師預測盈餘報導數量及盈餘預測誤差當作資訊環境的代理變數，分別用來衡量資訊環境之數量與質量，以OLS迴歸模型進行分析，本文所欲探討之議題之一為海外上市是否能改善企業的資訊環境，另一議題則是分析各海外上市地點的資訊環境有無差異。 實證結果顯示：一、以分析師預測數量作為代理變數，於香港、美國、新加坡三地上市皆能改善資訊環境，且香港及美國之間不存在差異，但兩地均優於新加坡；二、以預測誤差作為代理變數，只有當企業於美國上市時預測誤差顯著降低，於新加坡上市則預測誤差反而增加，顯示該地資訊環境品質不佳；三、公司規模愈大、盈餘波動愈小，則企業所獲得的報導數量較多，且預測誤差亦降低。

本論文分為兩部分，第一部份探討日經225和摩根台指成分股調整的價格變動效果。第二部份則是探討分析師對於股票被納入日經225和摩根台指的盈餘預測反應和絕對預測誤差。 / Two essays are comprised in this dissertation to examine the effects of changes in price and the analyst responses of earnings forecasts to stocks Indices adjustments. Stock markets vary in nature from one country to another and the characteristic of stock index adjustments also alter significantly. The analytical results can provide better information for investors and management to make better decisions. In the first essay, we examine price effects associated with changes in the composition of the Nikkei 225 Index and MSCI Taiwan Index. The analytical results show the price effects on stocks experiencing adjustments in the Nikkei 225 Index are consistent with the price pressure hypothesis. The price effects of composite stocks changed for the MSCI Taiwan Index are consistent with the downward sloping demand curve hypothesis. Based on classifying the characteristics of composite stocks into three categories, we find that large-scale added stocks dominate the price trend of the whole added sample in the Nikkei 225 Index. Also, added stocks with upwards revision earnings forecasts make more abnormal returns than the added stocks with downwards revision earnings forecasts in the Nikkei 225 Index during the post-announcement period. The electronic stocks earn larger abnormal returns than non-electronic stocks in the MSCI Taiwan Index. That can enable investors to profit by buying electronic stocks and added stocks with upwards revision earnings forecasts. The price reactions for the composite stocks in the Nikkei 225 Index and MSCI Taiwan Index around the Internet bubble burst have significantly difference. In the second essay, we study the earnings forecast changes and absolute forecast errors made by analysts of the Nikkei 225 Index and MSCI Taiwan Index. Depending on the properties of brokerage firms that analysts work for, we divide them into local analysts and foreign analysts to separate who are more accurate than one the other. The results show that in comparison with the matching firms in Japan, the magnitudes of mean forecast revisions and absolute forecast errors are smaller made by analysts focusing on firms newly added to the Nikkei 225 Index. For firms newly added to the MSCI Taiwan Index, the magnitude of changes in analysts EPS forecasts do not differ clearly from those of their peer groups. Absolute forecast errors made by analysts focusing on firms newly added to the MSCI Taiwan Index are smaller than those made by analysts focusing on the matching firms. This phenomenon demonstrates firms that are newly added to the Nikkei 225 Index and MSCI Taiwan index exhibit significantly improved performance. In terms of the relative accuracy of local and foreign analysts, the results display that the forecasts of foreign analysts are less accurate than those of local analysts in Japan and the forecasts of foreign analysts are more accurate than those of local analysts in Taiwan.

無 / Existing literature has shown that force of mortality has amazing resemblance of interest rate. It is then tempting to extend existing model of interest rate model context to mortality modeling. We apply the model in Diebold and Li (2006) and other models that belong to family of yield rate model originally proposed by Nelson and Siegel (1987) to forecast (force of) mortality term structure. The fitting performance of extended Nelson-Siegel model is comparable to the benchmark Lee-Carter model. While forecasting performance is no better than Lee-Carter model in younger ages, it is at the same level in elder ages. The forecasting performance increases for 5-year ahead forecast is better than 1-year ahead comparing to Lee-Carter forecast. In the end, the forecast outperforms Lee-Carter model when age dimension is trimmed to age 20-100.

本文引用Pagan and Sossounovb（2003）針對Bry and Boschan（1971）景氣循環周期判定法修改後的法則，判定大盤與類股指數的牛市、熊市周期。將判定的周期結果畫成圖表，藉由簡單的圖表分析將可明確得知大盤周期與類股周期領先與落後的關係，並應用計量模型估計，找尋能夠顯著預測大盤周期變動方向的類股，或是檢驗大盤周期是否能夠預測類股周期方向；反之亦然。並且比較圖表分析與計量模型估計結果是否一致。 圖表分析與向量自我迴歸模型的實證結果一致，八大類股中，營建、金融、機電、塑化等四類股周期能夠顯著預測大盤周期走勢，其中以塑化類股最具預測能力；而大盤周期皆無法精準預測類股周期走勢。而羅吉斯迴歸模型結果也發現，營建、金融、機電、塑化等四類股周期能夠增加大盤周期走勢的預測機率；同樣的，大盤周期無法影響類股周期走勢的預測機率。

自工業革命之後，人類與科技間關係的變化牽引著整個社會、經濟的發展，而其中泛用型科技(GPTs)又扮演著要角，科技持續以指數式速度發展，大數據的出現是有脈絡可循的，某個程度上來說(從資料及分析兩方面的演進觀之)，可以說是必然發生的。大數據分析，不是時尚名詞，而是一個影響著現在及未來的大趨勢，縱有許多反對的聲音與論述，但它確實已經是國家安全戰略的一環，也是企業生存戰賴以維生的命脈。 大數據與過去不同的是我們擁有更多資料的來源，資料可能來自外部(Open Data、第三方資料)，也可能是更精進的資料蒐集機制得來(如：設計誘因機制使顧客自願提供其資料或設計隨機試驗取得異於歷史資料的新資訊)，而在資料種類格式、資料取得與回饋反應的速度上，在新興的MapReduce技術、NoSQL資料庫及串流資料處理技術支撐下，均可有效即時或近即時地被完成。 大數據分析最重要的還是在於「預測分析」，而為了讓資料說話，我們要熟悉大數據的特性與缺點，而支持大數據的硬技術與軟技術發展上一日千里，更提升了大數據在各產業的應用可能，而投資大數據的企業營收比那些沒有投資大數據的企業可以高出12％以上，在多數產業紛紛投入這場軍備競賽取得初步成效之際，而傳統壽險產業在大數據及其他科技變革的因應上不如別的產業時，則應在壽險價值鏈上去觀察並利用大數據分析，突破現有商業模式，選擇最佳導入策略，尋覓理想的資料科學家擔任CDO，委任其組織分析團隊並擬定大數據成長策略，建立適切軟硬體的架構，並完成第一個先導計畫取得小規模成功，進而加強企業高層大數據分析的信心與投資意願，使得一的又一個專案得以遂行，最終形塑成資料導向的決策文化，成為可以因應未來的壽險公司，避免在這波科技變遷中成為被淘汰者。

在科技持續進步的時代，金融市場發展隨著社會的演進不斷地成長與活絡，金融商品也從原本單純的本國存放款、外幣投資衍生出票券、債券等利率投資工具；除此之外，隨著資本市場的擴張，股票、基金、期貨與選擇權等投資標的更是琳瑯滿目。 而後產生了許多人使用資料探勘工具預測市場的買賣時機。如Baba N., Asakawa H. and Sato K.(1999)使用倒傳遞類神經網路來預測到股市未來的漲跌，而後又在2000年研究當中加入基因演算法來求得倒傳遞類神經網路的權重，得到最後的類神經網路模型。 在做資料探勘的同時，我們得在希望預測目標(Target)上事先定義好一套固定規則，這會使得模型的彈性與可預測度降低，本研究希望能透過資料探勘工具增加預測目標規則的彈性，增加模型最後的預測準確度。 本研究樣本區間選用2010年到2015年的台指期貨數據做為資料，並結合羅吉斯回歸與粒子群演算法建構更加有彈性的預測模型結果，最後發現在未來10分鐘，若漲幅超過0.1114%做為買進訊號的話，其建立出的模型可達到84%的預測準確度。