完整後設資料紀錄
DC 欄位語言
dc.contributor.author林婉筑zh_TW
dc.contributor.author李佳芸zh_TW
dc.contributor.author張佳橋zh_TW
dc.contributor.author林瑋臻zh_TW
dc.contributor.author蔣舒涵zh_TW
dc.contributor.author張峻榤zh_TW
dc.contributor.author朱以宸zh_TW
dc.contributor.author陳昶弘zh_TW
dc.date112學年度度一學期zh_TW
dc.date.accessioned2024-04-18T06:43:35Z-
dc.date.available2024-04-18T06:43:35Z-
dc.date.submitted2024-04-18-
dc.identifier.otherD0940083、 D0913102、 D0939978、 D0986513、 D0913180、 D0940096、 D0940585、 D0939921zh_TW
dc.identifier.urihttp://dspace.fcu.edu.tw/handle/2376/4925-
dc.description.abstract因受到COVID-19疫情影響,國際金融資產價格產生大幅度波動。本研究探討16筆金融資產波動有預測性作為分析,剖析國際金融資產的波動以引領投資者的決策。本研究利用R的‘quantmod’套件其取自Yahoo各資產股票的數據資料,我們選取的資產分別有國際大盤、各種產業股票、礦產和匯率,共16筆投資標的。分別用日與週報酬率時間數列進行分析,日資料的期間為2019年1月1日至2023年10月16日,而週資料的期間為2022年6月1日至2023年9月25日。本文提供各資產的敘述統計量、時間序列圖並使用各種變異數異質性模型配適日報酬率,包括變異數異質性GARCH模式,不對稱GARCH模式和Ljung-Box test, ARCH test, Engle-Ng joint test 三種誤差假設。診斷分析涵蓋:(i) Ljung-Box test檢驗時間序列數據是否存在自我相關(ii) ARCH test檢定資料是否有波動群集性 (iii) Joint test檢定模型波動性的不對稱性。透過日報酬與週報酬的波動來比較,以長期來看,波動幅度較大的資產為TSLA,但平均報酬仍為正,為高風險型投資;波動幅度較小的資產為美金兌台幣,且平均報酬也為正,為低風險型投資。以短期來看,波動幅度最大的資產也是TSLA,但平均獲利最高,為高風險高報酬投資;而阿里巴巴的波動幅度也較大,且有一點極大值,但平均獲利最低,為高風險低報酬投資。在長期和短期投資時間內,歐元兌美元、YAMAHA、阿里巴巴的夏普比率為負,顯示這些資產相對於風險而言,未能提供足夠的報酬。zh_TW
dc.description.abstractDue to the impact of the COVID-19 pandemic, international financial asset prices have experienced significant volatility. This study explores the predictability of fluctuations in 16 financial assets, analyzing the volatility of international financial assets to guide investors' decisions. Utilizing the ‘quantmod’ package in R, data on various assets' stocks were obtained from Yahoo, including major international indices, various industry stocks, minerals, and exchange rates, covering a total of 16 investment targets. The analysis was conducted using daily and weekly return time series, with the daily data spanning from January 1, 2019, to October 16, 2023, and the weekly data from June 1, 2022, to September 25, 2023. This study provides descriptive statistics for each asset, time series plots, and fits the daily returns with various heteroskedastic models, including GARCH models, and asymmetric GARCH models with three error assumptions. The tests provided include the Ljung-Box, ARCH, and Engle-Ng joint tests. The diagnostic checking includes (i) the Ljung-Box test to check for autocorrelation in time series data, (ii) the ARCH test to examine data for volatility clustering, and (iii) the joint test to assess the asymmetry of model volatility. When comparing the volatility of daily and weekly returns, TSLA is the asset with higher volatility over the long term, yet it maintains a positive average return, making it a high-risk investment. On the other hand, the volatility of USD to TWD is lower, with a positive average return as well, marking it as a low-risk investment. In the short term, TSLA also has the highest volatility but the highest average profit, making it a high-risk, high-reward investment; Alibaba's volatility is also high, with some extreme values, but it has the lowest average profit, classifying it as a high-risk, low-reward investment. Over short and long investment periods, the Sharpe ratios for EUR to USD, YAMAHA, and Alibaba are negative, indicating that these assets do not provide sufficient returns relative to their risks.zh_TW
dc.description.tableofcontents一、介紹 .......................................................................................... 4 二、資料來源.................................................................................. 6 三、研究方法.................................................................................. 7 1. Ljung-Box Test ........................................................................ 7 2. ARCH Test ............................................................................... 8 3.GARCH模型 ............................................................................ 9 4.GARCH-in mean 模型 .......................................................... 10 5.GJR-GARCH模型 ................................................................ 10 6.E -GARCH模型 ..................................................................... 10 7.Joint Test ................................................................................. 11 四、分析資料................................................................................ 12 A、週資料 .................................................................................. 13 B、日資料 .................................................................................. 19 C、Sharpe Ratio ....................................................................... 23 D、GARCH model ................................................................... 25 五、結論 ........................................................................................ 32 六、參考文獻................................................................................ 33zh_TW
dc.format.extent35zh_TW
dc.language.isozhzh_TW
dc.rightsopenbrowsezh_TW
dc.subjectE-GARCHzh_TW
dc.subjectGARCHzh_TW
dc.subjectGJR-GARCHzh_TW
dc.subjectGARCH-in mean模 型zh_TW
dc.subjectSharpe-ratiozh_TW
dc.subject風險報酬率zh_TW
dc.subject國際金融資產zh_TW
dc.subject槓桿效應zh_TW
dc.subjectGARCH-in mean modelzh_TW
dc.subjectInternational financial assetszh_TW
dc.subjectLeverage effectzh_TW
dc.subjectRisk return ratezh_TW
dc.title剖析國際金融資產波動 -引領投資者决策的關鍵zh_TW
dc.title.alternativeAnalyzing fluctuations in international financial assets - the key to leading investors' decision-makingzh_TW
dc.typeUndergracasezh_TW
dc.description.course課程名稱:統計專題(一 )zh_TW
dc.contributor.department統計學系, 商學院zh_TW
dc.description.instructor陳, 婉淑-
dc.description.programme統計學系, 商學院zh_TW
分類:商112學年度

文件中的檔案:
檔案 描述 大小格式 
1121-30.pdf2.31 MBAdobe PDF檢視/開啟


在 DSpace 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。