| dc.contributor.advisor | 徐士勛 | zh_TW |
| dc.contributor.advisor | Hsu, Shih-Hsun | en_US |
| dc.contributor.author (作者) | 黃仕鴻 | zh_TW |
| dc.contributor.author (作者) | Huang, Shih-Hung | en_US |
| dc.creator (作者) | 黃仕鴻 | zh_TW |
| dc.creator (作者) | Huang, Shih-Hung | en_US |
| dc.date (日期) | 2024 | en_US |
| dc.date.accessioned | 5-八月-2024 13:37:07 (UTC+8) | - |
| dc.date.available | 5-八月-2024 13:37:07 (UTC+8) | - |
| dc.date.issued (上傳時間) | 5-八月-2024 13:37:07 (UTC+8) | - |
| dc.identifier (其他 識別碼) | G0111258023 | en_US |
| dc.identifier.uri (URI) | https://nccur.lib.nccu.edu.tw/handle/140.119/152702 | - |
| dc.description (描述) | 碩士 | zh_TW |
| dc.description (描述) | 國立政治大學 | zh_TW |
| dc.description (描述) | 經濟學系 | zh_TW |
| dc.description (描述) | 111258023 | zh_TW |
| dc.description.abstract (摘要) | 本研究採用2016年至2023年的資料，探討總體變數潛在因子與27項台股產業股價指數報酬之間的關係。我們首先利用稀疏因子模型將大量的總體變數進行資料降維，找尋出3個總體潛在因子後，將因子作為解釋變數，觀察因子對於產業股價指數的月報酬是否有顯著影響，接著再從能解釋的類股中找出個股，觀察因子對於其的影響力。首先，因子1對於水泥類股指數月報酬具解釋力；而因子2對電腦及週邊設備業類、通信網路業、資訊服務業類、建材營造類以及航運業類有解釋力；最後，因子3則對生技醫療類指數月報酬具解釋力。
而在個股研究部分，我們發現因子1對於水泥業的台泥(1101)與信大(1109)有解釋力；而因子2則對於電腦及週邊設備業的伺服器族群、電信服務業的無線通訊設備個股、資訊服務業、建材營造業中的營造商個股以及航運業中的海運業族群有顯著解釋力；最後，因子3對於我們選取的生技醫療個股中，僅對中化(1701)、中化生 (1762)、美時(1795)以及國光生(4142)具解釋力。
最後，透過本文的研究結果，我們能找出在台股中，報酬率較容易受到景氣波動或是總體變數改變所影響的產業與個股，並為台股投資者在建構投資組合時提供更多訊息，當國內景氣發生變化時，投資人能透過本研究來選擇合適的產業與個股進行資產配置。 | zh_TW |
| dc.description.abstract (摘要) | This study uses data from 2016 to 2023 to examine the relationship between macroeconomic latent factors and the returns of 27 Taiwanese stock market sector indices. We employ a sparse factor model to reduce the dimensionality of numerous macroeconomic variables, identifying three macroeconomic latent factors. These factors are then used to determine their impact on the monthly returns of sector indices. Subsequently, we identify individual stocks within the explainable sectors to observe the factors' influence on them.
Factor 1 explains the monthly returns of the cement sector index. Factor 2 explains the returns for the computer and peripheral equipment sector, telecommunications network sector, information services sector, building materials and construction sector, and shipping sector. Factor 3 explains the monthly returns of the biotechnology and medical care sector index.
In individual stock analysis, Factor 1 explains the returns of Taiwan Cement (1101) and Hsing Ta Cement (1109). Factor 2 significantly explains returns for the server group in the computer and peripheral equipment industry, wireless communication equipment stocks in telecommunications services, information services stocks, construction company stocks, and the sea transportation group in shipping. Factor 3 explains returns for selected biotechnology and medical care stocks, including China Petrochemical Development Corporation (1701), China Chemical & Pharmaceutical Co. (1762), Johnson Chemical Pharmaceutical Works Co., Ltd. (1795), and Adimmune Corporation (4142).
Finally, the study's results help identify industries and individual stocks in the Taiwanese market that are more sensitive to economic fluctuations or changes in macroeconomic variables, providing valuable insights for investors in portfolio construction and asset allocation. | en_US |
| dc.description.tableofcontents | 1 緒論
1.1 研究背景 1
1.2 研究動機與架構 1
2 文獻回顧 3
3 實證模型 6
3.1 強、弱因子模型的差異 6
3.2 WF-SOFAR 估計式 9
3.3 邊緣分配(Edge Distribution) 演算法 10
4 實證資料 11
4.1 資料說明 11
4.2 資料分析 13
5 實證結果 15
5.1 總體稀疏因子與因子負荷量結果 15
5.2 三因子對類股解釋力 18
5.2.1 因子1 對類股的解釋能力 18
5.2.2 因子2 對類股的解釋能力 20
5.2.3 因子3 對類股的解釋能力 22
5.3 三因子對個股解釋力 22
5.3.1 因子1 對個股的解釋能力 24
5.3.2 因子2 對個股的解釋能力 25
5.3.3 因子3 對個股的解釋能力 31
6 結論與建議 32
參考文獻 35
附錄 37
A 多變量迴歸實證結果 37
B 類股資料一覽表與分析結果 40 | zh_TW |
| dc.format.extent | 1156588 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.source.uri (資料來源) | http://thesis.lib.nccu.edu.tw/record/#G0111258023 | en_US |
| dc.subject (關鍵詞) | 稀疏因子模型 | zh_TW |
| dc.subject (關鍵詞) | 總體潛在因子 | zh_TW |
| dc.subject (關鍵詞) | 產業類股報酬 | zh_TW |
| dc.subject (關鍵詞) | 股價報酬 | zh_TW |
| dc.subject (關鍵詞) | 波動性 | zh_TW |
| dc.subject (關鍵詞) | Sparse Factor Model | en_US |
| dc.subject (關鍵詞) | Macroeconomic Latent Factors | en_US |
| dc.subject (關鍵詞) | Industry Sector Returns | en_US |
| dc.subject (關鍵詞) | Stock Price Returns | en_US |
| dc.subject (關鍵詞) | Volatility | en_US |
| dc.title (題名) | 應用SOFAR導入弱因子模型分析台灣股價報酬與總體經濟波動關係 | zh_TW |
| dc.title (題名) | Applying SOFAR in Weak Factor Model by Analyzing Relation between Taiwan Stock Returns and Macroeconomic Volatility | en_US |
| dc.type (資料類型) | thesis | en_US |
| dc.relation.reference (參考文獻) | 張卓眾與王祝三(2013)，「台灣時間序列與橫斷面股票報酬之研究：不同模型設定、投資組合建構以及樣本選擇下之再檢測」，《經濟研究》，49(1)，31-88。
顧廣平(2005)，「單因子、三因子或四因子模式？」，《證券市場發展季刊》，17(2)，101-146。
Bai, J. and Ng, S. (2013), “Principal Components Estimation and Identification of Static Factors”, Journal of Economics, 176, 18-29.
Holloway, R. (2011), “An Empirical investigation of the APT in a Frontier Stock Market,” Munich Personal RePEc Archive, No.38675.
Onatski, A. (2010), “Determining the Number of Factors from Empirical Distribution of Eigenvalues,” The Review of Economics and Statistics, 92(4), 1004-1016.
Sarianidis, N., Giannarakis, G., Litinas, N. and Konteos, G. (2010), “A GARCH Examination of Macroeconomic Effects on U.S. Stock Market: A Distinction Between the Total Index and the Sustainability Index,” European Research Studies, Issue(1).
Uematsu, Y. and Yamagata, T. (2019), “Estimation of Weak Factor Model,” Ecinstor, ISER Discussion Paper, No.1053.
Uematsu, Y. and Yamagata, T. (2021), “Inference in Sparsity-induced Weak Factor Models,” Journal of Business & Economic Statistics. | zh_TW |
