| dc.contributor | 國貿系 | |
| dc.creator (作者) | 郭炳伸 | |
| dc.date (日期) | 2020-05 | |
| dc.date.accessioned | 7-Apr-2026 13:28:42 (UTC+8) | - |
| dc.date.available | 7-Apr-2026 13:28:42 (UTC+8) | - |
| dc.date.issued (上傳時間) | 7-Apr-2026 13:28:42 (UTC+8) | - |
| dc.identifier.uri (URI) | https://ah.lib.nccu.edu.tw/item?item_id=181950 | - |
| dc.description.abstract (摘要) | 很多模擬的證據顯示，既有的穩健檢定並不穩健。主要歸因於，常用的長期變異數估計，呈現很大的均方差。為了減緩這問題， 本研究企圖建構新的平均估計式。該估計式，是將所有單獨的自我迴歸光譜估計，平均而得 。本估計式的特殊，在於建構時，同時考量估計與檢定。因此，在推導每一自我迴歸光譜估計的權重時，是由最小化檢定均方差而得，而不是最小化該平均估計式的均方差。 顯然地，本平均長期變異數估計式，將會有截然不同的統計性質。本計畫希望以2年期完成探討下列議題：(1)決定每一自我回歸光譜估計的最適權重，以及推導更重要的漸近性質；(2)發展本平均估計式的漸近理論，以及推導其漸近風險；以及 (3)模擬研究本平均估計式 ，對檢驗穩健度的改善程度。 | |
| dc.description.abstract (摘要) | As shown by ample simulation evidence, the robust testing procedures usuallydisplay substantial size distortion and power loss. It mainly attributes to the large mean-squared error of the existing long-run variance estimators used in the testing procedures. To remedy the problem, this project attempts to propose a new parametric estimator by averaging all the potential autoregressive spectral estimates. The novelty of the project lies in deriving the averaging estimator in an integrated approach where the estimation and testing are considered simultaneously. Instead of minimizing that of the averaging estimator itself, the weights assigned to each individual estimate are obtained by minimizing mean-squared error of the test statistic involving it. Thus, the proposed averaging long-run variance estimator appears to carry a very distinct character. This motivates and opens up a handful of research questions to be addressed in the projectregarding its statistical properties.Major investigations of the planned 2-year project should constitute:(1) To determine the optimal weight assigned to each considered autoregressive spectral estimate under the integrated MSE framework, and importantly to develop asymptotic theory of the optimal weights;(2) To develop the asymptotic theory of the proposed averaging estimator, and to derive its asymptotic risks; and(3) To examine to what extents the robustness of the test statistics using the averaging estimator make improvements in the finite sample. | |
| dc.format.extent | 116 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | 科技部, MOST107-2410-H004-019, 107.08-108.07 | |
| dc.subject (關鍵詞) | 均方差; 平均估計式; 長期變異數估計; 自我迴歸光譜估計 | |
| dc.subject (關鍵詞) | mean-squared error; averaging estimator; long-run variance estimator; autoregressive spectral estimator | |
| dc.title (題名) | 平均長期變異數估計 | |
| dc.title (題名) | Averaging Long Run Variance Estimation | |
| dc.type (資料類型) | report | |
