發(fā)布時(shí)間：2018-06-26 20:37

  本文選題：小波變換 + 局部線性尺度近似法��； 參考：《天津大學(xué)》2014年碩士論文

【摘要】：股票價(jià)格的變化是由信息的到達(dá)所引起的，如何準(zhǔn)確及時(shí)的掌握新信息的到達(dá)，對(duì)于揭示股票價(jià)格的內(nèi)在形成機(jī)制具有重要的意義，在對(duì)股票價(jià)格時(shí)間序列的分析中，除了長(zhǎng)期趨勢(shì)和季節(jié)變動(dòng)趨勢(shì)外，還有一種變動(dòng)也是由外部事件引起并會(huì)對(duì)時(shí)間序列走勢(shì)產(chǎn)生持續(xù)影響，即突變點(diǎn)，包括跳躍點(diǎn)（jumps）、陡坡（steepslopes）等，它往往包含重要信息卻被誤認(rèn)為噪聲進(jìn)而被忽視。高頻金融時(shí)間序列的突變點(diǎn)往往包含重要信息，準(zhǔn)確檢測(cè)和分析突變點(diǎn)的發(fā)生對(duì)投資決策具有重要意義。統(tǒng)計(jì)數(shù)據(jù)挖掘方法（或模型）需要一種去噪算法來清洗數(shù)據(jù)，從而獲得可靠和顯著的結(jié)果。大多數(shù)數(shù)據(jù)清洗方法只專注于某些已知類型的不規(guī)則行為。對(duì)于高頻金融數(shù)據(jù)而言，不規(guī)則性是多方面的，，那就是隨著不同的時(shí)間和不同的測(cè)量尺度的變化。因此，找到一個(gè)有效的去噪算法是進(jìn)行高頻金融數(shù)據(jù)挖掘的關(guān)鍵。 以往的研究都是在某一尺度上對(duì)全體數(shù)據(jù)使用相同的濾波規(guī)則，這存在一個(gè)不足：若要保證提取趨勢(shì)不包含過多噪聲則無法包含某些突變現(xiàn)象，相反地，若想檢測(cè)出突變現(xiàn)象則要付出納入不必要的干擾噪聲的代價(jià)。因而本文認(rèn)為使用小波分析方法研究數(shù)據(jù)突變點(diǎn)并重構(gòu)的關(guān)鍵在于是否能準(zhǔn)確捕捉突變的同時(shí)還保證所提取趨勢(shì)的相對(duì)平滑，也就是說，保證準(zhǔn)確檢測(cè)出突變部分的同時(shí)不引入額外的噪聲。本文使用一種基于最大重疊離散小波變換（MODWT）的改進(jìn)型小波分析方法——局部線性尺度近似法（簡(jiǎn)稱LLSA），同時(shí)結(jié)合線性和非線性濾波器的特點(diǎn)，對(duì)高頻金融數(shù)據(jù)進(jìn)行突變點(diǎn)檢測(cè)并重構(gòu)，研究該方法檢測(cè)出的突變現(xiàn)象能否對(duì)應(yīng)重大特殊事件，以及該方法重構(gòu)的時(shí)間序列是否更貼合實(shí)際數(shù)據(jù)，能否提高預(yù)測(cè)精度。實(shí)證結(jié)果表明該方法能有效地檢測(cè)出突變點(diǎn)的發(fā)生，突變點(diǎn)對(duì)應(yīng)了樣本期內(nèi)多件重大經(jīng)濟(jì)事件，重構(gòu)后的時(shí)間序列更貼合實(shí)際數(shù)據(jù)，說明LLSA方法在去噪方面的表現(xiàn)優(yōu)于最大重疊離散小波變換方法，可有效提高預(yù)測(cè)精度。此外，本文還從多時(shí)間尺度的角度檢驗(yàn)了此方法的實(shí)用性及其經(jīng)濟(jì)意義。
[Abstract]:The change of stock price is caused by the arrival of information. How to grasp the arrival of new information accurately and promptly is of great significance to reveal the internal formation mechanism of stock price. In the analysis of the time series of stock price, there is a kind of change also caused by external events in addition to the long-term trend and the trend of seasonal variation. It also has a continuous impact on the trend of time series, namely, the point of mutation, including jumping point (jumps), steep slope (steepslopes) and so on. It often contains important information but is mistaken for noise and is ignored. The mutation points of the high frequency financial time series often contain important information. It is important for the investment decision to detect and analyze the occurrence of the mutation point accurately. Statistical data mining methods (or models) require a denoising algorithm to clean data so as to obtain reliable and significant results. Most data cleaning methods only focus on some known types of irregular behavior. For high frequency financial data, the irregularity is multifaceted, that is, with different time and different measurements. Therefore, finding an effective denoising algorithm is the key to high frequency financial data mining.
Previous studies have used the same filtering rules for all data at a certain scale. There is a shortage: to ensure that the extraction trend does not contain too much noise, some mutation phenomena can not be included. On the contrary, if we want to detect the mutation phenomenon, it is necessary to pay the cost of the unnecessary interference noise. The key of the wavelet analysis method to study the mutation and reconstruction of the data is whether it can capture the mutation accurately and ensure the relative smoothness of the extracted trend, that is to say, it ensures the exact detection of the abrupt part without introducing the extra noise. In this paper, an improved wavelet based on the maximum overlapping discrete wavelet transform (MODWT) is used in this paper. The analysis method, local linear scale approximation (LLSA), combined with the characteristics of linear and nonlinear filters, to detect and reconstruct the catastrophe point of high frequency financial data, and to study whether the mutation can correspond to the major special events and whether the time series rebuilt by the method can be more suitable for the actual data. The results show that the method can detect the occurrence of catastrophe point effectively. The mutation point corresponds to a number of major economic events in the sample period. The reconstructed time series is more close to the actual data, indicating that the performance of the LLSA method in denoising is better than the maximum overlapping and scatter wavelet transform method, which can effectively improve the prediction accuracy. In addition, the practicability and economic significance of this method are examined from the perspective of multiple time scales.
【學(xué)位授予單位】：天津大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：F832.51

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 黃香,葉維彰,欒貽會(huì),謝衷潔;跳躍點(diǎn)統(tǒng)計(jì)檢測(cè)的小波方法及其在金融匯率中的應(yīng)用[J];北京大學(xué)學(xué)報(bào)(自然科學(xué)版);1997年03期

2 熊正德;謝敏;;中國(guó)利率與股市間波動(dòng)溢出效應(yīng)的實(shí)證研究[J];財(cái)經(jīng)理論與實(shí)踐;2007年01期

3 翟博;;金融高頻時(shí)間序列的MODWT波動(dòng)分析[J];電腦知識(shí)與技術(shù);2011年10期

4 潘泉;孟晉麗;張磊;程詠梅;張洪才;;小波濾波方法及應(yīng)用[J];電子與信息學(xué)報(bào);2007年01期

5 隋學(xué)深;楊忠海;;股指時(shí)間序列突變點(diǎn)小波檢測(cè)研究(英文)[J];哈爾濱商業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2007年02期

6 王春峰;姚寧;房振明;;基于小波變換的多尺度跳躍識(shí)別與波動(dòng)性估計(jì)研究[J];管理科學(xué)學(xué)報(bào);2010年10期

7 李明揚(yáng);唐建偉;;我國(guó)利率變動(dòng)對(duì)股票價(jià)格影響效應(yīng)的實(shí)證分析[J];經(jīng)濟(jì)經(jīng)緯;2007年04期

8 陳守東,陳雷,劉艷武;中國(guó)滬深股市收益率及波動(dòng)性相關(guān)分析[J];金融研究;2003年07期

9 劉瀾飚,顧晶晶,李保偉;中國(guó)股票市場(chǎng)與經(jīng)濟(jì)波動(dòng)的基礎(chǔ)關(guān)系研究[J];南開經(jīng)濟(jì)研究;2001年03期

10 張維;劉博;熊熊;;日內(nèi)金融高頻數(shù)據(jù)的異常點(diǎn)檢測(cè)[J];系統(tǒng)工程理論與實(shí)踐;2009年05期

本文編號(hào)：2071334