本文關(guān)鍵詞：線性回歸模型參數(shù)有偏估計(jì)的研究　出處：《東北農(nóng)業(yè)大學(xué)》2014年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 有偏估計(jì) 均方誤差 相對(duì)效率 I-divergence估計(jì)

【摘要】：線性模型作為統(tǒng)計(jì)模型的一類,由于其應(yīng)用廣泛、形式簡單和易于處理,得到了廣泛的關(guān)注與研究。在線性模型中,由于參數(shù)估計(jì)的基礎(chǔ)性地位,作為線性模型首先要面臨的問題,決定了估計(jì)回歸參數(shù)具有重要意義。參數(shù)估計(jì)最基本、最常見的方法是最小二乘估計(jì)。近些年來當(dāng)數(shù)據(jù)存在復(fù)共線性時(shí)最小二乘估計(jì)均方誤差異常大導(dǎo)致估計(jì)值變壞,提出了有偏估計(jì)的概念。有偏估計(jì)在一定條件下減小了均方誤差,改進(jìn)了最小二乘估計(jì)的不足。參數(shù)有偏估計(jì)對(duì)于線性模型理論的發(fā)展和完善具有非常重要的意義。 本文結(jié)合國內(nèi)外參數(shù)有偏估計(jì)的相關(guān)研究理論、存在的問題,主要在相對(duì)效率意義下推導(dǎo)優(yōu)于最小二乘估計(jì)效率上界,針對(duì)已有的有偏估計(jì)只從局部改進(jìn)最小二乘估計(jì),提出了帶有約束的有偏估計(jì)類,主要工作如下： 首先,用有偏估計(jì)代替最小二乘估計(jì)后雖然減小了估計(jì)的均方誤差,但是估計(jì)的精度受到一些損失,相對(duì)效率能更好的度量有偏估計(jì)代替最小二乘估計(jì)損失的大小。因此本文重點(diǎn)在相對(duì)效率評(píng)價(jià)準(zhǔn)則意義下分別推導(dǎo)出廣義嶺估計(jì)和Liu估計(jì)優(yōu)于最小二乘估計(jì)的效率上界。為推導(dǎo)有偏估計(jì)優(yōu)于最小二乘估計(jì)的條件提供了新的思路。 其次,已有的有偏估計(jì)雖然改進(jìn)了最小二乘估計(jì),但得出的均方誤差是未知參數(shù)的函數(shù),有偏估計(jì)得到的結(jié)果是探索性的,而不是確證性的。當(dāng)變量存在約束情況下,已有的有偏估計(jì)并不適用,得出的估計(jì)值很不理想。針對(duì)上述這些問題本文從函數(shù)差異性角度出發(fā),采用新的度量函數(shù),在變量有約束時(shí)最終提出I-divergence估計(jì)。并在Kuhn-Tucker理論基礎(chǔ)上,設(shè)計(jì)迭代算法,得出迭代解,并證明了迭代過程的收斂性。如果所涉及的數(shù)據(jù)均為非負(fù)實(shí)值約束,并且數(shù)據(jù)呈正相關(guān)性,則I-divergence準(zhǔn)則是僅有的一致性選擇。進(jìn)一步用仿真數(shù)據(jù)驗(yàn)證新估計(jì)的優(yōu)劣,計(jì)算嶺估計(jì)、Liu估計(jì)的均方誤差和新估計(jì)比較充分證明了在變量非負(fù)約束情況下新估計(jì)比已有的有偏估計(jì)更好的減小了均方誤差。I-divergence估計(jì)理論的提出又進(jìn)一步豐富和發(fā)展了參數(shù)估計(jì)理論。 最后,結(jié)合股票定價(jià)模型實(shí)例給出了I-divergence估計(jì)在股票定價(jià)中的應(yīng)用,分析結(jié)果說明了該估計(jì)的可行性和優(yōu)越性。該估計(jì)能夠幫助投資人有效描述和跟蹤市場(chǎng)變化,將逐漸為證券界認(rèn)可和接受,其意義重大,必將為如何更有效地為企業(yè)價(jià)值評(píng)估提供一些有益的思考。在金融領(lǐng)域初次應(yīng)用該估計(jì)有力說明了統(tǒng)計(jì)理論知識(shí)的實(shí)用性和創(chuàng)新性。 帶約束參數(shù)有偏估計(jì)對(duì)于線性模型理論的發(fā)展和完善具有非常重要的意義。做為線性模型理論有益補(bǔ)充,將廣泛應(yīng)用于農(nóng)業(yè)、管理,經(jīng)濟(jì)、軍事,工程技術(shù)等領(lǐng)域,進(jìn)一步豐富了統(tǒng)計(jì)理論。對(duì)社會(huì)作出巨大的貢獻(xiàn)。
[Abstract]:As a kind of statistical model, linear model has been widely studied because of its wide application, simple form and easy to deal with. In the linear model, because of the basic position of parameter estimation. As the first problem of linear model, it is important to estimate regression parameters, which is the most basic. The most common method is the least square estimation. In recent years, when the data is complex collinearity, the mean square error of the least squares estimation is very large, which leads to the deterioration of the estimation value. The concept of biased estimation is proposed, which reduces the mean square error under certain conditions. The parameter biased estimation is very important for the development and improvement of the linear model theory. In this paper, combined with the domestic and foreign research theory of biased estimation of parameters, the existing problems, mainly in the sense of relative efficiency than the least square estimation of the efficiency of the upper bound. In this paper, a class of constrained biased estimators is proposed, which only improves the least square estimators from the local level. The main work is as follows: First, though the mean square error of estimation is reduced by using biased estimation instead of least square estimation, the accuracy of estimation is reduced. The relative efficiency can better measure the loss of biased estimation instead of least square estimation. Therefore, the generalized ridge estimate and Liu estimate are derived respectively in the sense of relative efficiency evaluation criterion, which is superior to the least square estimate. A new idea is provided for the derivation of the condition that the biased estimation is superior to the least square estimation. Secondly, although the existing biased estimation improves the least square estimation, the mean square error obtained is a function of unknown parameters, and the results obtained by the biased estimation are exploratory. When the variables are constrained, the existing biased estimation is not applicable, and the estimated value is not ideal. In view of these problems, this paper starts from the point of view of function difference. Using a new metric function, the I-divergence estimation is proposed when the variables are constrained. Based on the Kuhn-Tucker theory, an iterative algorithm is designed and the iterative solution is obtained. The convergence of the iterative process is proved if the data involved are non-negative real value constraints and the data are positively correlated. The I-divergence criterion is the only consistent choice. Further, the new estimation is verified by simulation data, and the ridge estimation is calculated. The mean square error of Liu estimator and the new estimator fully prove that the new estimator can reduce the mean square error better than the existing biased estimator in the case of variable nonnegative constraint. The theory of parameter estimation is further enriched and developed. Finally, the application of I-divergence estimation in stock pricing is given with an example of stock pricing model. The analysis results show the feasibility and superiority of this estimate, which can help investors to effectively describe and track market changes, and will gradually be recognized and accepted by the securities industry, which is of great significance. It will provide some useful thoughts on how to evaluate the enterprise value more effectively. The first application of this estimate in the field of finance can explain the practicability and innovation of statistical theory knowledge. The biased estimation of constrained parameters is of great significance to the development and improvement of linear model theory. As a useful supplement of linear model theory, it will be widely used in agriculture, management, economy and military. Engineering technology and other fields have further enriched statistical theory and made great contributions to society.
【學(xué)位授予單位】：東北農(nóng)業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2014
【分類號(hào)】：O212.1;F830.91

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 戴林送;;測(cè)量單位對(duì)線性模型參數(shù)估計(jì)相對(duì)效率的影響[J];安慶師范學(xué)院學(xué)報(bào)(自然科學(xué)版);2010年01期

2 羅冬梅;;一般線性模型回歸系數(shù)的可估計(jì)性[J];巢湖學(xué)院學(xué)報(bào);2009年03期

3 歸慶明,李國重;嶺—壓縮組合估計(jì)及其在測(cè)量平差中的應(yīng)用[J];大地測(cè)量與地球動(dòng)力學(xué);2002年01期

4 劉平,梁逸曾,俞汝勤;病態(tài)分析體系有偏估計(jì)的研究[J];分析化學(xué);1995年12期

5 李艷雙,曾珍香,張閩,于樹江;主成分分析法在多指標(biāo)綜合評(píng)價(jià)方法中的應(yīng)用[J];河北工業(yè)大學(xué)學(xué)報(bào);1999年01期

6 張?zhí)K林;;股票定價(jià)理論方法綜述[J];湖南財(cái)經(jīng)高等�？茖W(xué)校學(xué)報(bào);2010年02期

7 霍學(xué)文,趙軍;關(guān)于股票定價(jià)理論的發(fā)展脈絡(luò)[J];南開經(jīng)濟(jì)研究;1998年01期

8 劉潤幸,蕭燦培,宮齊,侯曉莉;利用SPSS進(jìn)行主成分回歸分析[J];數(shù)理醫(yī)藥學(xué)雜志;2001年02期

9 王正明;回歸系數(shù)的改進(jìn)主成分估計(jì)[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);1990年01期

10 李兵;朱寧;唐文芳;段復(fù)建;;改進(jìn)的最小二乘估計(jì)確定高精度參數(shù)模型[J];統(tǒng)計(jì)與決策;2007年23期

，

本文編號(hào)：1404022