發(fā)布時(shí)間：2018-03-09 06:11

  本文選題：潛變量　切入點(diǎn)：因果效應(yīng)　出處：《長(zhǎng)春工業(yè)大學(xué)》2017年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：因果關(guān)系是復(fù)雜事物間普遍存在的一種基本關(guān)系,不僅在現(xiàn)實(shí)生活中存在著非常多的因果關(guān)系,在統(tǒng)計(jì)學(xué)、醫(yī)學(xué)、經(jīng)濟(jì)學(xué)等眾多領(lǐng)域中也得到了科研工作者們非常廣泛的關(guān)注,有著重要的應(yīng)用。在研究因果關(guān)系的過(guò)程中,潛變量的引入是非常重要的,它不僅更清楚并深刻地刻畫(huà)了變量間的關(guān)系,同時(shí)為簡(jiǎn)化復(fù)雜問(wèn)題做出了很大的貢獻(xiàn)。對(duì)于含潛變量模型下因果效應(yīng)的研究,本文主要從三個(gè)方面來(lái)進(jìn)行。其一是虛擬事實(shí)模型,二是因果網(wǎng)模型,三就是基于因子分析進(jìn)行因果關(guān)系的探索。第一部分是在虛擬事實(shí)模型框架下進(jìn)行研究。我們?cè)赩anderWeele(2008)和Chiba(2009)對(duì)平均因果效應(yīng)研究的基礎(chǔ)上進(jìn)行比較,通過(guò)實(shí)際例子和模擬研究,我們可以得出這種結(jié)論,在大多數(shù)情況下Chiba與VanderWeele的邊界相比,前者的方法是更好的,因?yàn)樗姆椒ǹ梢缘玫揭粋�(gè)較小的邊界,這個(gè)小的邊界可以使我們的研究更加精確,同時(shí)在實(shí)際應(yīng)用中也可以得到更精確的結(jié)果。虛擬事實(shí)模型是通過(guò)引進(jìn)虛擬事實(shí)變量,來(lái)評(píng)價(jià)一個(gè)變量對(duì)另一個(gè)變量的因果作用,而因果網(wǎng)模型是用網(wǎng)絡(luò)結(jié)構(gòu)表示變量間的因果關(guān)系,可以借助圖模型的相關(guān)方法在潛變量存在的情況下判斷變量間的因果關(guān)系(即網(wǎng)絡(luò)中的邊)是否存在。本篇文章通過(guò)NSCOT數(shù)據(jù)探索送往醫(yī)院時(shí)間、身體狀況、生存狀況等變量之間的因果關(guān)系。我們可以得出送往醫(yī)院的時(shí)間與生存狀況是有因果關(guān)系的,而一個(gè)人的身體素質(zhì)和受傷的嚴(yán)重情況會(huì)對(duì)病人送往醫(yī)院的時(shí)間產(chǎn)生影響,從而對(duì)生存狀況產(chǎn)生影響。第三個(gè)研究的問(wèn)題是因子分析,因子分析的主要思想是用少數(shù)幾個(gè)因子來(lái)描述多個(gè)指標(biāo)之間的聯(lián)系,以較少的幾個(gè)因子反應(yīng)原數(shù)據(jù)中的絕大部分信息的統(tǒng)計(jì)學(xué)方法,而這幾個(gè)被綜合的因子其實(shí)就是文章中討論的潛變量。在本文中,利用各省市居民生活質(zhì)量數(shù)據(jù)進(jìn)行因子分析,經(jīng)分析我們可以得到三個(gè)公共因子,其分別為總體因子、個(gè)體因子和消費(fèi)品因子。這三個(gè)因子就是綜合得來(lái)、無(wú)法直接觀(guān)測(cè)到的潛變量。
[Abstract]:Causality is a kind of basic relationship that exists widely among complicated things. It not only has many causality in real life, but also has been widely concerned by researchers in many fields, such as statistics, medicine, economics and so on. In the process of studying causality, the introduction of latent variables is very important. It not only clearly and profoundly depicts the relationship between variables, At the same time, it has made a great contribution to simplify the complex problem. For the study of causality under the model with latent variables, this paper mainly deals with three aspects: one is the virtual fact model, the other is the causality net model. The first part is to carry on the research under the framework of the virtual fact model. We compare the average causality based on Vander Weele 2008) and Chibaan 2009), through the actual examples and simulation research. We can conclude that in most cases Chiba's method is better than VanderWeele's, because his method can get a smaller boundary, which makes our research more accurate. At the same time, more accurate results can be obtained in practical applications. Virtual fact models are used to evaluate the causal effect of one variable on another by introducing virtual fact variables. The causality net model uses the network structure to express the causality between variables. With the help of the relevant method of graph model, we can judge whether the causality between variables exists (that is, the edge of the network) in the presence of latent variables. This article explores the time to hospital, physical condition through NSCOT data. We can conclude that there is a causal relationship between the time taken to the hospital and the living condition, and that the physical quality of a person and the severity of the injury will have an impact on the time the patient is sent to the hospital. The third problem is factor analysis. The main idea of factor analysis is to use a few factors to describe the relationship between multiple indicators. A few factors reflect the vast majority of the information in the original data, and these combined factors are actually the underlying variables discussed in the paper. In this paper, factor analysis is carried out using the quality of life data of the residents of various provinces and cities. Through analysis, we can get three common factors, which are the total factor, the individual factor and the consumer factor, which are the latent variables which can not be observed directly.
【學(xué)位授予單位】：長(zhǎng)春工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：C81

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李春平;葛瑩玉;;基于潛變量的人口素質(zhì)測(cè)度方法研究[J];統(tǒng)計(jì)與管理;2016年07期

2 丁紅艷;陳建;張敏;;基于因子分析和聚類(lèi)分析的新疆各地區(qū)經(jīng)濟(jì)發(fā)展水平綜合評(píng)價(jià)[J];數(shù)學(xué)的實(shí)踐與認(rèn)識(shí);2016年04期

3 許穎玉;張忠占;;依從者平均因果效應(yīng)的統(tǒng)計(jì)推斷[J];數(shù)理統(tǒng)計(jì)與管理;2015年03期

4 韓微;翟盤(pán)茂;;三種聚類(lèi)分析方法在中國(guó)溫度區(qū)劃分中的應(yīng)用研究[J];氣候與環(huán)境研究;2015年01期

5 劉建偉;崔立鵬;羅雄麟;;概率圖模型的稀疏化學(xué)習(xí)[J];計(jì)算機(jī)學(xué)報(bào);2016年08期

6 蔣思瑤;;R軟件在Bayes統(tǒng)計(jì)中的應(yīng)用[J];商業(yè)經(jīng)濟(jì);2014年13期

7 王德青;朱建平;謝邦昌;;主成分聚類(lèi)分析有效性的思考[J];統(tǒng)計(jì)研究;2012年11期

8 林海明;;因子分析應(yīng)用中一些常見(jiàn)問(wèn)題的解析[J];統(tǒng)計(jì)與決策;2012年15期

9 王駿;王士同;鄧趙紅;;聚類(lèi)分析研究中的若干問(wèn)題[J];控制與決策;2012年03期

10 馬京然;曾躍進(jìn);;數(shù)據(jù)標(biāo)準(zhǔn)化與科學(xué)管理的方法[J];中國(guó)教育技術(shù)裝備;2008年24期

相關(guān)碩士學(xué)位論文 前2條

1 和超;基于結(jié)構(gòu)EM的隱變量模型學(xué)習(xí)方法[D];云南大學(xué);2015年

2 張娟;潛變量統(tǒng)計(jì)建模方法的發(fā)展演化過(guò)程及其演化規(guī)律研究[D];山東經(jīng)濟(jì)學(xué)院;2010年

，

本文編號(hào)：1587307