本文選題：傾向性評分匹配 + 最鄰近匹配法�。� 參考：《第二軍醫(yī)大學(xué)》2014年博士論文

【摘要】：研究背景： 隨著信息技術(shù)的不斷發(fā)展，觀察性研究無論是在數(shù)量上還是在研究準(zhǔn)確性上都在不斷增加和提高。大樣本的觀察性研究在醫(yī)學(xué)研究當(dāng)中發(fā)揮著越來越重要的作用。但在觀察性研究中，由于研究對象所在的組別不是隨機分配的，而是自然存在的，因此具有某些特征的研究對象更傾向于進入處理組或?qū)φ战M，導(dǎo)致不同組間存在混雜偏倚。傾向性評分法(propensity score, PS)是解決觀察性研究中存在混雜偏倚的常用研究方法。該方法便于理解、研究步驟標(biāo)準(zhǔn)化程度高，近些年在非隨機化大樣本的觀察性研究當(dāng)中被廣泛應(yīng)用。傾向性評分法的應(yīng)用主要包括匹配法、分層法和回歸校正法等，以匹配法最具優(yōu)勢，應(yīng)用范圍也最為廣泛。傾向性評分匹配法主要包括最鄰近匹配法、卡鉗匹配法和馬氏距離匹配法等幾種方法。目前，對于傾向性評分匹配法的應(yīng)用上還有一些問題尚未得到解決。例如，對于在傾向性評分模型中應(yīng)放入何種類型的協(xié)變量，目前仍存在著爭議；何種匹配方法更具優(yōu)勢目前尚未得到定論；另外，目前傾向性評分匹配法主要用于分組因素為二分類的觀察性研究資料，很少有研究將其用于分組因素為多分類的觀察性研究資料中。 研究目的： 構(gòu)建分組因素為有序三分類的傾向性評分匹配方法。通過模擬研究篩選納入到傾向性評分模型中的協(xié)變量，比較多種匹配方法在分組因素為有序三分類情況下優(yōu)劣，通過調(diào)整參數(shù)確定不同數(shù)據(jù)特征下最具優(yōu)勢的匹配方式，同時在分組因素為有序三分類的情況下對不同傾向性評分應(yīng)用方法進行比較，最后將模擬研究中建立的最優(yōu)傾向性評分匹配方法應(yīng)用到實際數(shù)據(jù)分析中。 研究方法： 本研究采用蒙特卡洛法模擬數(shù)據(jù)集。分組因素模擬為有序三分類，并分別調(diào)整不同組間的樣本量比例為1:1:1、2:3:5、1:2:3和1:4:5。根據(jù)協(xié)變量與分組因素和結(jié)局的關(guān)系模擬不同類型的協(xié)變量，包括與分組因素和結(jié)局均相關(guān)聯(lián)的協(xié)變量、與分組因素相關(guān)聯(lián)的協(xié)變量、與結(jié)局相關(guān)聯(lián)的協(xié)變量和與分組因素和結(jié)局均不相關(guān)聯(lián)的協(xié)變量。通過在傾向性評分模型中納入不同類型的協(xié)變量，確定在分組因素為有序三分類情況下傾向性評分模型中應(yīng)納入的協(xié)變量類型。根據(jù)分組因素為二分類的傾向性評分匹配方法的基本思想，構(gòu)建分組因素為有序三分類的傾向性評分匹配法，包括最鄰近匹配法、卡鉗匹配法和馬氏距離匹配法，并通過SAS宏程序?qū)崿F(xiàn)各種匹配方法。在不同匹配方法中設(shè)定不同匹配參數(shù)，如匹配比例、卡鉗值等，通過比較不同匹配方法和設(shè)定不同匹配參數(shù)確定不同數(shù)據(jù)特征下最具優(yōu)勢的匹配方式。另外，還將利用模擬數(shù)據(jù)比較不同傾向性評分應(yīng)用方法，包括匹配法、分層法、回歸校正法和匹配后回歸校正法。 采用有序logistic回歸分析法計算分組因素為有序三分類的研究對象的傾向性評分值。在傾向性評分匹配前后需要對放入傾向性評分模型中的協(xié)變量進行均衡性檢驗。本研究采用標(biāo)準(zhǔn)化差異法(standardized differences, SD)來評價不同組間協(xié)變量的均衡性。通過預(yù)實驗得到，當(dāng)分組因素為有序三分類時，，不同組間標(biāo)準(zhǔn)化差異的絕對值的最大值大于0.1時，三組間的協(xié)變量尚未達到均衡。當(dāng)完成傾向性評分匹配后，還要對模型的偏性和精度進行評價。本研究采用相對偏倚(relative bias, RB)來評價模型的偏性，RB的絕對值越小，表明模型的偏性就越��；采用平均誤差均方(mean squarederror, MSE)來評價模型的精度，MSE越小，表明模型的精度越高。 最后，將模擬研究建立的分組因素為有序三分類的傾向性評分匹配方法應(yīng)用到實例分析中。實例分析部分的數(shù)據(jù)來源于第二軍醫(yī)大學(xué)承擔(dān)的“中國大陸胃腸道疾病流行病學(xué)調(diào)查”的數(shù)據(jù)。本研究利用問卷中調(diào)查對象的一般信息、體格檢查問卷和SF-36健康調(diào)查問卷中的數(shù)據(jù)，評價腹部肥胖與健康相關(guān)的生活質(zhì)量(health-related quality oflife, HRQOL)之間的關(guān)系。人口學(xué)信息包括性別、年齡、身高、體重、教育水平、職業(yè)和慢性病發(fā)病情況等。腹部特征定義為“正常腰圍”、“輕度腹部肥胖”和“重度腹部肥胖”三類。健康相關(guān)的生活質(zhì)量采用中文版的健康測量簡表(SF-36)進行評價。以腹部特征為分組因素，健康相關(guān)的生活質(zhì)量的各個維度得分為結(jié)局，篩選人口學(xué)信息中的變量為協(xié)變量，構(gòu)建傾向性評分模型。利用模擬研究建立的傾向性評分匹配方法控制混雜因素對結(jié)局的影響，從而評價腹部肥胖對健康相關(guān)的生活質(zhì)量的影響。 研究結(jié)果： （1）協(xié)變量篩選：在分組因素為有序三分類的情況下，當(dāng)傾向性評分模型中納入與結(jié)局相關(guān)聯(lián)的協(xié)變量時，可獲得相對較高的匹配比例，并且估計的處理效應(yīng)的偏性相對最小，精度最高。當(dāng)逐步從模型中剔除一個協(xié)變量后，如果該協(xié)變量與分組因素和結(jié)局變量均相關(guān)聯(lián)，會極大增加處理效應(yīng)估計值的偏性，降低其精度，說明與分組因素和結(jié)局變量均相關(guān)聯(lián)的協(xié)變量需全部納入，同時再納入與結(jié)局相關(guān)聯(lián)但與分組因素不相關(guān)聯(lián)的協(xié)變量可進一步減小處理效應(yīng)估計的偏性，增大處理效應(yīng)估計的精度。因此，在分組因素為有序三分類的情況下，傾向性評分模型中需納入與結(jié)局相關(guān)聯(lián)的協(xié)變量，無論其是否與分組因素相關(guān)聯(lián)。 （2）匹配方法構(gòu)建和比較：本研究構(gòu)建了分組因素為有序三分類的傾向性評分匹配方法，包括最鄰近匹配法、卡鉗匹配法和馬氏距離法，并對不同匹配方法進行比較。在不同組間樣本量比例下，卡鉗匹配法的效果均達到最好。當(dāng)組間樣本量比例為1:1:1時，采用卡鉗匹配法（卡鉗值設(shè)為0.005）進行1:1:1匹配效果最好；當(dāng)組間樣本量比例為2:3:5時，采用卡鉗匹配法（卡鉗值設(shè)為0.01）進行1:1:1匹配效果最好；當(dāng)組間樣本量比例為1:2:3時，采用卡鉗匹配法（卡鉗值設(shè)為0.01）進行1:1:1匹配效果最好；組間樣本量比例為1:4:5時，采用卡鉗匹配法（卡鉗值設(shè)為0.01）進行1:2:2匹配效果最好。 （3）不同傾向性評分應(yīng)用方法比較：不同傾向性評分方法均能極大地降低處理效應(yīng)估計值的偏性，提高處理效應(yīng)估計值的精度。無論組間樣本量比例如何，匹配法和匹配后回歸校正法的效果均優(yōu)于其他方法。當(dāng)組間樣本量比例為1:1:1時，回歸校正法優(yōu)于分層法；當(dāng)組間樣本量的比例逐漸拉大時，分層法優(yōu)于回歸校正法。 （4）實例研究：經(jīng)傾向性評分匹配后，所有與結(jié)局相關(guān)聯(lián)的協(xié)變量均在不同腹部特征組間達到了均衡，因此可以直接評價腹部肥胖對健康相關(guān)的生活質(zhì)量的作用。結(jié)果表明，在體能維度上，重度腹部肥胖組的人群得分均顯著低與正常腰圍組，而輕度腹部肥胖組的人群得分顯著高于正常腰圍組。而在社會功能維度上，只有重度腹部肥胖組的人群在得分上顯著低于正常腰圍組人群，輕度腹部肥胖組人群與正常腰圍組人群在得分上無統(tǒng)計學(xué)差別。 研究結(jié)論： 在分組因素為有序三分類的情況下，傾向性評分模型中應(yīng)納入與結(jié)局相關(guān)聯(lián)的協(xié)變量。在進行傾向性評分匹配時，采用卡鉗匹配法進行匹配效果最好，卡鉗值和匹配比例根據(jù)組間樣本量比例進行調(diào)整。在不同傾向性評分應(yīng)用方法中，以匹配法和匹配后回歸校正法的效果最好。與傳統(tǒng)多因素統(tǒng)計方法相比，本研究建立的分組因素為有序三分類的傾向性評分匹配方法可通過控制混雜因素定量評價不同組間連續(xù)型結(jié)局變量的差異。
[Abstract]:Background of Study :

With the development of information technology , observational studies have been increasing and improving both in quantity and in research accuracy . The observational study of large samples plays a more and more important role in medical research .
What kind of matching method is more advantageous and has not yet been finalized ;
In addition , the current tendency score matching method is mainly used for observational study data of grouping factors into two categories , and few researches have been used in observational study data for grouping factors into multi - classification .

Purpose of study :

In this paper , we construct the matching method of propensity score in order three classification , and compare multiple matching methods under the condition of grouping factor into ordered three classification , and compare the best advantage in different data characteristics by adjusting the parameters , and then compare the application methods of different inclination scores under the condition of grouping factors as ordered three categories , and finally apply the optimal propensity score matching method established in the simulation study to the actual data analysis .

Study method :

In this study , the data set is simulated by Monte Carlo method . The grouping factors are modeled as ordered three categories , and the proportion of sample size between different groups is 1 : 1 : 1 , 2 : 3 : 5 , 1 : 2 : 3 and 1 : 4 : 5 .

By means of sequential logistic regression analysis , we calculated the tendency score value of the grouped factors into the ordered three categories . By pre - experiment , the equilibrium between different groups was evaluated by standardized differences ( SD ) . When grouping factors were ordered three categories , the covariables between the three groups had not yet reached equilibrium . When the tendency score was completed , the bias and accuracy of the model were evaluated . The smaller the absolute value of RB , the smaller the bias of the model was shown .
The smaller the mean squarederror ( MSE ) is used to evaluate the accuracy of the model , the smaller the MSE , the higher the accuracy of the model .

Finally , the relationship between obesity and health - related quality of life ( HRQOL ) was evaluated by using the data from the general information , physical examination questionnaire and SF - 36 health questionnaire . The data from the questionnaire included sex , age , height , weight , education level , occupational and chronic diseases . The health - related quality of life was defined as " normal waist circumference " , " mild abdominal obesity " and " severe abdominal obesity " .

Results of the study :

( 1 ) Covariate screening : In the case of grouping factors into an ordered three classification , a relatively high matching ratio can be obtained when the covariables associated with the outcome are included in the propensity score model , and the accuracy is the highest . If the covariables are associated with both the grouping factor and the outcome variable , the accuracy of the processing effect estimate can be greatly increased , and the covariables associated with the outcome variables and the outcome variables can be further reduced , so that the accuracy of the processing effect estimation is increased . Therefore , in the case of the grouping factors being ordered three categories , the covariables associated with the outcomes need to be included in the propensity score model regardless of whether or not it is associated with the grouping factor .

( 2 ) Construction and comparison of matching method : This study constructed the matching method of propensity score based on grouping factors as ordered three classification , including the most adjacent matching method , the caliper matching method and the Markov distance method . The effect of the caliper matching method is the best when the sample size ratio of the groups is 1 : 1 : 1 . When the sample size ratio is 1 : 1 : 1 , the matching effect of the caliper matching method is 1 : 1 : 1 .
When the sample size ratio of the group is 2 : 3 : 5 , the matching effect of 1 : 1 : 1 is best done by using the caliper matching method ( the caliper value is set to 0.01 ) .
When the sample size ratio of the group is 1 : 2 : 3 , the matching effect of 1 : 1 : 1 is best done by using the caliper matching method ( the caliper value is set to 0.01 ) .
When the sample size ratio between groups is 1 : 4 : 5 , the matching effect of 1 : 2 : 2 is the best by adopting the caliper matching method ( the caliper value is set to 0.01 ) .

( 3 ) Compared with other methods , the method of different propensity score can greatly reduce the deviation of treatment effect estimation value and improve the accuracy of treatment effect estimation value . The regression correction method is superior to other methods , regardless of the proportion of sample size , the matching method and the post - matching regression correction method .
When the proportion of sample size in the group gradually increases , the stratification method is superior to the regression correction method .

( 4 ) Case study : After the matching of the propensity score , all the covariables associated with the outcome were balanced among the different abdominal characteristic groups , so it was possible to directly evaluate the effect of abdominal obesity on the health - related quality of life . The results showed that the scores of the patients with severe abdominal obesity were significantly lower than those in the normal waist group .

Conclusions of the study :

In the case of grouping factors as ordered three classification , the covariables associated with the outcomes should be included in the propensity score model . The best results are compared with the traditional multi - factor statistical methods . The grouping factors established in this study are the best results compared with the traditional multi - factor statistical methods .

【學(xué)位授予單位】：第二軍醫(yī)大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2014
【分類號】：R181.2

【引證文獻】

相關(guān)期刊論文 前1條

1 鄧峰;屈蒙;楊培榮;王紅林;楊彪;高建民;;寶雞市農(nóng)村居民高血壓糖尿病社區(qū)干預(yù)效果分析[J];中國公共衛(wèi)生管理;2016年05期

本文編號：1862851