中华预防医学杂志
中華預防醫學雜誌
중화예방의학잡지
CHINESE JOURNAL OF
2015年
1期
50-55
,共6页
李镒冲%于石成%赵寅君%姜勇%王丽敏%张梅%蒋炜%包鹤龄%周脉耕
李鎰遲%于石成%趙寅君%薑勇%王麗敏%張梅%蔣煒%包鶴齡%週脈耕
리일충%우석성%조인군%강용%왕려민%장매%장위%포학령%주맥경
抽样研究%模型,统计学%计算机模拟%基于设计%基于模型
抽樣研究%模型,統計學%計算機模擬%基于設計%基于模型
추양연구%모형,통계학%계산궤모의%기우설계%기우모형
Sampling studies%Models,statistical%Computer simulation%Design-based%Model-based
目的 比较基于设计和基于模型方法在复杂样本统计描述中的表现.方法 以2010年中国慢性病及其危险因素监测的收缩压(SBP)和血压升高率为材料,利用多阶段随机抽样模拟抽取1 000次(样本量均为2 000名),同时赋予样本随年龄增加而变大的应答率,使样本年龄结构偏离目标人群.以均方误差(MSE)和95％可信区间(CI)覆盖参数的概率为评价标准,比较基于设计方法,基于模型的常规方法和多水平模型对均数和率进行统计描述时的表现.结果 常规方法、基于设计方法和多水平模型在估计SBP均数时,MSE分别为6.41、1.38和5.86,基于设计方法表现最好;3种方法估计的95％ CI覆盖总体参数的概率分别为24.7％、97.5％和84.3％,常规方法和多水平模型均可导致统计推断Ⅰ类错误概率增加.估计血压升高率时,基于设计方法的MSE为4.80,表现优于常规方法(20.9)和多水平模型(17.2);而常规方法95％ CI包含总体参数的概率仅为29.4％,多水平模型为86.4％,均低于基于设计的方法(97.3％).结论 对样本结构存在系统偏差的复杂抽样数据进行统计描述时,基于设计方法在估计的无偏性和统计推断的有效性方面均优于常规方法和多水平模型,应作为首选方法.
目的 比較基于設計和基于模型方法在複雜樣本統計描述中的錶現.方法 以2010年中國慢性病及其危險因素鑑測的收縮壓(SBP)和血壓升高率為材料,利用多階段隨機抽樣模擬抽取1 000次(樣本量均為2 000名),同時賦予樣本隨年齡增加而變大的應答率,使樣本年齡結構偏離目標人群.以均方誤差(MSE)和95％可信區間(CI)覆蓋參數的概率為評價標準,比較基于設計方法,基于模型的常規方法和多水平模型對均數和率進行統計描述時的錶現.結果 常規方法、基于設計方法和多水平模型在估計SBP均數時,MSE分彆為6.41、1.38和5.86,基于設計方法錶現最好;3種方法估計的95％ CI覆蓋總體參數的概率分彆為24.7％、97.5％和84.3％,常規方法和多水平模型均可導緻統計推斷Ⅰ類錯誤概率增加.估計血壓升高率時,基于設計方法的MSE為4.80,錶現優于常規方法(20.9)和多水平模型(17.2);而常規方法95％ CI包含總體參數的概率僅為29.4％,多水平模型為86.4％,均低于基于設計的方法(97.3％).結論 對樣本結構存在繫統偏差的複雜抽樣數據進行統計描述時,基于設計方法在估計的無偏性和統計推斷的有效性方麵均優于常規方法和多水平模型,應作為首選方法.
목적 비교기우설계화기우모형방법재복잡양본통계묘술중적표현.방법 이2010년중국만성병급기위험인소감측적수축압(SBP)화혈압승고솔위재료,이용다계단수궤추양모의추취1 000차(양본량균위2 000명),동시부여양본수년령증가이변대적응답솔,사양본년령결구편리목표인군.이균방오차(MSE)화95％가신구간(CI)복개삼수적개솔위평개표준,비교기우설계방법,기우모형적상규방법화다수평모형대균수화솔진행통계묘술시적표현.결과 상규방법、기우설계방법화다수평모형재고계SBP균수시,MSE분별위6.41、1.38화5.86,기우설계방법표현최호;3충방법고계적95％ CI복개총체삼수적개솔분별위24.7％、97.5％화84.3％,상규방법화다수평모형균가도치통계추단Ⅰ류착오개솔증가.고계혈압승고솔시,기우설계방법적MSE위4.80,표현우우상규방법(20.9)화다수평모형(17.2);이상규방법95％ CI포함총체삼수적개솔부위29.4％,다수평모형위86.4％,균저우기우설계적방법(97.3％).결론 대양본결구존재계통편차적복잡추양수거진행통계묘술시,기우설계방법재고계적무편성화통계추단적유효성방면균우우상규방법화다수평모형,응작위수선방법.
Objective To compare design-based and model-based methods in descriptive analysis of complex sample.Methods A total of 1 000 samples were selected and a multistage random sampling design was used in the analysis of the 2010 China chronic disease and risk factors surveillance.For each simulated sample,cases with probability proportional age were randomly deleted so that sample age structure was deviated systematically from that of the target population.Mean systolic blood pressure(SBP) and prevalence of raised blood pressure,as well as their 95 ％ confidence intervals (95 ％ CI) were determined using designbased and model-based methods(routine method and multi-level model).For estimators generated from those 3 methods,mean squared error(MSE) was computed to evaluate their validity.To compare performance of statistical inference of these methods,the probability of 95％ CI covering the true parameter(mean SBP and raised blood pressure prevalence of the population) was used.Results MSE of mean estimator for routine method,design-based analysis and multilevel model was 6.41,1.38,and 5.86,respectively; and the probability of 95％ CI covering the true parameter was 24.7％,97.5％ and 84.3％,respectively.The routine method and multi-level model probably led to an increased probability of type Ⅰ error in statistical inference.MSE of prevalence estimator was 4.80 for design-based method,which was far lower than those for routine method (20.9) and multilevel model (17.2).Probability of 95％ CI covering the true prevalence for routine method was only 29.4％,and 86.4％ for multilevel model,both of which were lower than that for design-based method(97.3％).Conclusion Compared to routine method and multi-level model,designbased method had the best performance both in point estimation and confidence interval construction.Designbased method should be the first choice when doing statistical description of complex samples with a systematically biased sample structure.
