用户名: 密码: 验证码:
山西省HIV/AIDS结核感染监测资料预测方法研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
目的
     为有效利用中国疾病预防控制中心(CDC)结核病管理信息系统、山西省结核病网络监测数据库和运城地区5个项目防治县已收集的TB/HIV双重感染者监测随访数据(第五轮中国全球基金TB/HIV双重感染项目)的信息,设计、修订并完善能反映山西省结核感染、结核患病和TB/HIV双重感染流行病学监测信息库;对运城地区5个项目防治县HIV/AIDS结核感染数据进行稀有事件logistic回归分析及贝叶斯估计,以进一步揭示运城地区HIV/AIDS结核感染的现状及其影响因素,并与常规分析方法进行对比研究,为制定有针对性的双向预防和防治措施提供参考;同时对传染性最强的涂阳结核病发生、流行及其变化趋势进行预测,为政府及相关部门及时采取有效措施提供依据。
     方法
     本课题结合山西省结核病发生特点,在利用中国疾病预防控制中心结核病信息管理系统监测数据库基础上,进一步完善、修订和编制山西省TB/HIV双重感染流行病学监测随访记录表,对山西省运城市第五轮中国全球基金结核病项目芮城、夏县、新绛、绛县、稷山5个项目防治县TB/HIV双重感染者进行监测,为山西省TB/ HIV双重感染的严重程度及影响因素评价提供基础数据。根据TB/ HIV双重感染监测数据特点,采用稀有事件logistic回归、随机效应logistic回归、贝叶斯估计等方法对HIV/AIDS结核感染概率进行估计,并对监测数据评价方法进行对比研究,全部过程采用SAS9.1.3、Stata10.0软件编程实现。利用中国疾病预防控制中心结核病信息管理系统数据,建立山西省2005年-2008年涂阳结核病例时间序列分析ARMA模型和ARIMA模型,Microsoft SQL Server Analysis Services数据挖掘模型-(Microsoft时序算法),对山西省结核病发病趋势进行预测,并对两种模型预测结果进行对比分析。
     结果
     1、目前国家结核病信息管理系统运转良好,信息搜集全面。结核病监测信息是进行结核病预防与控制及干预评价的基础数据,其数据质量直接影响评价效果。国家结核病监测信息系统运转良好,但结合山西工作特点,根据省结核病防治办公室工作需求,欲将结核感染,结核患病以及HIV感染等防治信息融合为统一的互联信息。本课题在现有的国家结核病管理信息系统的基础上,完善TB/HIV双重感染防治的内容,在了解山西省多年的疫情监测资料基础上,增加了TB/HIV双重感染随访及死亡登记相关调查内容,进一步完善与修订了基线调查条目,增加了结核病人的收入水平、营养状况、治疗过程记录及其副反应等,并能在监测系统中方便地提供信息整合后的TB/HIV双重感染统计分析数据库,为结核病与艾滋病防治监测数据管理与分析提供了一种模式。
     2、探讨HIV/AIDS结核感染的影响因素,采用经典logistic回归分析,往往会由于反应变量的两类取值频率相差悬殊(HIV/AIDS结核感染表现为稀有医学事件),而引致不切实际的参数估计,低估稀有事件的发生概率。本课题探讨了稀有事件logistic回归校正参数和概率估计值的方法。通过原理阐述、软件编程,对监测数据分别拟合普通logistic回归、logistic回归先验校正、logistic回归MCN先验校正、logistic回归加权校正和logistic回归MCN加权校正模型,并根据Vuong检验原理编程实现非嵌套模型间的对比分析,结果显示logistic回归MCN加权校正拟合结核双重感染监测数据较好。针对稀有事件发生概率估计问题,采用最大似然估计、加权最大似然估计、近似无偏估计、近似Bayes估计方法,结果显示近似Bayes估计得到的结果最优。根据近似Bayes估计结果可知,山西省的HIV/AIDS结核感染概率约为5.0%。
     3、由于五个项目监测县HIV/AIDS的结核感染率在地区之间存在组群效应,本课题采用广义线性混合效应模型进行分析,建立HIV/AIDS结核感染的随机效应logistic回归模型来解决同一地区结核感染非独立的问题。对山西省五个项目监测县HIV/AIDS结核感染实例分别采用随机效应logistic回归、稀有事件的随机效应logistic回归和稀有事件的随机效应logistic回归MCN加权校正模型进行分析,由模型拟合评价指标结果可见,稀有事件随机效应logistic回归MCN加权校正模型对数据拟合较好。CD4细胞计数水平可作为HIV/AIDS结核发病概率估计的一个预警因素, HIV/AIDSCD4计数对数值每增加一个单位,HIV/AIDS结核感染的危险性降低74.9%。
     4、广义线性混合效应模型的参数估计常需要对联合似然函数数值积分或者对模型采用某种近似,限制伪似然估计方法就是对广义线性混合效应模型的一阶泰勒近似。本课题将贝叶斯估计方法引入广义线性混合效应模型的参数估计,结果显示在选取了无信息先验后,贝叶斯估计所得的后验均数与限制伪似然估计结果比较接近。
     5、山西省2005年到2008年涂阳结核病例时间序列预测模型ARIMA(1,1,0)(1,1,0)12分析结果表明,2009年的新发涂阳病例数较往年会有大幅度降低,2009年3月到8月的涂阳结核病发病例数可能较高,4月份的病例数预计最多,提示结核病防治还应加大力度,重视及时防治。所建模型显示预测值和实际值平均绝对误差为136.64,平均相对误差为8.10%,拟合效果较好。Microsoft时序算法预测结果与ARIMA(1,1,0)(1,1,0)12模型预测趋势一致,各级防疫部门应根据预警信息,进一步加强2009年第二、三季度结核防治工作。
     6、与ARIMA模型的拟合结果相比,2007年1月至2008年8月,Microsoft时序算法的预测平均绝对误差为116.7,平均相对误差为6.60%,而ARIMA模型的预测平均绝对误差为104.4,平均相对误差为5.90%。Microsoft时序算法的预测结果与ARIMA(1,1,0)(1,1,0)12模型基本一致,预测相对误差均较小,但Microsoft时序算法在2008年9月-12月的预测误差明显大于ARIMA(1,1,0)(1,1,0)12模型。可见在山西省涂阳结核病例预测中以ARIMA模型更好,它不仅可以通过差分运算提取序列中蕴含的季节效应和长期趋势效应等强劲的确定性信息,而且尚可利用随机信息,故其预测精度较高。
     结论
     1、经过修订完善的结核感染监测量表,增加了TB/HIV双重感染防治的内容,可以为结核感染与疾病的预防与治疗效果的评价提供更丰富的第一手材料,它是有效控制TB/HIV双重感染,降低HIV感染者中结核病的发病和死亡,减少结核病人中HIV的感染机会,共享结核病与艾滋病防治信息,进行资料联合评价的重要条件。
     2、对稀有事件数据的分析,无论是模型的参数估计,还是预测预报,稀有事件logistic回归确实更优于普通logistic回归。因此,针对生物医学现象中发病、患病水平较低的很多疾病研究,稀有事件的logistic回归是一种值得推广的应用统计模型。然而实际应用中是否有必要对稀有事件的logistic回归进行参数和预测概率校正,也即是稀有事件logistic回归相对普通logistic回归的模型选择问题。由于两者之间不是嵌套的关系,而是竞争性的非嵌套非线性模型,所以本文首先提出将Vuong检验作为评价模型好坏的检验方法,其原理易于理解,可在SAS软件中编程实现,结果评价合理,能解决实际应用问题,是值得推崇的一种方法。
     3、在贝叶斯假定下,对参数指定无信息先验,应用MCMC技术进行广义线性混合效应模型参数估计,得到了和限制伪似然估计一致的结果,为广义线性混合效应模型提供了另一种有效的分析途径。随机效应logistic回归的贝叶斯估计相对限制伪似然估计,结果更精确,解释更合理,尤其是在能执行贝叶斯分析的统计软件的支持下,贝叶斯估计更具优势。
     4、时间序列模型(ARMA模型)可方便地处理平稳序列问题,而实际应用中许多非平稳序列经过差分运算后会表现出平稳序列的性质,ARIMA模型就是差分运算与ARMA模型的结合,对序列数据的拟合效果较好,是传染病尤其是结核病发病趋势预测中实用性较强的数学模型与预测工具。依据模型分析应用条件,选择恰当的分析模型是ARIMA模型保证预测效果的关键。
     5、本研究首次将Microsoft时序算法引入医学时序资料的统计分析中,构建了山西省2005年1月至2008年12月CDC结核病管理信息涂阳结核病例数训练模型,作为一种新的预测算法,它将自回归和决策树技术结合在一起,丰富了医学时序资料的预测方法。虽然本例中Microsoft时序算法的预测误差略大于ARIMA模型,预测效果的稳健性尚有待继续探讨,但其原理简单易于理解,软件操作方便,便于基层监测数据快速分析,亦不失是一种值得推广学习的新方法。
Objectives
     Cooperated with the Center of Disease Control and Prevention of Shanxi Province, tuberculosis data came from the Chinese Center of Disease Control and Prevention(CDC) network monitor system , and TB / HIV co-infection data came from the investigation of 5 counties in Yuncheng city based on the fifth tuberculosis global fund project. Aimed at establishing the TB / HIV co-infection monitoring evaluation system, To provide scientific basis for trend prediction and control measures of the TB / HIV co-infection. To find out the severity of the tuberculosis infection and its influencing factors in HIV/AIDS patients using statistical analysis methods.
     Methods
     Survey and monitor were carried on TB/HIV co-infected patients from the 5 counties of Yuncheng city, including Ruicheng, Xiaxian, Xinjiang, Jiangxian and Jishan. The follow-up table coincident with the actual situation of co-infection of Shanxi was prepared and revised. Collected data were analyzed with rare event logistic regression, random effect logistic regression, bayesian estimation and so on. Programming was realized with software of SAS 9.1.3 and Stata 10.0.Collecting and comparing the data of the smear-positive tuberculosis patients from tuberculosis Information Management System database of CDC in Shanxi Province. Time series analysis (ARMA and ARIMA model) and Microsoft SQL Server Analysis Services data mining model - Microsoft Time Series algorithm were used to predict the trend of tuberculosis incidence of Shanxi province.
     Results
     1. Due to the tuberculosis Information Management System database of CDC could not included the information of TB / HIV co-infection,this article will make the database perfect, added the Follow-up survey form, Death registration form,incomes, nutritional status and so on.Based on the tuberculosis Information Management System database of CDC in Shanxi Province. To provide the baseline information for the prevention and treatment of TB/HIV co-infection.
     2. If the frequency difference of dependent variable between two types of values was disparate, the classical logistic regression might underestimate the probability of rare events.Therefore, we adjusted parameters and the estimated value of the probability to solve such problems. Examples in this article, the following methods were used,including the classical logistic regression, logistic regression prior correction, logistic regression MCN prior correction, logistic regression weighted correction and logistic regression MCN weighted correction.The Vuong test was used to compard among different models,the results showed that the logistic regression MCN weighted correction was fit model respectively. Maximum-likelihood estimation, weighted maximum-likelihood estimation, approximate unbiased estimation, approximate bayesian estimation were used to estimate Probability. The results showed that approximate bayesian estimation results optimal. According to Approximate Bayesian estimation, the tuberculosis infection rate of HIV / AIDS patients was about 0.05 in Shanxi Province.
     3. In this investigation, if groups effects among tuberculosis infection rate of HIV / AIDS patients in five counties were considered, there was more individual similarity, then the tuberculosis infection rate of HIV / AIDS patients were non-independent in the same region. Generalized linear mixed-effects model was used to establish logistic regression random effects for the data of HIV / AIDS patients with tuberculosis infection to solve the non-independent problem for the data of HIV / AIDS patients with tuberculosis infection. Examples in this article, the following methods were used the classical logistic Regression, including logistic Regression priori correction, logistic Regression MCN priori correction, logistic Regression weighted correction and logistic Regression MCN weighted correction to fit model respectively. The goodness-of-fit indicators showed that rare event random-effects logistic regression with weighted MCN correction model was better for data fitting. The levels of CD4 would affect the probability of HIV / AIDS patients with tuberculosis incidence. The logarithm of CD4 values changes one unit, The risk lower by 74.9 percent of tuberculosis infection in HIV / AIDS patients.
     4. Generalized linear mixed effect model required numerical integration for joint likelihood function or approximation of the model, and the restricted pseudo-likelihood was the first-order Taylor approximation of generalized linear mixed-effect model. We introduced bayesian estimation into generalized linear mixed-effect model, and the results showed that the posterior estimates were closed to the restricted pseudo-likelihood estimation if the priori noninformation was selected .
     5. The results showed that the model of ARIMA (1,1,0) (1,1,0)12 was better for fitting the data model. The average absolute error was 136.64 between prediction value and actual value, with an average relative error 8.10%. The forecasting results from 2009 showed that the cases of smear-positive in 2009 was much lower than that of previous years, climbing up from March to August, highest in April in 2009.The results of the Microsoft Time Series algorithm was consistented with the model of ARIMA (1,1,0)(1,1,0)12.
     6. Compared with the history predict results of ARIMA model, The average absolute error of Microsoft Time Series algorithm was 116.7, average relative error was 6.60 percents from January 2007 to August 2008, while the average absolute error of ARIMA model was 104.4, average relative error was 5.90 percent, the relative prediction error of ARIMA model was lower than Microsoft Time Series algorithm.
     Conclusions
     1. The content of TB/HIV co-infection was added to the revised form of tuberculosis monitor, it could evaluated the treatment effect of tuberculosis better, controlled TB/HIV co-infection more effective, provided theoretical basis for establishing cooperated pattern of TB and AIDS.
     2. The rare event logistic regression was superior to the classical logistic regression in the rare event analysis, it was worthy of promoted and applied for the rare disdeases. Vuong test was used to evaluated the different regression models.
     3. Under the bayesian assumption,noninformative priors were specified for the parameters in generalized linear mixed-effect model, applying MCMC for parameter estimation,the estimators were consistent with the results that had been gained by using restricted pseudo-likelihood. Bayesian models provided us an effective alternative for nonlinear mixed-effect model,because bayesian estimation did not rely on the asymptotication and approximation, it was more accurate and natural than restrictive pseudo-likelihood estimation under classical statistic. Especially the support of implementation software for bayesian analysis, bayesian models had much more attractive advantages.
     4. Time-series model (ARMA model) could easily dealed with the smooth sequence , and fitting better, it is a practical mathematical model and prediction instrument for infectious diseases prediction, especially tuberculosis. Appropriate analytical model was the key of prediction effect.
     5. The Microsoft Time Series algorithm was introduced to the medical timimg data analysis firstly, we constructed a training model for the the cases of smear-positive in Shanxi Province from January 2005 to December 2008. It combined with self-regression and decision tree technology, enriching the prediction method of medical time-series data. Although Microsoft time sequence algorithm prediction error slightly larger than ARIMA models in this case, the robustness of the prediction effect need to continue to explore, but the principle was simple and easy to comprehend and operate, it was worthy of promoted as a new predicted algorithm.
引文
[1] WHO. Anti - tuberculosis Drug Resistance in the World ,Report No. 2 Prevalence and Trends . Geneva 2000
    [2] World Health Organization , Global Tuberculosis Control ,WHO Report 2000. Geneva :WHO ,2000
    [3] Wandwalo ER , Morkve O. Knowledge of disease and treatment among tuberculosis patients in Mwanza , Tanzania[J]. Int J Tuberc Lung Dis ,2000 ,4(11) :1041-1046
    [4]宋文虎.有关结核病耐药监测的几点看法[J].中华结核和呼吸杂志,2000,23 (2) :73-74
    [5]钱元福,王雪静,游小清.浅评我国第四次结核病流调的设计和调查方法[J].结核病与胸部肿瘤,2000,2 :71-74
    [6]王忠仁,张本.中国结核病学发展史[M].北京:当代中国出版社,1997
    [7]宋文虎,肖成志,宋礼章.结核病学进展[M].第1版,光明日报出版社,北京.1995
    [8]谭京录,王仕昌,韩建平,等.世行贷款结核病控制项目实施的不均衡性和影响因素评析[J].中国防痛杂志,2001,23(2):95
    [9]全国结核病流行病学抽样调查办公室. 2000年全国结核病流行病学抽样调查报告[J].中国防痨杂志,2002,24 (2):65-108
    [10]李晓清.山西省结核病流行病学调查分析.山西医科大学硕士研究生毕业论文,2002
    [11]山西省结核病防治研究所.山西省结核病流行病学调查资料汇编.1980
    [12]山西省结核病防治研究所.山西省结核病流行病学调查资料汇编.1991
    [13]陈明亭,杨功焕.我国疾病监测的历史与发展趋势.疾病监测,2005,20(3):113-114.
    [14]孙振球主编.医学统计学.北京,人民卫生出版社,2005.
    [15] J. A. Nelder and R. W. M. Wedderburn .Generalized Linear Models. Journal of the Royal Statistical Society. Series A (General), 1972,135,3 :370-384.
    [16] McCullagh, P., and Nelder, J. A.. Generalized Linear Models, Second Edition. Chapman and Hall, London. ,1989.
    [17] Long, J. S. Regression Models for Categorical and Limited Dependent Variables. Thousand Oaks: S年龄Publications,Inc.1997.
    [18] Greene, W. Econometric Analysis.Prentice Hall, 2002.
    [19] Cosslett, Stephen R. 1981b.“Efficient Estimation of Discrete-Choice Models.”In Structural Analysis of Discrete. Data with Econometric Applications, eds. Charles F. Manski and Daniel McFadden.MITPress.MA:Cambridge.
    [20] Imbens, Guido. 1992.“An Efficient Method of Moments Estimator for Discrete Choice Models with Choice-Based Sampling.”Econometrica 60(5):1187–1214.
    [21]陈峰.医用多元统计分析方法.北京,中国统计出版社,2001
    [22] Imbens, Guido. 1992. An Efficient Method of Moments Estimator for Discrete Choice Models with Choice-Based Sampling. Econometrica 60(5):1187–1214.
    [23] Cosslett, Stephen R. 1981a. Maximum Likelihood Estimator for Choice-Based Samples. Econometrica 49(5):1289–1316.
    [24] Lancaster, Tony, and Guido Imbens. 1996b. Efficient Estimation and Stratified Sampling. Journal of Econometrics 74:289–318.
    [25] Gary King, Langche Zeng. Logistic Regression in Rare Events Data.Political Analysis, 9:137– 163,. http://gking.harvard.edu/files/abs/0s-abs.shtml.
    [26] Prentice, R. L., and R. Pyke. 1979. Logistic Disease Incidence Models and感染结核-Control Studies. Biometrika 66:403–411.
    [27] Manski, Charles F., and Steven R. Lerman. 1977. The Estimation of Choice Probabilities from Choice Based Samples. Econometrica 45(8):1977–1988.
    [28] Manski, Charles F., and Daniel McFadden. 1981. Alternative Estimators and Sample Designs for Discrete Choice Analysis. In Structural Analysis of Discrete Data with Econometric Applications, eds. Charles F. Manski and Daniel McFadden. Cambridge: MA: MIT Press
    [29] Xie, Yu, and Charles F. Manski. 1989. The Logit Model and Response-Based Samples. Sociological Methods and Research 17(3):283–302
    [30] Amemiya, Takeshi, and Quang H.Vuong. 1987. AComparison of Two Consistent Estimators in the Choice-Based Sampling Qualitative Response Model. Econometrica 55(3):699–702
    [31] Scott, A. J., and C. J. Wild. 1986. Fitting Logistic Models Under tuberculosis-Control or Choice Based Sampling. Journal of the Royal Statistical Society, B 48(2):170–182
    [32] McCullagh, P., and J. A. Nelder, 1989. Generalized Linear Models, 2nd ed. New York: Chapman and Hall
    [33] Gary King ,Langche Zeng .Explaining Rare Events in International Relations . International Organization, Vol. 55, No. 3, pp. 693-715, Summer 2001
    [34] Geisser, Seymour. 1993. Predictive Inference: An Introduction. New York: Chapman and Hall
    [35] King, Gary, and Langche Zeng. 2000a. Inference in tuberculosis-Control Studies with Limited Auxilliary Information .Preprint at http://Gking.harvard.edu
    [36]Tanner, M. A. 1996. Tools for Statistical Inference: Methods for the Exploration of Posterior Distributions and Likelihood Functions, 3rd ed. New York: Springer-Verlag
    [37] Strazzera, Elisabetta - Genius, Margarita . Evaluation of likelihood based tests for non-nested dichotomous choice contingent valuation models. Evaluation of likelihood based tests for non-nested dichotomous choice contingent valuation models. Working Paper. CRENoS. 2000.
    [38] Greene, W. Accounting for excess zeros and sample selection in Poisson and negative binomial regression models. Working Paper No. EC-94-10, Department of Economics, Stern School of Business, New York University,1994
    [39] Vuong, Q.H. Likelihood ratio tests for model selection and non-nested hypotheses. Econometrica, 1989, 57:307-333
    [40] Kullback,S., and Leibler, R.A. On information and sufficiency.Annals of Mathematical Statistics,1951,22: 79-86.
    [41] Sawa, T. Information criteria for discriminating among alternative regression models. Econometrica,1978,46:1273-1282.
    [42] White,H.Maximum likelihood estimation of misspecified models, Econometrica,1982 ,50: 1-25.
    [43]张世英.计量经济模型的选择和检验.信息与控制,1987,6:34-40.
    [44] Akaike H. A new look at the statistical model identification. IEEE Trans. Automat. Contr. 1974,AC-19:716-23.
    [45] Brown H,Prescott R. Applied Mixed Models in Medicine. London: John Wiley and Sons, 1999
    [46] Kleinman K, Lazarus R,Platt R.A generalized linear mixed models approach for detecting incident clusters of disease in small areas, with an application to biological terrorism.Am J Epidemiol,2004,159(3):217-224
    [47] McCullagh P,Nelder JA. Generalized Linear Models. London: Chapman and Hall, 1989
    [48] Breslow NE,Clayton DG.Approximate inference in generalized linear mixed models.Journal of the American Statistical Association,1993,88(421):9-25
    [49] Lin X,Breslow NE.Bias correction in generalized linear mixed models with multiple components of dispersion.Journal of Amrican Statistical Assosiation,1996,91:1007-1016
    [50] Vonesh EF, Wang H, Nie L, et al.Conditional second-order generalized estimating equations for generalized linear and nonlinear mixed-effects models.Journal of the American Statistical Association,2002,96:282-291
    [51] Wolfinger R,O'Connell M.Generalized linear mixed models: A pseudo-likelihood approach.Journal of Statistical Computation and Simulation,1993,48:233-243
    [52] Agresti A, Booth JG, Hobert JP, et al.Random-Effects Modeling of Categorical Response Data.Sociological Methodology,2000,30(2000):27-80.
    [53] Barr SC,O'Neill TJ.The analysis of group truncated binary data with random effects: injury severity in motor vehicle accidents.Biometrics,2000,56(2):443-450.
    [54] Chen Z,Dunson DB.Random effects selection in linear mixed odels.Biometrics.,2003,59(4):762-769.
    [55] Gerhard Tutz,Kauermann G.Generalized linear random effects models with varying coefficients.Computational Statistics & Data Analysis,2003,43(1):13-28.
    [56] Schwarz, G. (1978),“Estimating the Dimension of a Model,”Annals of Statistics, 6, 461–464.
    [57] Hurvich, C. M. and Tsai, C.-L. (1989),“Regression and Time Series Model Selection in Small Samples,”Biometrika, 76, 297–307.
    [58] Hannan, E. J. and Quinn, B. G. (1979),“The Determination of the Order of an Autoregression,”Journal of the Royal Statistical Society, Series B, 41, 190–195.
    [59] Burnham, K. P. and Anderson, D. R. (1998), Model Selection and Inference: A Practical Information-Theoretic Approach, New York: Springer-Verlag.
    [60] Bozdogan, H. (1987),“Model Selection and Akaike’s Information Criterion (AIC): The General Theory and Its Analytical Extensions,”Psychometrika, 52, 345–370.
    [61] Akaike, H. (1974),“A New Look at the Statistical Model Identification,”IEEE Transaction on Automatic Control, AC–19, 716–723.
    [62] Diggle, P. J., Liang, K. Y., and Zeger, S. L. Analysis of Longitudinal Data, Oxford: Clarendon Press,1994 .
    [63] Zeger, S. L., Liang, K. Y., and Albert, P. S. Models for Longitudinal Data: A Generalized Estimating Equation Approach.Biometrics, 1988,44, 1049–1060.
    [64] Liang, K. Y. and Zeger, S. L. Longitudinal Data Analysis Using Generalized Linear Models. Biometrika, 1986, 73, 13–22.
    [65] Laird, N. M. and Ware, J. H. Random-Effects Models for Longitudinal Data.Biometrics, 1982, 38, 963–974.
    [66]徐利治主编.现代数学手册-随机数学卷.华中科技大学出版社,357-390,1999.
    [67] Garrett Fitzmaurice, Nan Laird and James Ware. Applied Longitudinal Analysis, 1st ed. John Wiley ,2004.
    [68] Geert Molenberghs, Geert Verbeke .Models for Discrete Longitudinal Data.Springer Series in Statistics,2005.
    [69] Deborah Ashby. Bayesian statistics in medicine: A 25 year review.Statistics in Medicine,2006, 25:3589–3631.
    [70]方积乾,陆盈.现代医学统计学.北京:人民卫生出版社,2002.
    [71] Metropolis, N. and Ulam, S.The Monte Carlo Method, Journal of the American Statistical Association, 1949,44.
    [72] Sutton, A. and Higgins, J. Recent Development in Meta-analysis. Statistics in Medicine, 2008,27(5), 625–650.
    [73] Carlin, B. P. and Louis, T. A. Bayesian Methods for Data Analysis. 2008,London: Chapman & Hall/CRC.
    [74] Gelman, A., Carlin, J., Stern, H., and Rubin, D. Bayesian Data Analysis, Second Edition.2004,London: Chapman &Hall.
    [75] S. Geman, Donald Geman . Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images. IEEE Transactions on Pattern Analysis and Machine Intelligence , 1984,6: 721–741.
    [76] Metropolis, N., Rosenbluth, A., Rosenbluth, M., Teller, A., and Teller, E.Equation of State Calculations by Fast Computing Machines, Journal of Chemical Physics,1953, 21, 1087–1092.
    [77]王丽娜,肖冬荣.基于ARMA模型的经济非平稳时间序列的预测分析[J].武汉理工大学学报,2004,28(1):133-136.
    [78]林少宫袁蒲佳.多元统计分析及计算程序[M].武汉:华中理工大学出版社,1987,281-295.
    [79]孟昭为.多维ARMR(p,q)模型的适时递推预报[J].山东工程学院学报,2000,14(4):21-24.
    [80]王艳明许启发.时间序列分析在经济预测中的应用[J].统计与预测,2001,5(113);32-34.
    [81]朱玉贵,余祥万.自回归模型在病毒性肝炎预测中的应用[J].数理医药学杂志,1998,11 (3):91-92.
    [82]王振龙.时间序列分析[M].北京:中国统计出版社,2000
    [83]王燕.应用时间序列分析(第二版)[M].北京:中国人民大学出版社,2008
    [84]张晋昕方积乾.基于预报效果的ARIMA模型筛选[J].中国卫生统计,2002,21(1):6-9.
    [85]丁宁銮,唐家琦,王洁贞. ARIMA模型在发病率预测的应用[J].中国医院统计,2003,10(1):23-26.
    [86]温亮,徐德忠,林明和等.应用时间序列模型预测疟区疟疾发病率[J].第四军医大学学报,2004,25(6):507-510.
    [87]张蔚,张彦琦,杨旭.时间序列资料ARIMA季节乘积模型及其应用[J].第三军医大学学报,2002,24(8):955-957.
    [88]孔凡坤.新余市2005~2007年肺结核病流行病学特征分析.实用临床医学,2008,9(4):113-114.
    [89]华海庆.泰州市1997~2003年肺结核流行病学分析.实用预防医学,2005,12(3):590-591.
    [90]黄毅群.保持隐私的数据挖掘.华中科技大学博士研究生毕业论文,2006
    [91]王欣,徐腾飞,唐连章,等. SQL Server 2005数据挖掘实例分析[M].北京:中国水利水电出版社,2008
    [92] Tang ZH,Jamie M. Data mining with SQL Server 2005[M].John Niley and Sons Inc, 2005
    [93]曾平,刘桂芬,曹红艳等.广义线性模型贝叶斯分析的SAS实现.中国卫生统计,2009,26(1):104-106
    [1]孙振球,徐勇勇.医学统计学[M].北京:人民卫生出版社,2002,251-271.
    [2]王丙刚,曲波,郭海强等.传染病预测的数学模型研究[J].中国卫生统计,2007,24(5):535-540.
    [3]谢朝晖,黄建始.传染病预测方法的探讨[J].中国全科医学,2008,11(1):85-87.
    [4]李艳梅孙薇.多元线性回归分析在用电量预测中的应用[J].华北电力技术,2003,11:40-41.
    [5]丁宁銮,唐家琦,王洁贞. ARIMA模型在发病率预测的应用[J].中国医院统计,2003,10(1):23-26.
    [6]温亮,徐德忠,林明和等.应用时间序列模型预测疟区疟疾发病率[J].第四军医大学学报,2004,25(6):507-510.
    [7]张蔚,张彦琦,杨旭.时间序列资料ARIMA季节乘积模型及其应用[J].第三军医大学学报,2002,24(8):955-957.
    [8]张文彤. SPSS统计分析教程[M].北京:北京希望电子出版社,2002,250-289
    [9]钟朝晖,刘达伟,张燕.重庆市主城区人口死亡率的时间序列分析[J].中国公共卫生,2003,19(7):796-798.
    [10] Chatfield C.The Analysis of Time Series:An Introduction [M].New York:Chapman and Hall, 1984,18.
    [11]王振龙.时间序列分析[M].北京:中国统计出版社,2000.
    [12] Veit Oehkler,Francesco Luongo.The Galileo Integrity Concept[A].In:ION GNSS 17th International Meeting of the Satellite Division[C],21-24 Sept 2004,Long Beach,CA 2004:604-615.
    [13]徐国祥.统计预测和决策[M].上海:上海财经大学出版社,2005.202-225.
    [14]Carlos Hernandez,etc.SISA Computation Algorithm and their Applicability for Galileo Integrity[A].In:ION GNSS International Meeting of the Satellite Division[C],24-27 Sept 2002,Portland,OR:2173-2184
    [15]Shaojun Feng and Washington Y Ochieng.An Efficient Worst User Location Algorithm for the Generation of the Galileo Integrity Flag[A].In:ION GNSS International Meeting of the Satellite Division[C],13-16 Sept 2005,Long Beach,CA.2005:2374-2384.
    [16]R Dellago,JM Pieplu.The Galileo System Architecture at the End of the Design Phase[A].In:ION GNSS International Meeting of the Satellite Division[C],9-12 Sept 2003,Portland,OR.
    [17]程颖恺,曾光.麻疹、猩红热流行中存在”Z-D现象”的进一步论证及其预测价值研究[J].中华流行病学杂志,1999,19(4):9-12.
    [18]张晋昕方积乾.基于预报效果的ARIMA模型筛选[J].中国卫生统计,2002,21(1):6-9.
    [19]王丽娜,肖冬荣.基于ARMA模型的经济非平稳时间序列的预测分析[J].武汉理工大学学报,2004,28(1):133-136.
    [20]林少宫袁蒲佳.多元统计分析及计算程序[M].武汉:华中理工大学出版社,1987,281-295.
    [21]孟昭为.多维ARMR(p,q)模型的适时递推预报[J].山东工程学院学报,2000,14(4):21-24.
    [22]王艳明许启发.时间序列分析在经济预测中的应用[J].统计与预测,2001,5(113);32-34.
    [23]朱玉贵,余祥万.自回归模型在病毒性肝炎预测中的应用[J].数理医药学杂志,1998,11 (3):91-92.
    [24] Report:AIDS epidemic update December.1999,WHO&UNAIDS,1999.
    [25]李艳梅,徐爽.应用余弦模型分析流行性腮腺炎发病季节性[J].中国卫生统计,1999,16(1):41.
    [26]杨倬.利用数学模型研究传染病发病季节特征[J].现代预防医学,2003,30(6):786-788.
    [27]谢学勤,高京晓,孙贤理.余弦模型在痢疾季节性研究中的应用[J].中国公共卫生,2000,16(6):560.
    [28] Shugin B,Stone L,Agur Z.Pulse vaccination strategy in the SIR epidemic model.Bull Math Biol,1998,60:1-26.
    [29] Feng Z,lannelli M,Milner FA.A two-strain tuberculosis model with age of infection.SIAM API ath,2002,62(5):1634-1656.
    [30]Riley S.et al.Transmission Dynamics of etiological agent of SARS in Hong Kong:impact of public heath interventions.Science,2003,300:1961-1966.
    [31]吴开录,吴开琛,陈文江等.登革热数学模型及其应用研究(Ⅰ)兼评Newton的登革热传播模式[J].中国热带医学,2001,1 (1):12-16.
    [32] Guo WS.Marshall G.ORDMKV:a computer program fitting proportional odds mod el for multi-state Markov process[J].Computer Methods and Programs in Biomedicine,1995,46:257-263.
    [33]Ghahrarnni Z.Variation learning for switching state-space models[J].Neural Compute,2000,12(4):831-864.
    [34]Penny WD,Roberts SJ.Dynamic models for no stationary signal segmentation[J]. Compute Biomed Res,1999,32(6):483,502.
    [35]王倩,金丕焕.Markov模型在卫生经济评价的应用[J].中国卫生统计,2000,17(2):86-88.
    [36]丁元林,孔丹莉,倪宗瓒.多状态Markov模型及其在慢性流行病学研究中的应用[J].中国公共卫生,2002,18(12),1420-1422.
    [37]郑月秀,刘景荣,肖树生等.应用马尔可夫链进行流行性出血热疫情预测[J].海峡预防医学杂志,2001,7 (3):47-26.
    [38]巴剑波,方旭东,徐雄利.马尔可夫链在海军疟疾疫情预测中的应用[J].解放军预防医学杂志,2001,19:114-116.
    [39]HW Hethcote.The mathematics of infectious diseases.SIAM ev.2O00,42(5):999.
    [40]L Arcangelis.HJ Hermann.Self-organized criticality on small world networks.Physica A,2002,308(1):545-549.
    [41]Ioannidis JP,McQueen PG ,Goedert JJ et a1 . Use of neural networks to model complex immunogenetic associations of disease:human leukocyte antigen impact on the progression of human imm unodeficiency virus infection.Am J Epidemiol,1998,147(5):464-471.
    [42]丁守銮,王洁贞,袁晓红.肾综合征出血热发病率的ANN预测模型[J].山东大学学报(医学舨),2002,47:100-102.
    [43]高春玉,熊鸿燕,易东等.智能神经网络模型用于气象因素对疟疾发病影响的初步研究[J].中华流行病学杂志,2003,23 (9):82-85.
    [44]余国华黄厚宽.时间序列模型的选择方法[J].广西师范大学学报,2003,21(1):191-194.
    [45]潭冠军.GM(1,1)模型的背景值构造方法和应用[J].系统工程理论与实践,2000,20(4):99-103.
    [46]刘思峰.灰色系统理论及应用[M].北京:科学出版社,2000.
    [47]Guthmann JP,Lianos-Cuentas A,Palacios A,et a1.Environmental factors as delerminants of malaria risk:A descriptive study on the northern coast of Peru[J]. T P Med Int Health,2002,7:518-525.
    [48]龚向龙,王全佩,张君炎等.试应用灰色系统GM(1,1)模型预测性病发病率.中国公共卫生,1997:13(11):643-644.
    [49]Christophe Boete,Jacob CK.A theoretical approach to predicting the success of genetic manipulation of malaria mosquitoes in malaria control.Mar,2002,1:3-10.
    [50]黄春萍,倪宗瓒.灰色模型在预测肺结核发病率中的应用[J].现代预防医学,2002,28: 791-793.
    [51]冯丹,罗艳侠,鲍卫华等.流行性脑脊髓膜炎流行特征的灰色预测模型[J].数理医药学杂志,2003,16:97-99.
    [52]赖永珲,洪福昌,曾序春等.深圳市H1V/艾滋病流行趋势灰色预测[J].现代预防医学,2003,29:446-447.
    [53]边馥苓.地理信息系统原理和方法[M].北京:北京测绘出版社,1996.
    [54]Bavia Me,Hale LF,Malone JB,et al. Geographic information systems and the environmental risk of schistosomiasis in Bahia,Brazil[J].Am J Med Hyg,1999,60:556-572.
    [55]杨国静,周晓农,JB Malon.江苏省疟疾流行地理信息系统预测模型的研究[J].中华预防医学杂志,2002,36(2):103-106.
    [56]周晓农,洪青标,孙乐平等.地理信息系统应用于血吸虫病的监测-应用预测模型的可能性[J].中国血吸虫病防治杂志,1998,10:321-324.
    [57]汪天平,周晓农,刘建翔等.地理信息系统(GIS)用于江苏、安徽和江西省血吸虫病流行预测的研究[J].中国血吸虫病防治杂志,2004,16:86-89.
    [58] Wolfram S ,Michael F. Cellular automata as models of complexity[ J ]. Nature, 1984, 311: 419- 424.
    [59]邬伦,马修军,田原.基于场模型的空间动态数据建模与空间动态模型语言设计[ J ].地理学与国土研究,2000, 16 (4) : 73-76. [60 ]孙战利.空间复杂性与地理元胞自动机模拟研究[ J ].地球信息科学, 1999, 11 (4) : 32.
    [61] Berry J K. Beyond Mapping: Concepts, Algorithms, and Issuesin GIS For Collins[ J ]. GIS World, 1993: 39-57.
    [62] Tomlin D. Cartographic Modelling In Maguire D, Good child M, Rhind D. Geographical Information System: Principles and Applications[M ]. New York: John Wiley andSons, 1991: 361-374. [63 ]马修军,周贵云,邬伦. GIS空间动态模型组件的设计与实现[J].地理学与国土研究, 2002, 8 (3) : 20 - 21. [64 ]李才伟.元胞自动机及复杂系统的时空演化模拟[D ].武汉:华中理工大学, 1997.
    [65]于鑫,段小东,刘向东等.基于元胞自动机的流行病传播模型及模拟[J].计算机工程与应用, 2005(2) : 206 - 207. [66 ]谢惠民.非线性科学丛书:复杂性与动力系统[M ].上海:上海科技教育出版社, 1994 : 127-129.
    [67]Anderson RM,Grenfell BT.Quantitative investigations of different vaccination policies for the control of congenital rubella syndrome(CRS)in the United Kingdom [J].J Hyg(Lond),1986,96:305-333.
    [68]Garnett GP, Meaz KJ, Finelli L et al.The transmission of dynamics of gonorrhoea modelling the reported behavior of infected patients from Newark,New Jersey [J].Philos Trans R Soc Lond B Biol Sci, 1999,354:787-797.
    [69]Robinson NJ,Mulder DW,Auvert B et al.Modelling the impact of alternative HIV intervention strategies in rural Uganda [J].AIDS,1995,9:1263-1270.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700