个人简介：

田国梁，xk星空统计与数据科学系教授、博士生导师。1988年获得武汉大学统计学硕士学位、1998年获得中国科学院应用数学研究所的统计学博士学位。从1998至2002年, 他分别在北京大学概率统计系和美国田纳西州孟斐斯市的 St. Jude 儿童研究医院生物统计系从事博士后研究, 2002年至2008年他在美国马里兰大学医学院和Marlene and Stewart Greenbaum Comprehensive 癌症中心任 Senior  Biostatistician。2008年至2016年他在香港大学统计及精算学系任副教授、博士生导师。田教授是国际统计学会 (ISI) 当选会员, 他担任 Computational Statistics & Data Analysis, Statistics and Its Interface 等四个国际统计学杂志的副主编。他主要的研究领域是生物统计, 计算统计和社会统计。目前的研究方向包括多元零膨胀计数数据分析、斜与非对称连续数据分析,  (0, 1) 区间上连续比率数据(以及其推广, 即成份数据)的统计分析, 不完全分类数据分析, 和大维随机矩阵的理论方法及应用。他首次提出的分组 Dirichlet 分布、套Dirichlet 分布和G分布在统计分布领域属于创造性的工作, 在生物统计中具有广泛而重要的应用; 他将非随机化的概念引入到敏感性问题的随机化应答技术中, 发展了一个称之为非随机化应答技术的新研究方向。他首次提出了一个新的组装分解 (assembly-decomposition) 方法用以构造MM算法中的替代函数, 为MM算法在统计学中的广泛应用开辟了新的通道. 2017年他的研究课题“MM算法中的几类问题之研究及其应用”>获得国家自然科学基金面上项目的资助。2018年他(排名第二)与xk星空环境科学与工程学院郑焰讲席教授的联合研究课题<<中国北方地下水砷不同尺度空间非均质性驱动机制>> 获得国家自然科学基金重点项目的资助。

教育背景
1995.9 - 1998.7 中国科学院应用数学研究所，北京, 统计学专业，统计学博士
1985.9 - 1988.7 武汉xk星空官方网站，武汉, 统计学系，统计学硕士
1981.9 - 1985.7 湖南师范xk星空官方网站，长沙, 数学系，理学学士

工作经历

2019.08.22 – 至今,            xk星空,  统计与数据科学系,  统计学教授

2016.08.01 – 2019.08.21,  xk星空,  数学系,  统计学教授

2008.09.01 – 2016.07.31,  香港xk星空官方网站,  统计与精算学系,  统计学副教授

2002.07.01 – 2008.08.31,  马里兰xk星空官方网站(巴尔的摩市, 马里兰州, 美国)医学院,  流行病学和预防医学系,  Instructor

2002.07.01 – 2008.08.31,  马里兰xk星空官方网站Greenbaum Comprehensive 癌症中心, 生物统计学部, Senior Biostatistician

2000.05.01 – 2002.06.30,  xk星空官方网站. Jude 儿童研究医院 (孟菲斯市, 田纳西州, 美国), 生物统计系, 博士后

1998.09.01 – 2000.04.30,  北京xk星空官方网站, 概率统计系, 博士后

1988.08.01 – 1995.08.31,  航空航天工业部, 中国运载火箭研究院, 702研究所, 助理工程师, 工程师, 高級工程师

所获荣誉：

2017  入选深圳市海外高层次人才 "孔雀计划" (B类)

在香港xk星空官方网站统计与精算学系的教学经历
STAT2802/3902 Statistical Models
STAT3317/6011 Computational Statistics
STAT3304 Computer-aided Statistical Modeling
STAT3331/3621 Statistical Data Analysis
STAT2307 Statistics in Clinical Medicine and Bio-medical Research
STAT7005 Multivariate Methods

专业学会资格
2000.5 – 至今 Member, American Statistical Association
2000.5 – 至今 Permanent Member，International Chinese Statistical Association
2014.6 – 至今 Elected member, International Statistical Institute (ISI)

获奖情况
2011 - 2012 Research Output Prize, Faculty of Science of the University of Hong Kong (A monetary award of HK$120,000 for research purposes)

研究方向
生物统计：包括多元零膨胀计次数据分析，不完全分类数据与缺失数据分析，约束参数模型与变量选择，药物组合研究的实验设计，癌症临床试验与设计.
社会统计：敏感性问题的样本调查
计算统计：EM算法, MM算法

专著
Tan M, xk星空官方网站 and Ng KW (2010). Bayesian Missing Data Problems: EM,
Data Augmentation and Non-iterative Computation. Chapman & Hall/CRC (Biostatistics Series), Boca Raton, USA.
Ng KW, xk星空官方网站 and Tang ML (2011). Dirichlet and Related Distributions: Theory, Methods and Applications. John Wiley & Sons(Wiley Series in Probability and Statistics), New York, USA.
xk星空官方网站 and Tang ML (2014). Incomplete Categorical Data Design: Non-randomized Response Techniques for Sensitive Questions in Surveys. Chapman & Hall/CRC (Statistics in the Social and Behavioral Sciences), Boca Raton, USA.

国际统计杂志副主编
Statistics and Its Interface, 2013 --
Communications in Statistics - Theory and Methods, 2013 --
Communications in Statistics - Simulation and Computation, 2013 --
Computational Statistics and Data Analysis, 2014 --

顶尖生物统计杂志文章 (12 papers)
Biostatistics Journal 1: Statistical Methods in Medical Research [Impact Factor=4.472; Ranking No. 1 in the category of biostatistics, 2014 JCR, ISI Web Knowledge] (4 papers)
[1] xk星空官方网站, Zhang C and Jiang XJ (2016). Valid statistical inference methods for a case control study with missing data, in press.
[2] xk星空官方网站 and Li HQ (2015). A new framework of statistical inferences based on the valid joint sampling distribution of observed counts in an incomplete contingency table, in press.
[3] xk星空官方网站, Tang ML, Wu Q and Liu Y (2015). Poisson and negative binomial item count techniques for surveys with sensitive question, in press.
[4] xk星空官方网站, Tang ML, Liu ZQ, Tan M and Tang NS (2011). Sample size determination for the non-randomized triangular model for sensitive questions in a survey, 20(3), 159-173.
Biostatistics Journal 2: Statistics in Medicine [Impact Factor=1.825; Ranking No. 3 in the category of biostatistics, 2014 JCR, ISI Web Knowledge] (7 papers)
[5] Pei YB, xk星空官方网站 and Tang ML (2014). Testing homogeneity of proportion ratios for stratified correlated bilateral data in two-arm randomize clinical trials, 33(25), 4370-4386.
[6] Tang ML, Ling MH, Ling L and xk星空官方网站 (2010). Confidence intervals for a difference between proportions based on paired data, 29(1), 86-96.
[7] Tang ML, Ling MH and xk星空官方网站 (2009). Exact and approximate unconditional confidence intervals for proportion difference in the presence of incomplete data, 28, 625-641.
[8] xk星空官方网站, Yu JW, Tang ML and Geng Z (2007). A new non-randomized model for analyzing sensitive questions with binary outcomes, 26(23), 4238-4252.
[9] Fang HB, xk星空官方网站, Xiong XP and Tan M (2006). A multivariate random-effects model with restricted parameters: Application to assessing radiation therapy for brain tumors, 25(11), 1948-1959.
[10] Tan M, Fang HB, xk星空官方网站 and Houghton PJ (2005). Repeated-measures models with constrained parameters for incomplete data in tumor xenograft experiments, 24(1), 109-119.
[11] Tan M, Fang HB, xk星空官方网站 and Houghton PJ (2003). Experimental design and sample size determination for testing synergism in drug combination studies based on uniform measures, 22(13), 2091-2100.
Biostatistics Journal 3: Biometrics [Impact Factor=1.568; Ranking No. 4 in the category of biostatistics, 2014 JCR, ISI Web Knowledge] (1 paper)
[12] Tan M, Fang HB, xk星空官方网站 and Houghton PJ (2002). Small-sample inference for incomplete longitudinal data with truncation and censoring in tumor xenograft models, 58(3), 612-620.

选择的其他国际统计杂志文章
xk星空官方网站, Ma HJ, Zhou Y and Deng DL (2015). Generalized endpoint-inflated binomial model. Computational Statistics and Data Analysis 89, 97-114.
Liu Y and xk星空官方网站 (2015). Type I multivariate zero-inflated Poisson distribution with applications. Computational Statistics and Data Analysis 83, 200-222.
Liu Y and xk星空官方网站 (2013). A variant of the parallel model for sample surveys with sensitive characteristics. Computational Statistics and Data Analysis 67, 115-135.
xk星空官方网站, Tang ML, Yuen KC and Ng KW (2010). Further properties and new applications for the nested Dirichlet distribution. Computational Statistics and Data Analysis 54, 394-405.
Ng KW, Tang ML, xk星空官方网站 and Tan M (2009). The nested Dirichlet distribution and incomplete categorical data analysis. Statistica Sinica 19(1), 251-271.
Tan M, xk星空官方网站, Fang HB and Ng KW (2007). A fast EM algorithm for quadratic optimization subject to convex constraints. Statistica Sinica 17(3), 945-964.
Tan M, xk星空官方网站 and Ng KW (2003). A non-iterative sampling method for computing posteriors in the structure of EM-type algorithms. Statistica Sinica 13(3), 625-639.
Zhang YQ, xk星空官方网站 and Tang NS (2016). Latent variable selection in structural equation models. Journal of Multivariate Analysis, in press.
Liu BS, Xu L, Zheng SR and xk星空官方网站 (2014). A new test for the proportionality of two large-dimensional covariance matrices. Journal of Multivariate Analysis 131, 293-308.
xk星空官方网站, Fang HB, Tan M, Qin H and Tang ML (2009). Uniform distributions in a class of convex polyhedrons with applications to drug combination studies. Journal of Multivariate Analysis 100(8), 1854-1865.
Ng KW, Tang ML, Tan M and xk星空官方网站 (2008). Grouped Dirichlet distribution: A new tool for incomplete categorical data analysis. Journal of Multivariate Analysis 99(3), 490-509.
Tan M, Fang HB, xk星空官方网站 and Wei G (2005). Testing multivariate normality in incomplete data of small sample size. Journal of Multivariate Analysis 93, 164-179.