placeholder image
  • Contact Info
Publications in VIVO
 

Dukic, Vanja Professor

Positions

Research Areas research areas

Research

research overview

  • Dr. Dukic' research is focused on Bayesian statistical modeling and statistical computing, with applications to ecology, medicine, and business. Her research has resulted in insights into meta analysis techniques, diagnostic testing, survival modeling, biomarker modeling, risk and loss reserve modeling, smoking behavior, spread of epidemics (flu, smallpox, meningitis, and MRSA), and climate change impact on infectious diseases and pests.

keywords

  • Bayesian statistics, statistical inference, probability, stochastic processes, computational statistics, stochastic optimization, model selection, decision theory, applied mathematics

Publications

selected publications

Teaching

courses taught

  • APPM 4570 - Statistical Methods
    Primary Instructor - Fall 2018
    Covers basic statistical concepts with accompanying introduction to the R programming language. Topics include discrete and continuous probability laws, random variables, expectation and variance, central limit theorem, testing hypothesis and confidence intervals, linear regression analysis, simulations for validation of statistical methods and applications of methods in R. Same as APPM 5570.
  • APPM 4590 - Statistical Modeling
    Primary Instructor - Spring 2018 / Spring 2019
    Introduces methods, theory and applications of statistical models, from linear models (simple and multiple linear regression), to hierarchical linear models. Topics such as estimation, residual diagnostics, goodness of fit, transformations, and various strategies for variable selection and model comparison will be discussed in depth. Examples and exercises will be demonstrated using statistical software. Same as APPM 5590.
  • APPM 4720 - Open Topics in Applied Mathematics
    Primary Instructor - Spring 2019
    Provides a vehicle for the development and presentation of new topics that may be incorporated into the core courses in applied mathematics. Department enforced prerequisite: variable, depending on the topic, see instructor. May be repeated up to 15 total credit hours. Same as APPM 5720.
  • APPM 5570 - Statistical Methods
    Primary Instructor - Fall 2018
    Covers basic statistical concepts with accompanying introduction to the R programming language. Topics include discrete and continuous probability laws, random variables, expectation and variance, central limit theorem, testing hypothesis and confidence intervals, linear regression analysis, simulations for validation of statistical methods and applications of methods in R. Same as APPM 4570.
  • APPM 5590 - Statistical Modeling
    Primary Instructor - Spring 2018 / Spring 2019
    Introduces methods, theory and applications of statistical models, from linear models (simple and multiple linear regression), to hierarchical linear models. Topics such as estimation, residual diagnostics, goodness of fit, transformations, and various strategies for variable selection and model comparison will be discussed in depth. Examples and exercises will be demonstrated using statistical software. Department enforced prerequisite: APPM 4570 or APPM 4520 or MATH 4520 or instructor consent required. Same as APPM 4590.
  • APPM 5720 - Open Topics in Applied Mathematics
    Primary Instructor - Spring 2019
    Provides a vehicle for the development and presentation of new topics that may be incorporated into the core courses in applied mathematics. Department enforced prerequisite: variable, depending on the topic, see instructor. May be repeated up to 6 total credit hours. Same as APPM 4720.
  • APPM 6950 - Master's Thesis
    Primary Instructor - Spring 2020
    May be repeated up to 6 total credit hours.
  • STAT 4000 - Statistical Methods and Application I
    Primary Instructor - Fall 2018 / Fall 2019
    Introduces exploratory data analysis, probability theory, statistical inference, and data modeling. Topics include discrete and continuous probability distributions, expectation, laws of large numbers, central limit theorem, statistical parameter estimation, hypothesis testing, and regression analysis. Considerable emphasis on applications in the R programming language. Same as STAT 5000.
  • STAT 4400 - Advanced Statistical Modeling
    Primary Instructor - Spring 2020
    Introduces methods, theory and applications of modern statistical models, from hierarchical linear models, to generalized hierarchical linear models, including hierarchical logistic and hierarchical count regression models. Topics such as estimation, residual diagnostics, goodness of fit, transformations, and various strategies for variable selection and model comparison will be discussed in depth. Examples will be demonstrated using statistical programming language R.
  • STAT 4630 - Computational Bayesian Statistics
    Primary Instructor - Spring 2020
    Introduces Bayesian statistics, normal and non-normal approximation to likelihood and posteriors, the EM algorithm, data augmentation, and Markov Chain Monte Carlo (MCMC) methods. Additionally, introduces more advanced MCMC algorithms and requires significant statistical computing. Examples from a variety of areas, including biostatistics, environmental sciences, and engineering, will be given throughout the course. Recommended prerequisite: prior programming experience. Same as STAT 5630.
  • STAT 5000 - Statistical Methods and Application I
    Primary Instructor - Fall 2018 / Fall 2019
    Introduces exploratory data analysis, probability theory, statistical inference, and data modeling. Topics include discrete and continuous probability distributions, expectation, laws of large numbers, central limit theorem, statistical parameter estimation, hypothesis testing, and regression analysis. Considerable emphasis on applications in the R programming language. Same as STAT 4000.
  • STAT 5400 - Advanced Statistical Modeling
    Primary Instructor - Spring 2020
    Introduces methods, theory and applications of modern statistical models, from hierarchical linear models, to generalized hierarchical linear models, including hierarchical logistic and hierarchical count regression models. Topics such as estimation, residual diagnostics, goodness of fit, transformations, and various strategies for variable selection and model comparison will be discussed in depth. Examples will be demonstrated using statistical programming language R.
  • STAT 5630 - Computational Bayesian Statistics
    Primary Instructor - Spring 2020
    Introduces Bayesian statistics, normal and non-normal approximation to likelihood and posteriors, the EM algorithm, data augmentation, and Markov Chain Monte Carlo (MCMC) methods. Additionally, introduces more advanced MCMC algorithms and requires significant statistical computing. Examples from a variety of areas, including biostatistics, environmental sciences, and engineering, will be given throughout the course. Recommended prerequisite: prior programming and basic statistical modeling experience is required. Same as STAT 4630.

Background

International Activities

Other Profiles