placeholder image
  • Contact Info
Publications in VIVO
 

Kleiber, William Paul Assistant Professor

Positions

Research Areas research areas

Research

research overview

  • Dr. Kleiber is an expert in spatial statistics, developing theory for multivariate space-time processes, including flexible nonstationary models as well as feasible estimation approaches for large datasets. Dr. Kleiber also has expertise in computer experiments, and has developed methodological approaches for calibrating, emulating and analyzing complex geophysical computer models. Another primary focus is statistical climatology, especially in building stochastic weather simulators for use in agricultural, ecological and hydrological modeling. He has also developed approaches for probabilistic weather forecasting, focusing on sharp and calibrated local forecasting for temperature and precipitation. Recent research has focused on stochastic parameterizations and stochastic modeling for energy applications.

keywords

  • spatial statistics, matrix-valued positive definite functions, covariance functions, stochastic modeling, geostatistics, Gaussian processes, computer experiments, nonstationarity, space-time processes, model calibration, model emulation, large datasets, stochastic weather generators

Publications

selected publications

Teaching

courses taught

  • APPM 4540 - Introduction to Time Series
    Primary Instructor - Spring 2018
    Studies basic properties, trend-based models, seasonal models modeling and forecasting with ARIMA models, spectral analysis and frequency filtration. Same as STAT 5540 and MATH 4540 and MATH 5540.
  • APPM 4580 - Statistical Learning
    Primary Instructor - Spring 2018 / Spring 2019
    Consists of applications and methods of statistical learning. Reviews multiple linear regression and then covers classification, regularization, splines, tree-based methods, support vector machines, unsupervised learning and Gaussian process regression.
  • APPM 5540 - Introduction to Time Series
    Primary Instructor - Spring 2018
    Studies basic properties, trend-based models, seasonal models modeling and forecasting with ARIMA models, spectral analysis and frequency filtration. Department enforced prerequisite: APPM 5520 or MATH 5520. Same as STAT 4540 and MATH 4540 and MATH 5540.
  • APPM 5580 - Introduction to Statistical Learning
    Primary Instructor - Spring 2018 / Spring 2019
    Consists of applications and methods of statistical learning. Covers multiple linear regression, classification, regularization, splines, tree-based methods, support vector machines and unsupervised learning. Same as APPM 4580.
  • MATH 4540 - Introduction to Time Series
    Primary Instructor - Spring 2018
    Studies basic properties, trend-based models, seasonal models, modeling and forecasting with ARIMA models, spectral analysis and frequency filtration. Same as MATH 5540 and STAT 4540 and STAT 5540.
  • MATH 5540 - Introduction to Time Series
    Primary Instructor - Spring 2018
    Studies basic properties, trend-based models, seasonal models, modeling and forecasting with ARIMA models, spectral analysis and frequency filtration. Department enforced prerequisite: MATH 4520 or MATH 5520 or APPM 4520 or APPM 5520. Same as MATH 4540 and STAT 4540 and STAT 5540.
  • STAT 4430 - Spatial Statistics
    Primary Instructor - Spring 2019
    Introduces the theory of spatial statistics with applications. Topics include basic theory for continuous stochastic processes, spatial prediction and kriging, simulation, geostatistical methods, likelihood and Bayesian approaches, spectral methods and an overview of modern topics such as nonstationary models, hierarchical modeling, multivariate processes, methods for large datasets and connections to spines. Same as STAT 5430.
  • STAT 5430 - Spatial Statistics
    Primary Instructor - Spring 2019
    Introduces the theory of spatial statistics with applications. Topics include basic theory for continuous stochastic processes, spatial prediction and kriging, simulation, geostatistical methods, likelihood and Bayesian approaches, spectral methods and an overview of modern topics such as nonstationary models, hierarchical modeling, multivariate processes, methods for large datasets and connections to spines. Same as STAT 4430.

Background

International Activities

Other Profiles