FNR/STAT 598Z Applied Spatial Statistics

TTh 10:30-11:45, BRNG B261

Spring, 2008

 

Instructor:       Professor Hao Zhang, 496-9548, zhanghao@purdue.edu

                        http://www.stat.purdue.edu/people/faculty/zhanghao

 

Office Hours: Monday, Tuesday and Thursday, 1:30-2:30pm

 

Prerequisite:    A graduate course in statistics or probability.

Primary Audience:      Students who are interested in analyzing spatial data.

 

Description:     This course covers a wide range of statistical models and methods for data that are collected at different spatial locations and perhaps at different times. These data are called spatial or spatio-temporal data, which arise in many scientific disciplines such as agronomy, plant pathology, forestry and natural resources, environmental and health studies, climatology, geology, biosecurity, etc. Spatial statistics is currently one of the most active research areas in statistics and there has been a tremendous advancement in methodological and computational research in spatial statistics that enables us to analyze massive spatial data today. This course will introduce the classical methods as well as some newly developed ones, and will provide ample hands-on activities. The programming language R and a few packages for analyzing spatial data will be introduced. One objective is for students to be able to identify appropriate methods and analyze spatial data in their research.

Topics: This course covers statistical methods for georeferenced data (such as ozone measurements from different monitoring stations), spatial point patterns (such as incidents of plant/human disease), and areal data (such as county statistics in the US).  An incomplete list of topics is as follows.

·        Stationarity and variogram models

·        Fitting a variogram model

·        Kriging or best linear unbiased prediction (simple kriging,  ordinary kriging, and universal kriging).

·        Kriging with large datasets

·        Non-stationary models

·        Spatio-temporal models

·        Multivariate methods (direct and cross covariograms, cokriging)

·        Conditional autoregressive models

·        Spatial point patterns

·        Complete randomness and Poisson processes

·        Cluster processes and inhibition processes

·        K-function

·        Intensity function and inhomogenous Poisson processes

·        Scan statistics

·        Simulation of spatial processes and spatial point patterns

 

Grading:          Final grades will be based on homework, project and/or exams.  Students are allowed and indeed encouraged to study as a group. However, each one has to turn in an independent work in his/her own words. For example, although it is allowed to study together for programming, a student needs to turn in his/her own work to show that the student is able to carry out the programming.

 

The instructor reserves the right to make any changes that he deems academically advisable.