Dear Members of the Kansas-Western Missouri Chapter of the ASA,
Please join us for our spring Chapter meeting on Thursday, April 10th, 2014 at Kansas State University. The meeting will be held in the Holiday Inn of Manhattan. A map is provided below for your convenience. Professor Sudipto Banerjee in School of Public Health, Division of Biostatisticsat University of Minnesota will be presenting the Keynote Address “On complex spatial dependencies: Low-rank cross-covariance models”. Professor Banerjee will also present a seminar talk at Department of Statistics at Kansas State University on “Space, Time and Gradients: Why we need them in statistical modeling for public health data” at 4:00pm, Dickens 207. Additional information about his talks is listed below.
The cost to attend the chapter meeting is $30.00 ($20.00 for students), which includes dinner.
Registration for this event can be done online at
The on-line registration time frame is
Feb 06, 2014
Apr 07, 2014
Please contact our Chapter president, Weixin Yao(email@example.com) or Chapter secretary Juan Du (firstname.lastname@example.org) if you have any questions.
We look forward to seeing you in Manhattan!
6:00 – 6:15 p.m. Social time
6:15 - 6:30 p.m. The induction ceremony for Mu Sigma Rho Honor Society
6:30 – 7:15 p.m. Dinner
7:15 – 7:30 p.m. Chapter business
7:30 – 8:30 p.m. Keynote Address
Chapter Meeting Keynote Address
Title: On complex spatial dependencies: Low-rank cross-covariance models.
Abstract: Advances in geo-spatial technologies have created data-rich environments which provide extraordinary opportunities to understand the complexity of large and spatially indexed data and help tackle increasingly complex inferential questions in the natural sciences. A setting commonly encountered today is where multiple geo-referenced outcomes have been monitored over different spatial locations and inferential interest resides with how the association pattern among these outcomes change over space. These lead to joint (multivariate) spatial process models that also accommodate non-stationary correlations among the outcomes. Direct application of such multivariate models to even moderate-sized spatial data, unfortunately, is computationally
prohibitive. Here, we discuss approaches that help overcome these inferential hurdles without sacrificing richness in underlying association structures. We propose a new class of low-rank
spatially-varying cross-covariance matrices that produce non-degenerate spatial processes and that effectively capture non-stationary covariances among the multiple outcomes. We apply our methods to a soil nutrients data collected at the La Selva Biological Station, Costa Rica. Here, interest lies in visual and statistical inference in the spatially-varying relationship among the underlying spatial processes that generate the outcomes. Our framework produces substantive inferential tools such as maps of non-stationary cross-covariances that have hitherto not been easily available for environmental scientists and researchers.
*** This is joint work with Rajarshi Guhaniyogi, Andrew Finley and Richard Kobe. ***.
Additional statistical talk will be given by Professor Sudipto Banerjee at Department of Statistics, Kansas State University on April 10th from 4:00 – 5:00 p.m. The title of his talk is “Space, Time and Gradients: Why we need them in statistical modeling for public health data”.
Abstract: Advances in Geographical Information Systems (GIS) and related software have led to a burgeoning of spatial-temporal databases. Statisticians and spatial analysts today routinely encounter situations where they seek to model relationships among variables across space and time. In recent times interest has turned to inferring about rates of change of health outcomes over space and time. Why are such questions relevant and how should we estimate them? One example considers analyzing monthly hospitalization rates aggregated over the counties in California where hospital management seeks to carry out inference on gradients of the temporal process, while at the same time accounting for spatial similarities across neighboring regions. Another example (an extension) is to analyze spatial-temporal gradients for environmental pollutants to understand the nature of dispersal of pollutants. Here, we are interested in directional rates of change over space at any given time, temporal gradients at any given location and even "mixed" gradients, e.g., how the temporal rate of change varies over space. We will work within a fully Bayesian inferential paradigm without unnecessary, and potentially inflexible, parametric modeling assumptions and obtain the full posterior predictive distribution for these gradients using process-based models.
*** This is joint work with Harrison Quick and Bradley P. Carlin. ***
Key words: Bayesian inference, Gradients, Markov random fields, Smoothness of spatial processes; Spatial-temporal processes.
Biographical sketch of Professor Sudipto Banerjee:
Dr. Sudipto Banerjee is a Professor in Division of Biostatistics at University of Minnesota. Dr. Sudipto Banerjee’s research, dissertation advising and mentoring activities focus upon statistical modeling and analysis of geographically referenced datasets, Bayesian statistics, interface between statistics and Geographical Information Systems, and statistical computing. He has published over ninety peer-reviewed journal articles, several book chapters and has co-authored a book titled "Hierarchical Modeling and Analysis for Spatial Data". In 2009 he was honored with the Abdel El Sharaawi Award from the International Environmetrics Society. In 2011 he was honored with the Mortimer Spiegelman Award from the American Association of Public Health. This award, given annually since 1970, is presented to the nation's most outstanding public health statistician under the age of 40.
Chapter Meeting Address:
Holiday Inn Manhattan at Campus
(The intersection of N. 17th Street and Anderson Avenue)
Link to Map