Texas A&M - Labors of Lab
This installment of "Labors of Lab" features statistics Ph.D candidate Richard Payne '17, who is using Bayesian statistics -- specifically big-data classification methods -- in collaboration with Texas A&M distinguished professor of statistics Bani Mallick to make algorithms more efficient.
Texas A&M statistician Mikyoung Jun has been selected to receive the American Statistical Association's 2015 ENVR Young Investigator Award, presented by the ASA Section on Statistics and the Environment (ENVR) in honor of her outstanding contributions to statistical models and methods for geophysical applications.Read More →
Our latest Labors of Lab installment features statistics Ph.D. candidate Richard Payne '17, who is using Bayesian statistics -- specifically big-data classification methods -- in collaboration with Texas A&M distinguished professor of statistics Bani Mallick to make algorithms more efficient.Read More →
10:30 AM / 11:30 AM Blocker Building, Room 447 979-845-3143
PhD Candidate, Department of Statistics
Texas A&M University
"Statistical Methods for Large Spatial Datasets"
Gaussian process models are widely used for analyzing spatial datasets, its computational complexity however grows cubically with sample size, imposing obstacles for its applications to large spatial datasets. We propose a Smooth Full-Scale Approximation approach (SFSA) for analyzing large geostatistical datasets. It extends the FSA-Block approach (Sang et al. 2011) by correcting the approximation errors of residual covariance among neighboring data blocks. By applying the block conditional likelihood approximation to the residual likelihood, the residual covariance of neighboring blocks can be partially preserved. The proposed method inherits the merits of both the FSA-Block and the block version of the nearest neighbor Gaussian process methods. Compared with the FSA-Block approach, the SFSA approach can alleviate the prediction errors for block boundary locations. In addition, due to the additional corrections of residual covariance across data blocks, the SFSA approach is less sensitive to the knot set than the FSA-Block approach. We show that the proposed approach can result in a valid Gaussian process so that both parameter estimation and prediction can be performed in a unified framework. We illustrate the effectiveness of the proposed method through simulation studies and a precipitation dataset.
All Day Blocker Building, Room 448, daily 979-845-3143
AP Statistics Summer Institute - July 6-9, 2015
This course is designed primarily for new teachers in AP Statistics. However, experienced teachers will find many useful things to take back to their classrooms. Much of the week will be devoted to experimental design, correlation and regression, probability models, and inference. We will discuss how to organize the course and how to use technology, simulation and data-gathering activities. Time will be spent working with activities and simulations as a building block for the course. At least one morning will be allocated for working on laptops to view and use online resources and applets that are immensely useful for the course.
In addition to the binder for the week, participants will receive a flash drive, which will be loaded with lessons, worksheets/handouts, class note sheets, a set of old tests, AP practice sets, projects, and activities. Participants will review the 2015 test through the questions, rubrics and the grading of student responses.
The registration fee ($475) includes classroom materials, light lunches and snacks each day.
Consultant: Michael Legacy
Dr. James H Matis (c/o Elaine James)
Department of Statistics
College Station, TX 77843-3143
PH: (979)845-3143, FX: (979)845-3144
Full refunds will be available for cancellations made by June 15, 2015. Partial refunds may be available for cancellations up to one week before the institute begin. No refunds will be made after that time.