UCLA Department of Statistics Seminar Series
Tue, 3/11/2014, 2:00 PM—3:00 PM
2434 Physics and Astronomy Bldg.
Gary Evans
Statistics
UCLA
Logistic Gifi: A Logistic Distance Association Model for Exploratory Analysis of Categorical Data
In this work, we explore a distance association method we call Logistic Gifi, for categorical data which advances geometric data analysis techniques in much the same way that homogeneity analysis did with regard to correspondence analysis, multidimensional scaling, and general clustering methods. It uses the methods of multidimensional unfolding with a likelihood-based loss measure to create low- dimensional geometric representations of data in which distances correspond in a direct way to the probabilistic structure of the data. As with homogeneity analysis, a central feature of our method is the use of binary indicator matrices and, in some applications, fuzzy-coded (i.e., non-binary, row stochastic) indicator matrices to represent categorical data. This gives us a very versatile method with considerable flexibility in the types of data which can be analyzed. We create and study algorithms to use the method to compute low-dimensional geometric representations of various types of data. We analyze the convergence properties of this complex algorithm and show how minimal polynomial extrapolation can be used to accelerate it. We then study relationships between this logistic distance method and logit-based regressions. We present several applications of the method to visualizations of regression results as well as data types such as roll calls, social networks, and Markov chains. Finally, a version of the method with bias parameters is introduced and developed and used to emphasize features of data visualizations. We show how bias constraints can be used to represent certain types of model testing. Last, we study the stability of the method.
UCLA Statistics Faculty Search
Open-ranked faculty position (tenured or tenure track) in the Department of Statistics at the University of California, Los Angeles. We seek applicants contributing to the cutting edge development of theoretical statistics, learning theory and big data. We welcome applicants whose experience in research, teaching and service has prepared them to contribute to UCLA’s commitment to excellence and diversity. Applicants with a desire to mentor women and/or underrepresented minorities in STEM fields are encouraged to apply. Ph.D. is required by date of anticipated appointment of July 1, 2014. Salary will be commensurate with education and experience. Please refer to Tracking Job #1015-1314-02 on all correspondence.
Reviews for the position will commence on Nov 15, 2013 and will continue until a successful candidate is identified. Interested applicants should apply at UCLA Academic Recruit at:
https://recruit.apo.ucla.edu/apply/JPF00108
UCLA is an Affirmative Action/Equal Opportunity Employer with a strong institutional commitment to excellence through diversity. Women and Minorities are especially encouraged to apply.
Applicants should submit:
1) CV
2) Cover letter describing how their qualifications and interests would fit with the position description
3) Statement of research
4) Three representative publications
5) Statement of teaching
6) Three letters of recommendation
All inquiries may be sent to Chie Ryu at chie.ryu@stat.ucla.edu.
Two UCLA Statistics Faculty Win Prestigious "PAMI Helmholtz Test-of-Time Award"
Congratulations to Song-Chun Zhu and Alan Yuille who won the “PAMI Helmholtz Test-of-Time Award”. This was awarded by the IEEE PAMI Technique Committee at the International Conference on Computer Vision (ICCV) held in Sydney in December 2013. They received this honor for the paper entitled, “Region Competition: Unifying Snakes, Region Growing, and Bayes / MDL for Multiband Image Segmentation”, which they co-authored in 1996. The paper developed a new algorithm called “Region Competition” which first linked statistical models of images to partial differential equations (PDEs) for image segmentation. The paper that wins the “PAMI Helmholtz Test-of-Time Award” is one that is frequently cited by other papers in computer vision, judged to have made a powerful impact to the field and must have been published by ICCV more than a decade ago.
Inferring "Dark Matter" from Videos
Our VCLA (Vision, Cognition, Learning and Art) research group built two low cost hex rotor helicopters to take aerial videos on Sep 11, 2013 in Malibu State Park. These videos captured the motion of 15 "actors" from our group playing different roles in various activities. Designing and carrying out the activities required creativity and was a lot of fun for the participants.
In the aerial videos it is difficult to identify some objects due to view angle, distance or occlusions (without considering other cues). These unidentified objects are called “dark matter”. The purpose of this exercise was to collect data to test a novel model based on the cue of human activities in the scene. This model, proposed by Dan Xie, Sinisa Todorovic and Song-Chun Zhu, will appear in Proceedings of International Conference on Computer Vision (ICCV) 2013.
Statistics/Social Sciences Tenure Track Faculty Position
Open-ranked tenured and tenure track position, joint in the Department of Statistics and a department or departments in the Division of Social Sciences at the University of California, Los Angeles. We seek a faculty member contributing at the cutting edge to the development of statistical methodology relevant to the social sciences. We welcome candidates whose experience in teaching, research or community service has prepared them to contribute to our commitment to diversity and excellence. Duties include new course development, teaching, and methodological and collaborative research. Ph.D. required by date of anticipated appointment of July 1, 2014. Salary will be commensurate with education and experience. Please refer to Tracking Job #1015-1314-01 on all correspondence.
Reviews for the position begin October 1, 2013, and will continue until the position is filled. Interested applicants should apply at UCLA Academic Recruit at:
https://recruit.apo.ucla.edu/apply/JPF00072
Applicants should submit:
1) CV
2) Cover letter describing how their qualifications and interests would fit with the position description
3) Statement of Research
4) Statement of Teaching
5) Three letters of recommendation
For more information on the departments in the Division of Social Sciences see www.sscnet.ucla.edu.
All inquiries may be sent to Professor Mark Handcock at css@stat.ucla.edu.
UCLA is an Affirmative Action/Equal Opportunity Employer with a strong institutional commitment to excellence through diversity. Women and Minorities are especially encouraged to apply.
Announcing the R User Conference 2014 to be held from June 30 to July 3 2014 at UCLA
The annual useR! international R User conference is the main meeting of the R user and developer community. It is being held at UCLA from June 30 to July 3, 2014. Please goto http://user2014.stat.ucla.edu for more details.