Robert E. Kass, Ph.D. - US grants

Our research is oriented toward implementation of Bayesian inference. There has been increasing interest recently in the Bayesian approach to statistics, in part because advances in computational ability have made it feasible in many settings, and in part because Bayesian analysis of data can make use of information from additional sources. Our work will build on our previous research in Bayesian statistics, part of which has been funded by NSF. Our main concerns are: (1) review and assessment of methods for choosing prior probability distributions by formal rules, and further development of methods for assessing sensitivity to the choices; (2) investigation of approximate and exact computational methods for Bayesian hypotheses testing; (3) modification and enhancement of numerical integration techniques and Monte Carlo simulation of posterior distributions; also, improvement of statistical computing environments including use of animation and three dimensional rendering for visualization of uncertainty in higher dimensions; (4) further work on the foundations of subjective probability; and (5) several other topics related to our previous work on elicitation of priors and asymptotic approximations. When analyzing data, it is important to combine all sources of information effectively. Bayesian statistical methods are tailored to this purpose. Our research focuses on finding practical ways to implement Bayesian methods and on investigating the theoretical basis for these methods. We are concerned with the development of computational and graphical techniques that make Bayesian inference feasible in complicated problems. These include: simulation, animation and the construction of statistical computing environments. We will also investigate theoretical issues that support Bayesian techniques. These issues include the foundations of subjective probability and the development of mathematical approximations.

This workshop will contribute to developments in both practical and theoretical statistics. Its contributions to practice will be dissemination of experience in applying Bayesian methods and the identification of specific theoretical and implementation tools that can aid in the convenient, routine use of Bayesian methods. It will contribute to theory by providing a collection of concrete, contextually grounded research problems in the light of which actual and potential theoretical developments can be examined. The workshop will be held in September, 1991 at Carnegie- Mellon University. It will include those who use and develop statistical theory and methods, and several applications will be presented in length, with a thematic focus on the contribution of the Bayesian theory of statistics. This conference has the potential for great impact in the field of statistics. Bringing together good statistical theory and computing power to solve a real problem is the direction of future research.

DESCRIPTION: (Adapted from the Applicant's Narrative) A symposium entitled "Bayesian Statistics in Science and Technology:Case Studies II" will be held at Carnegie-Mellon University in Pittsburgh, Pennsylvania, on Saturday, October 9, 1993 through Monday, October 11, 1993. The symposium will include three extended presentations of applications of Bayesian methods in problems in which the statistician was an integral member of the research team and the statistical methods were an important part of the research. Two contributed poster sessions will also be held. The objectives of the symposium are to: identify and focus attention on specific implementation and theoretical problems that hinder applications of Bayesian methods, and to identify candidate solutions; provide a forum in which the interplay between statistical theory and practice will be explored in the context of concrete research projects; and produce a book containing well-documented case studies and data sets suitable for use in teaching applied statistics. The applicants plan to have a common theme for the invited papers. Three abstracts on proposed biomedical topics have already been received. A call for both invited and contributed papers is being issued to the general statistical community. Papers will be selected by the organizers based on appropriateness to the goals of the workshop and, in the case of the invited papers, commonality of theme.

As increasingly much background information becomes available to scientists undertaking an investigation, it is important to utilize previous knowledge effectively in designing studies and analyzing data. Bayesian statistical methods are tailored to this computation, but scientific meetings rarely spend substantial time discussing applications of Bayesian statistics. The goal is to elucidate the interplay between theory and practice and thereby identify successful methods and indicate important directions for future research.

Symposium on Case Studies in Bayesian Statistics Robert E. Kass Carnegie Mellon University A symposium entitled ``Case Studies in Bayesian Statistics 4'' will be held at Carnegie-Mellon University in Pittsburgh, Pennsylvania, on Friday September 26 and Saturday September 27, 1997. The symposium will include four extended presentations of applications of Bayesian methods to a range of medical and industrial applications. More specifically, topics of the selected presentations inalude: modeling for risk of breast cancer, pharmacokinetic modeling in drug development, problems of customer value analysis, and statistical aspects of functional MRI. In these applications the statistician was an integral member of the research team. A contributed poster session will also be held. The objectives of the symposium are to: (i) identify and focus attention on specific implementation and theoretical problems that hinder applications of Bayesian methods, and to identify candidate solutions; (ii) provide a forum in which the interplay between statistical theory and practice will be explored in the context of concrete research projects; (iii) provide a small-meeting atmosphere within which junior investigators and graduate students can explore substantial Bayesian applications with experienced researchers; and (iv) produce a volume containing well-documented case studies and data sets suitable for use by researchers, practitioners, educators and students of applied statistics and other quantitative fields. As increasingly much background information becomes available to scientists undertaking an investigation, it is important to utilize previous knowledge effectively in designing studies and analyzing data. Bayesian statistical methods are tailored to this purpose. There have been many recent advances in Bayesian statistical theory and computation, b ut scientific meetings rarely spend substantial time discussing applications. The purpose of this symposium is to concentrate attention solely on applications of Bayesian statistics. The goal is to elucidate the interplay between theory and practice and thereby identify successful methods and indicate important directions for future research.

A symposium entitled "Bayesian Statistics in Science and Technology: Case Studies IV" will be held at Carnegie-Mellon University in Pittsburgh, Pennsylvania, on Friday, September 26 and Saturday, September 27, 1996. The symposium will include four extended presentations of applications of Bayesian research team. A contributed poster session will also be held. the objectives of the symposium are to: (I) Identify and focus attention on specific implementation and theoretical problems that hinder applications of Bayesian methods, and to identify candidate solutions; II) Provide a forum in which the interplay between statistical theory and practice will be explored in the context of concrete research projects; (III) Provide a small-meeting atmosphere within which junior investigators and graduate students can explore substantial Bayesian application with experienced researchers; and (IV) Produce a volume containing well-documented case studies and data sets suitable for use by researchers, practitioners, educators and students of applied statistics and other quantitative fields. As increasingly much background information becomes available to scientists undertaking an investigation, it is important to utilize previous knowledge effectively in designing studies and analyzing data. Bayesian statistical methods are tailored to this purpose. There have been many recent advances in Bayesian statistical theory and computation, but scientific meetings rarely spend substantial time discussing applications. The purpose of this symposium is to concentrate attention solely on applications of Bayesian statistics. the goal is to elucidate the interplay between theory and practice and thereby identify successful methods and indicate important directions for future research.

9803433
Robert E. Kass

This research is focused on reference Bayesian methods (Bayesian inference with prior distributions chosen by some formal rule), mixture models, Bayes factors, and causal inference, with an emphasis on hierarchical models (including classical mixed models and their generalizations). Both parametric and nonparametric or semiparametric models are studied. Many of the results are obtained by asymptotic methods, but ``exact'' computation (typically via simulation) also play a substantial role.

Elaboration of simple statistical models has been a major theme in the discipline in the latter part of this century. Previously, models have involved a small number of parameters, the values of which have been determined from observed data. With increased computing power, more complicated statistical models involving many more parameters have become central to much current statistical activity. Yet, despite recent progress, fundamental issues remain. This research is motivated in part by problems in statistical genetics, cognitive neuroscience, and the study of criminal behavior.

9720354 Lovett This project is being funded by the Learning and Intelligent Systems (LIS) Initiative, including support from the Office of Multidisciplinary Activities of the Directorate for Mathematics and Physical Sciences. This project will develop the three core components of an innovative, intelligent learning environment for teaching statistical reasoning. It is aimed at directly facilitating students' ability to transfer what they have learned to situations outside the original learning context. The three components are (1) a computer interface that helps students develop a general understanding, (2) a detailed specification of the knowledge required to apply statistical reasoning effectively, and (3) new computational and statistical techniques for assessing the accuracy and generality of students' knowledge and then generating appropriate remediation. This project entails a unique collaboration among cognitive psychologists, statisticians, and computer scientists. This project will lead to fundamental advances on several fronts. First, the interface provides a new learning tool that will be used by every humanities and social sciences student at Carnegie Mellon University and will be disseminated to other colleges. Second, because the interface is designed to apply the principles revealed by recent cognitive psychology research, it offers a test of these principles' effectiveness in practice. Third, developing a detailed specification of the knowledge required for statistical reasoning will yield new insights that can inform statistics instruction and cognitive theories. Fourth, the techniques for assessing students' knowledge develop new ways of using the information recorded by computerized learning environments. Fifth, the rich data collected on students' transfer throughout this project will lead to a deeper understanding of how, when, and why transfer occurs. Statistical reasoning is the domain for this project because (a) effective transfer is critical here--stude nts must apply the skills they have learned across a wide range of issues and content areas, and (b) students often have great difficulty transferring these skills.

The symposium ``Case Studies in Bayesian Statistics 4'' will be held at Carnegie Mellon University on Friday September 24 and Saturday September 25, 1999.

The symposium will include three extended presentations of applications of Bayesian methods. In these applications the statistician has been an integral member of the research team. Two contributed poster sessions will also be held. The objectives of the symposium are to:
(i) identify and focus attention on specific implementation and theoretical problems that hinder applications of Bayesian methods, and to identify candidate solutions;
(ii) provide a forum in which the interplay between statistical theory and practice will be explored in the context of concrete research projects;
(iii) provide a small-meeting atmosphere within which junior investigators and graduate students can explore substantial Bayesian applications with experienced researchers; and
(iv) produce a volume containing well-documented case studies
and data sets suitable for use by researchers, practitioners, educators and students of applied statistics and other quantitative fields.

As increasingly much background information becomes available to scientists undertaking an investigation, it is important to utilize previous knowledge effectively in designing studies and analyzing data. Bayesian statistical methods are tailored to this purpose. There have been many recent advances in Bayesian statistical theory and computation, but scientific meetings rarely spend substantial time discussing applications. The purpose of this symposium is to concentrate attention solely on applications of Bayesian statistics. The goal is to elucidate the interplay between theory and practice and thereby identify successful methods and indicate important directions for future research.

9819900
Eddy

At Carnegie Mellon University, the Department of Statistics and the Department of Mathematical Sciences will build on their complementary strengths to develop a joint, vertically-integrated program of education and research. Responding to national needs, the program will (i) train postdoctoral fellows for careers emphasizing research in settings that require versatility, (ii) aim to recruit and retain U.S. graduate students, avoiding excessive time to complete Ph.D.s while providing students with a high probability of success after graduation, and (iii) help increase the numbers of U.S. undergraduates, including women and minorities, who pursue advanced degrees in mathematical and statistical sciences. The program emphasizes cross-disciplinary research and understanding the needs of learners in a context of disciplinary advancement. Many of the activities grow from two previously-funded Group Infrastructure Grants to our respective departments, and from a very successful Undergraduate Summer Research Institute in Applied Mathematics. For instance, we plan to use the graduate support model from the infrastructure grant to Mathematical Sciences, we will expand the operation of the Summer Institute to include students from Statistics, and we will adapt for Mathematical Sciences some of the postdoctoral mentoring procedures that have worked well in Statistics.

Our evaluation of this training program will assess the following:
involvement of undergraduates in meaningful research experiences; its success in producing acceptable average time-to-degree for VIGRE graduate trainees; its effectiveness in expanding the mathematical horizons and career opportunities of students at both the undergraduate and the graduate levels, with particular focus on the graduate program; its effectiveness at the postdoctoral level in preparing VIGRE postdoctoral fellows for careers as professional mathematical scientists; its effectiveness in developing the communications skills of VIGRE participants; the effectiveness of the mentoring of undergraduate students, graduate trainees, and postdoctoral fellows; overall effectiveness of the research teams and other efforts to integrate research and education; the effectiveness of the partnership-in-training between the Departments of Statistics and Mathematical Sciences; and the degree of involvement of women and minorities.

Funding for this award is provided by the Division of Mathematical Sciences and the MPS Directorate's Office of Multidisciplinary Activities.

Failure to learn hidden skills is a persistent obstacle to students in science, math, and engineering domains. Hidden skills, which include problem categorization, feature detection, and planning, are critical to solving problems in a domain but do not have any immediate, external product for students to see. Unfortunately, it is unclear how best to identify and teach these difficult-to-learn skills. Instructional scaffolding is a popular and effective technique for providing targeted support and guidance while students learn to solve problems in a new domain. Scaffolding has great potential for improving hidden-skill learning. However, the reasons it works and how best to implement it are largely unknown.

The proposed research will explain the effectiveness of instructional scaffolding in terms of hidden skill learning. Several hypotheses about the relationship between scaffolding and hidden skills will be tested, and new scaffolding designs will be evaluated. This will lead to a systematic approach to teaching hidden skills that improves students' learning and transfer. The four specific aims of this project are:
(1) Develop a systematic, efficient method for identifying hidden skills. While methods currently exist for analyzing domain-specific knowledge, these methods are not robust for identifying hidden skills, and they tend to be difficult and slow. This project will develop and test an automated method that combines logistic regression models and heuristic search algorithms to infer where hidden skills lie.
(2) Develop a theoretical explanation for why scaffolding works. Although instructional scaffolds often lead to better learning, there has been little theoretical progress in explaining when and how scaffolding works. A sequence of experiments will be conducted to test three hypotheses that offer increasingly concrete levels of explanation for how scaffolding benefits learning and transfer.
(3) Develop practical guidelines for the design of effective instructional scaffolding. Three critical questions for scaffolding design will be examined: What level of scaffolding support is sufficient to achieve its main benefit? When and how should scaffolding support be built and faded? And how can human instructors (i.e., TA's) best complement a computerized scaffolded learning environment?
(4) Develop novel applications of our results on scaffolding hidden skills. There are at least two novel applications of this work, beyond the scope of learning theory and instructional design. First, the scaffolding designs from Specific Aim 3 will be used to develop new on-line assessments of students' understanding. Second, the results from Specific Aim 1 will be used to develop tools that train instructors to "see" the hidden skills in complex problems and thus better anticipate students' learning difficulties.

[unreadable] DESCRIPTION (provided by applicant): Much current neurophysiological research concerns the way neuronal activity evolves over time. For static characterizations, standard statistical tools such as Analysis of Variance suffice, but for dynamic studies there is a large neuroscientific payoff for using state-of-the-art, special-purpose statistical methods. In addition, a major relatively new direction for the field involves the use of multielectrode recording. Multielectrode neuronal recording has not only produced new scientific insights, it has also led to development of neural prostheses via brain-computer interface, which are likely to have important clinical applications. There is a widespread perception that there are not yet adequate tools for understanding dynamic responses available from current recording technologies. From a statistical point of view it is natural to view neuron firing events (spike trains) as defining point processes. While there exist rich theory and methods for stationary point processes, nonstationarity is common. Many neurophysiological experiments use time-varying stimuli and produce time-varying responses. Furthermore, there are interesting physiological phenomena that evolve across experimental trials. Thus, statistical methods for the analysis of single and multiple nonstationary point process data are urgently needed. The research to be conducted under this grant emphasizes statistical modeling and inference for point processes, Bayesian sequential modeling, and clustering of functions. Specific aims involve functional data analysis of trial-averaged firing rates; non-Poisson modeling of spike trains for within-trial analysis; multivariate point process modeling of dependency among multiple spike trains; variable clustering methods for identifying clusters of correlated neurons; particle filtering and related methods for decoding of motor cortical signals; and functional goal-oriented clustering for spike sorting in the context of decoding. [unreadable] [unreadable]

Complex Statistical Models: Theory and Methodology
for Scientific Applications

Larry Wasserman, Christopher Genovese, Robert E. Kass
and Kathryn Roeder

ABSTRACT

This project is aimed at developing statistical theory and methodology for highly complex, possibly infinite dimensional models. Although the methodology and theory will be quite general, we will conduct the research
in the context of three scientific collaborations. The first is ``Characterizing Large-Scale Structure in the Universe,'' a joint project with astrophysicists and computer scientists. The main statistical challenges are nonparametric density estimation and clustering, subject to highly non-linear constraints. The second project is ``Locating Disease Genes with Genomic Control.'' We aim to locate regions of the genome with more genetic similarity among cases (subjects with disease) than controls. These regions are candidates for containing disease genes. Finding these regions ina statistically rigorous fashion requires testing a vast number of hypotheses. We will extend and develop recent techniques for multiple hypothesis testing.
The third projects is ``Modeling Neuron Firing Patterns.'' The goal is to construct and fit models for neuron firing patterns, called spike trains. The data consist of simultaneous voltage recordings of numerous neurons which have been subjected to time-varying stimuli. The data are correlated over time and a major effort is to develop a class of models, called inhomogeneous Markov interval (IMI) process models, which can adequately represent the data.

Statistical methods for simple statistical models with a small number of parameters are well established.
These models often do not provide an adequate representation of the phenomenon under investigation.
Currently, scientists are deluged with huge volumes of high quality data. These data afford scientists the opportunity to use very complex models that more faithfully reflect reality. The researchers involved in this proposal are developing methodology and theory for analyzing data from these complex models. The methods are very general but they are being developed for applications in Astrophysics, Genetics and Neuroscience.

DESCRIPTION: (provided by applicant) A symposium entitiled "Bayesian Statistics in Science and Technology: Case Studies VI" will be held at Carnegie-Mellon University in Pittsburgh, Pennsylvania, on Friday September 28 and Saturday September 29, 2001. The symposium will include two extended presentations of applications of Bayesian methods in problems in which the statistician was an integral member of the research team, and one case study of statistical methods analyzed by a panel of three experts. Two contributed poster sessions will also be held. The objectives of the symposium are to: (i) Highlight the close interplay of statistical theory and applications in the context of substantive scientific research. (ii) Contribute to the development of Bayesian statistics, by identifying problems without standard solution, and encouraging the extension of the theory and its implemtation so that posible approaches to analyses may be found. (iii) Bring to the fore the topic of reporting of Bayesian statistical analyses to the scientific community, and discuss effective and relevant means of communicating both the methods used in, and the conclusions drawn from quantitative analyses. (iv) Provide a small meeting atmosphere for young researchers and graduate students to present their work and to interact with senior colleagues, and to learn about the recent advances in implementation of Bayesian methods in substantive problems. (v) Encourage the collaboration between statisticians and researchers in subject matter disciplines, by emphasizing the many challenging statistical problems that arise in the course of scientific research. (vi) Disseminate the results of the research presented at the workshop by publishing a volume containing well-documented and peer-reviewed case studies and data sets, and other selected workshop presentations. As increasingly much background information becomes available to scientists undertaking an investigation, it is important to utilize previous knowledge effectively in designing studies and analyzing data. Bayesian statistical methods are tailored to this purpose. There have been many recent advances in Bayesian statistical theory and computation, but scientific meetings rarely spendsubstantial time discussing applications. The purpose of this symposium is to concentrate attention solely on applications of Bayesian statistics. The goal is to elucidate the interplay between theory and practice and thereby identify sucessful methods and indicate important directions for future research.

A symposium entitled "Bayesian Statistics in Science and Technology: Case Studies VI" will be held at Carnegie-Mellon University in Pittsburgh, Pennsylvania, on Friday September 28 and Saturday September 29, 2001. The symposium will include two extended presentations of applications of Bayesian methods in problems in which the statistician was an integral member of the research team, and one case study of statistical methods analyzed by a panel of three experts. Two contributed poster sessions will also be held. The objectives of the symposium are to (i) Highlight the close interplay of statistical theory and applications in the context of substantive scientific research, (ii) Contribute to the development of Bayesian statistics, by identifying problems without standard solution, and encouraging the extension of the theory and its implementation so that possible approaches to analyses may be found. (iii) Bring to the fore the topic of reporting of Bayesian statistical analyses to the scientific community, and discuss effective and relevant means of communicating both the methods used in, and the conclusions drawn from quantitative analyses. (iv) Provide a small meeting atmosphere for young researchers and graduate students to present their work and to interact with senior colleagues, and to learn about the recent advances in implementation of Bayesian method in substantive problems. (v) Encourage the collaboration between statisticians and researchers in subject mater disciplines, by emphasizing the many challenging statistical problems that arise in the course of scientific research. (vi) Disseminate the results of the research presented at the workshop by publishing a volume containing well-documented and peer-reviewed case studies and data sets, and other selected workshop presentations.

As increasingly much background information becomes available to scientists undertaking an investigation, it is important to utilize previous knowledge effectively in designing studies and analyzing data. Bayesian statistical methods are tailored to this purpose. There have been many recent advances in Bayesian statistical theory and computation, but scientific meetings rarely spend substantial time discussing applications. The purpose of this symposium is to concentrate attention solely on applications of Bayesian statistics. The goal is to elucidate the interplay between theory and practice and thereby identify successful methods and indicate important directions for future research.

Proposal ID: DMS-0307616
PI: Robert E Kass
Title: VII Symposium of Case Studies in Bayesian Statistics

Case Studies in Bayesian Statistics VII is the seventh workshop in the series that was begun in 1991. The workshops are held in odd years at Carnegie Mellon University in early fall. The seventh workshop is planned for September 12-13, 2003. The goals of the workshop are to
(i) emphasize the close interplay of statistical theory and applications in the context of substantive scientific research;
(ii) promote the continued development of Bayesian statistics, by highlighting problems in the sciences that require non-standard approaches, thereby requiring theoretical and methodological developments for their solution;
(iii) provide an opportunity for scientists and statisticians to present their work in depth, highlighting both the scientific background and the analytical approaches, for the benefit of the audience;
(iv) encourage young researchers and graduate students to present their work, interact with senior colleagues, learn about the latest developments in Bayesian statistics, and participate in discussions, by providing a small-meeting atmosphere;
(v) highlight the many research opportunities that exist for statisticians who engage in interdisciplinary work;
(vi) include as participants women and under-represented minorities who might benefit from the small workshop environment and the opportunities for one-on-one discussions with colleagues at other institutions;
(vii) disseminate the findings presented at the workshop by publishing a volume or special issue of a journal containing well-documented and peer-reviewed case studies and related workshop presentations, and by posting the same information on the workshop's web pages (www.stat.cmu.edu/bayesworkshop).

At Carnegie Mellon University, the VIGRE program of the Department of Statistics will involve all trainees in supervised, cross-disciplinary research, where they will learn how to translate a research question into well-posed statistical problems, solve these problems, and translate the results back into a product that is accessible to the relevant scientific community. This skill is also central to learning basic statistics and forms a conceptual link between research and education, facilitating their integration. At the graduate level experience in the process includes a year-long project, typically with a faculty member in another domain, while a Statistics faculty member serves as advisor; provides a series of steps to improve communication skills and teaching effectiveness, and mentors in the area of professional growth. The graduate curriculum will be modified to make it more effective in building cross-disciplinary skills. Undergraduates will have several new courses available and will be involved in a capstone research project, and we will run a summer program, emphasizing minority students. Postdoctoral fellows will be involved in research projects, and will co-teach courses with senior faculty. They will also participate in structured mentoring sessions.

Undergraduate, graduate, and postdoctoral trainees will be integrated in research teams. The Carnegie Mellon VIGRE program in Statistics will (i) train postdoctoral fellows for careers emphasizing research in settings that require versatility, (ii) recruit and retain U.S. graduate students, avoiding excessive time to complete Ph.D.s while providing students with a high probability of success after graduation, and (iii) help increase the numbers of U.S. undergraduates, including women and minorities, with advanced training in statistical science. While maintaining a strong disciplinary foundation for statistical practice, the program emphasizes cross-disciplinary research and understanding the needs of statistical novices.

The Principal Investigator will spend the 2004-2005 year studying neuroscience at Pittsburgh's Center for the Neural Basis of Cognition (CNBC), which is operated jointly by the University of Pittsburgh and Carnegie Mellon The plan is (i) to acquire the scientific knowledge contained in four CNBC graduate courses, (ii) to get experience with some basic experimental methods, (ii) to join reading groups and attend seminars, and (iv) to attend scientific meetings, and make special trips when necessary in order to meet key researchers in the field..

The Department of Statistics at Carnegie Mellon University will
purchase a cluster of computers dedicated to the support of
statistical research in a number of applied and theoretical areas.
In addition to advancing science in the applied areas, knowledge of
how to use the parallel processing cluster for statistical research will
disseminate through education of students and visitors and through
postings of algorithms on StatLib, the public repository of data and
software.

The areas of application include estimating uncertainty about the
cosmic microwave background radiation, estimating the signal from in
vivo neuroimages, identifying which genes are related to complex
diseases, and learning how neurons control movement to help develop
brain-controlled prosthetics. Each of these areas is currently being
pursued by faculty and students in the Department, and they will all
benefit from the increased computing capabilities provided by the new cluster.
The statistical research directed toward each of the applications
will produce methodology that will be useful in other areas of science
as well.

Case Studies in Bayesian Statistics VIII is the eighth workshop in the
series that was begun in 1991. These workshops aim to advance
statistical practice by examining Bayesian methods in specific applied
contexts. The workshops are held in odd years at Carnegie Mellon
University in early fall. The eighth workshop is planned for September
16--17, 2005.

The objectives of the workshop, "Case Studies in Bayesian Statistics
VIII" is are to explore the interplay of statistical theory and
practice in the context of substantive scientific research; to promote
the continued development of Bayesian statistics by highlighting
problems in the sciences that require non-standard approaches; to
provide an opportunity for scientists and statisticians to present
their work in depth, highlighting both the scientific background and
the analytical approaches; and to encourage dissemination of the
findings presented at the workshop via well-documented and
peer-reviewed case studies. As it has evolved, this workshop series
has become an important meeting for younger researchers in Bayesian
statistics. The workshop aims to encourage young researchers,
including graduate students, to present their applied work; provide a
small meeting atmosphere to facilitate the interaction of young
researchers with senior colleagues; expose young researchers to
important challenges and opportunities in collaborative research; and
include as participants women, under-represented minorities and
persons with disabilities who might benefit from the small workshop
environment.

DESCRIPTION (provided by applicant): Multiple-electrode neuronal recording has created tremendous new opportunities for gaining insight into the neural substrate of behavior, and it has made possible the construction of brain-controlled robotic devices. A crucial problem is to describe evolution of neuronal activity during learning, which is of interest not only from the point of view of basic science, but also because knowledge of the changes that occur while a subject learns a task is necessary for the construction of reliable neural prosthetic algorithms. This research will develop and adapt statistical methods for analysis of multiple-electrode data from a series of experiments aimed at understanding the evolution of cortical activity in several areas of the brain while a monkey learns hand movement tasks. The results will lead to improvements in brain-controlled robotic devices for neural prostheses and, thus, will likely benefit people paralyzed by head or spinal cord trauma, amputees, and those with severe deficits caused by diseases such as stroke, amyotrophic lateral sclerosis, cerebral palsy, or multiple sclerosis.

[unreadable] DESCRIPTION (provided by applicant): Case Studies in Bayesian Statistics VHI and IX are the eighth and ninth workshops in the series that was begun in 1991. The workshops are held in odd years in Carnegie Mellon University in early fall. The eighth workshop is planned for September 16-17, 2005, and the ninth is planned for September 28-29, 2007. The highest level goal of the workshop series is to advance statistical practice by examining Bayesian methods in specific applied contexts. Because biomedical problems typically make up a large portion of the case studies at the conference and much of the methodology is applicable to cancer studies, we are seeking the support of NCI again this year. The specific objectives of the workshop are to [unreadable] (1) explore the interplay of statistical theory and practice in the context of substantive scientific research; [unreadable] (2) promote the continued development of Bayesian statistics by highlighting problems in the sciences that require non-standard approaches; [unreadable] (3) provide an opportunity for scientists and statisticians to present their work in depth, highlighting both the scientific background and the analytical approaches; [unreadable] (4) encourage young researchers, including graduate students, to present their applied work; [unreadable] (5) provide a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues; [unreadable] (6) expose young researchers to important challenges and opportunities in collaborative research; [unreadable] (7) include as participants women, under-represented minorities and persons with disabilities who might benefit from the small workshop environment; [unreadable] (8) encourage dissemination of the findings presented at the workshop via well-documented and peer reviewed case studies. [unreadable] [unreadable] [unreadable]

In 2002, the first international conference ""Statistical Analysis of Neuronal Data (SAND)" brought together a small number of experimental neuroscientists, and theoreticians (statisticians, computer scientists, physicists and applied mathematicians) who were interested in quantitative analysis of neural data. The second conference, SAND2, was held in 2004. Both were in Pittsburgh, PA, at the joint Carnegie Mellon and University of Pittsburgh Center for the Neural Basis of Cognition. The third and fourth SAND workshops will take place during the Spring of 2006 and 2008. The specific objectives of the workshops are to define important problems in neuronal data analysis and useful strategies for attacking them; foster communication between experimental neuroscientists and those trained in statistical and computational methods; encourage young researchers, including graduate students, to present their work; expose young researchers to important challenges and opportunities in this interdisciplinary domain, while providing a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues; include as participants women, under-represented minorities and persons with disabilities who might benefit from the small workshop environment; encourage dissemination of the findings presented at the workshop via a set of peer-reviewed articles.

[unreadable] DESCRIPTION (provided by applicant): Neuroscience increasingly requires the integration of sophisticated experimental and quantitative approaches. The development of increasingly sophisticated models and the analysis of massive sources of data routinely push neuroscientists to the limits of their quantitative and analytical abilities. In this way, computational neuroscience has become an element of the mainstream of neuroscience research. However, few training programs have adapted to this increase in the importance of quantitative approaches in neuroscience, leaving many students under prepared to exploit future opportunities in the field. Here we propose training programs involving faculty from more than ten departments at Carnegie Mellon University and the University of Pittsburgh that seek to move computational neuroscience into the mainstream of the field. Specifically, we seek to: 1) expose hundreds of undergraduate students in biomedical fields and hundreds of students in quantitative disciplines to computational neuroscience each year. 2) develop a comprehensive research and education program that provide excellent in depth training in computational neuroscience to 10-15 undergraduates from a variety of disciplines each year 3) develop and extend the training of our graduate students to include substantial additional education in computational neuroscience and 4) expose a group of a dozen talented students primarily from other institutions to training and research in computational neuroscience. This last group of students will consist mostly of students from groups underrepresented in the field of computational neuroscience. The training will be broad and interdisciplinary including biological and psychological approaches on the experimental side and statistical, computational and mathematical on the quantitative side. [unreadable] [unreadable] [unreadable]

Studies of the neural basis of behavior typically use time-varying stimuli and produce time-varying neuronal responses. Statistically, the setting involves both continuous multiple time series and inhomogeneous point processes, sometimes dozens or hundreds of them observed simultaneously. There are many challenging analytical issues, including that of combining information obtained from multiple modalities (EEG, fMRI, MEG, and extracellular recordings). The third workshop Statistical Analysis of Neuronal Data will be devoted to discussion of these issues.

The Statistical Analysis of Neuronal Data (SAND) workshops are held in even years in Pittsburgh, PA. The third workshop is planned for May 11--13, 2006. SAND3 will bring together neurophysiologists, statisticians, physicists, and computer scientists who are interested in quantitative analysis of neuronal data. In addition to four scientific sessions, we will run a pair of half-day short courses to provide relevant background on neurophysiological data, for statisticians, and in state-of-the-art statistics for experimentalists. This workshop series aims to define important problems in neuronal data analysis and useful strategies for attacking them; foster communication between experimental neuroscientists and those trained in statistical and computational methods encourage young researchers, including graduate students, to present their work; expose young researchers to important challenges and opportunities in this interdisciplinary domain, while providing a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues.

Statistical Analysis of Neuronal Data (SAND4) is a workshop devoted to defining important problems in neuronal data analysis and useful strategies for attacking them. The conference will display novel statistical methods in the context of substantive neuroscientific research, and will highlight problems that require new statistical approaches. Throughout the conference an attempt will be made to discuss the interplay of statistical theory and practice. There will be 5 scientific sessions, at which 9 senior investigators and 16 junior investigators will speak. There will also be a poster session. A special issue of the Journal of Computational Neuroscience is planned for publication of selected papers from the conference.

Statistical Analysis of Neuronal Data (SAND4) is the fourth international workshop in the series that began in 2002. The workshops are held in even years at Carnegie Mellon University during the Spring. The fourth workshop will occur May 29-31, 2008. SAND4 will bring together neurophysiologists, statisticians, physicists, computer scientists, and engineers who are interested in quantitative analysis of neuronal data. This workshop series aims to foster communication between experimental neuroscientists and those trained in statistical and computational methods; and to provide further dissemination of the findings presented at the workshop via a set of peer-reviewed articles. Secondary objectives are to encourage young researchers, including graduate students, to present their work; expose young researchers to important challenges and opportunities in this interdisciplinary domain, while providing a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues; and include as participants women, under-represented minorities and persons with disabilities who might benefi from the small workshop environment.

? DESCRIPTION (provided by applicant): Much mental health research uses neurophysiological measurements to describe the way neural activity within and across brain regions is related to behavioral function and dysfunction. One kind of signal, known as spike trains, comes from individual neurons. Other signals, including local field potentials (LFPs), electroencephalography (EEGs), and magnetoencephalography (MEG) are based on activity from large numbers of neurons within specified parts of the brain. With all of these sources of data, scientifically rigorous statistical analysis must accommodate unstable fluctuations, associated with movement or thought, known in statistics as non-stationary. The continuing research program of this grant is to develop methods for analyzing non-stationary neural data. The number of neural signals that can be recorded simultaneously has been increasing rapidly. Because neural network dysfunction is widely considered to be associated with psychopathology, improvements in recording technologies offer exciting opportunities. They also create big statistical challenges due to greatly increased complexity. The research in this grant aims to provide methods for analyzing the ways that network structure may change with particular variables, including those that help characterize behavior, which involves the transmission of neural information at multiple timescales. Fast timescales include oscillations and neural synchrony, which could provide an essential mechanism of neural network information flow and may be a marker that distinguishes normal from diseased states. At slower timescales there is considerable redundancy in the recorded signals, which suggests dimensionality reduction. New methods investigated in this research program can accommodate both faster and slower timescales, and they can also accommodate relationships arising from the spatial configuration of electrodes that record neural signals. These methods are tailored to handle spike trains, LFP, and MEG data, especially as they might arise in experiments related to mental health research. Because a neural spike train is a set of times at which a neuron fired, it is common to consider it to be a point process, which is the statistical model set up to handle sequences of event times. The research supported by this grant concerns development and investigation of statistical techniques involving both multi-dimensional continuous time series (for LFP, EEG, and MEG data) and multi-dimensional point processes (for spike trains).

The workshop Statistical Analysis of Neuronal Data (SAND5) is planned for May 20-22, 2010. SAND5 will bring together neurophysiologists, statisticians, physicists, and computer scientists who are interested in quantitative analysis of neuronal data. There will be 5 scientific sessions, at which 8 keynote investigators and 16 junior investigators will speak. There will also be a poster session. Selected papers will be published in the Journal of Computational Neuroscience.

Statistical Analysis of Neuronal Data is the fifth workshop in a series that began in 2002. The workshops are held in even years at Carnegie Mellon University during the Spring. The primary objectives of the workshop are to define important problems in neuronal data analysis and useful strategies for attacking them; foster communication between experimental neuroscientists and those trained in statistical and computational methods; and provide further dissemination of the findings presented at the workshop via a set of peer-reviewed articles. Secondary objectives are to encourage young researchers, including graduate students, to present their work; expose young researchers to important challenges and opportunities in this interdisciplinary domain, while providing a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues; and include as participants women, under-represented minorities and persons with disabilities who might benefit from the small workshop environment.

DESCRIPTION (provided by applicant): The Statistical Analysis of Neural Data (SAND) meetings have become a principal forum for discussion and study of data analytic techniques in neuroscience. They are held in even years in Pittsburgh, PA. The fifth workshop is planned for May 20-22, 2010 and the sixth for May 31-June 2, 2012. SAND5 and SAND6 will bring together experimental neuroscientists, computer scientists, statisticians, engineers, and physicists who are interested in quantitative analysis of neuronal data. This workshop series aims to define important problems in neuronal data analysis and useful strategies for attacking them;foster communication between experimental neuroscientists and those trained in statistical and computational methods encourage young researchers, including graduate students, to present their work;and expose young researchers to important challenges and opportunities in this interdisciplinary domain, while providing a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues. PUBLIC HEALTH RELEVANCE: Major advances in recording and imaging technologies have put into the hands of investigators wonderful tools for conducting previously unimagined experiments, yielding rich data sources that can shed new light on basic neuroscience and its clinical implications. The data sets are, however, often large and complex, so that novel methods of analysis are needed if the wealth of new information is to be turned into useful knowledge. The Statistical Analysis of Neural Data (SAND) meetings will continue to push neuroscience forward by encouraging young computationally-oriented researchers and by improving communication and dissemination of relevant results.

Statistics curricula have required excessive up-front investment in statistical theory, which many quantitatively-capable students in ``big science'' fields initially perceive to be unnecessary. A training program at Carnegie Mellon will expose students to cross-disciplinary research early, showing them the scientific importance of ideas from statistics and machine learning, and the intellectual depth of the subject. Graduate students will receive instruction and mentored feedback on cross-disciplinary interaction, communication skills, and teaching. Postdoctoral fellows will become productive researchers who understand the diverse roles and responsibilities they will face as faculty or members of a research laboratory.

The statistical needs of the scientific establishment are huge, and growing rapidly, making the current rate of workforce production dangerously inadequate. The Department of Statistics at Carnegie Mellon University will train undergraduates, graduate students, and postdoctoral fellows in an integrated program that emphasizes the application of statistical and machine learning methods in scientific research. The program will build on existing connections with computational neuroscience, computational biology, and astrophysics.Carnegie Mellon will recruit students from a broad spectrum of quantitative disciplines, with emphasis on computer science. Carnegie Mellon already has an unusually large undergraduate statistics program. New efforts will strengthen the training of these students, and attract additional highly capable students to be part of the pipeline entering the mathematical sciences.

Statistics curricula have required excessive up-front investment in statistical theory, which many quantitatively-capable students in ``big science'' fields initially perceive to be unnecessary. A research training program at Carnegie Mellon exposes students to cross-disciplinary research early, showing them the scientific importance of ideas from statistics and machine learning, and the intellectual depth of the subject. Graduate students receive instruction and mentored feedback on cross-disciplinary interaction, communication skills, and teaching. Postdoctoral fellows become productive researchers who understand the diverse roles and responsibilities they will face as faculty or members of a research laboratory.

The statistical needs of the scientific establishment are huge, and growing rapidly, making the current rate of workforce production dangerously inadequate. The research training program in the Department of Statistics at Carnegie Mellon University trains undergraduates, graduate students, and postdoctoral fellows in an integrated environment that emphasizes the application of statistical and machine learning methods in scientific research. The program builds on existing connections with computational neuroscience, computational biology, and astrophysics. Carnegie Mellon is recruiting students from a broad spectrum of quantitative disciplines, with emphasis on computer science. Carnegie Mellon already has an unusually large undergraduate statistics program. New efforts will strengthen the training of these students, and attract additional highly capable students to be part of the pipeline entering the mathematical sciences.

DESCRIPTION (provided by applicant): Case Studies in Bayesian Statistics and Machine Learning I continues in the tradition of the Case Studies in Bayesian Statistics series. The original series of workshops were held in odd years at Carnegie Mellon University in the early fall. The first edition of the new workshop will be held at Carnegie Mellon University on October 14-15, 2011. The highest level goal of the workshop series is to generate and present successful solutions to difficult substantive problems in a wide variety of areas. The specific objectives of the workshop are to 1. Present and discuss solutions to challenging scientific problems that illustrate the potential for statistical machine learning approaches in substantive research;2. Present an opportunity for statisticians and computer scientists to present applications-oriented research that changes the way that data are analyzed in scientific fields;3. Stimulate discussion of the challenges of the analysis of high-dimensional and complex datasets in a scientifically useful manner;4. Encourage young researchers, including graduate students, to present their applied work;5. Provide a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues;6. Expose young researchers to important challenges and opportunities in collaborative research;7. Include as participants women, under-represented minorities and persons with disabilities who might benefit from the small workshop environment;8. Encourage dissemination of the findings presented at the workshop via well-documented and peer- reviewed journal articles. PUBLIC HEALTH RELEVANCE: Bayesian and statistical machine learning approaches are essential for the analysis of data in the health sciences, particularly in complex diseases like cancer. The proposed workshop will highlight interesting applications of Bayesian and statistical machine learning, particularly in bioinformatics and imaging, which are relevant to cancer research and provide a venue for important collaboration amongst junior and senior researchers in statistics, computer science, and other disciplines.

This application requests renewal of support for undergraduate and graduate training programs in computational neuroscience (TPCN) at both Carnegie Mellon University (CMU) and the University of Pittsburgh (Pitt), and for a summer school in computational neuroscience for undergraduates, which will be available to students coming from colleges and universities throughout the United States. The TPCN will administered by the Center for the Neural Basis of Cognition (CNBC), an umbrella organization operated jointly by CMU and Pitt that was established in 1994 to foster interdisciplinary research on the neural mechanisms of brain function, which now comprises 107 faculty having appointments in 20 departments. Research in neuroscience is crucial for attacking the causes of neurological and mental health disorders. If the field of neuroscience is to continue its rapid advance, neuroscientists must use, understand, and develop new technologies, acquire and analyze ever larger data sets, and grapple more directly with the complexity of neurobiological systems. In this effort, widespread development and adoption of new computational methods has become essential to progress. The primary goal of TPCN programs is to help train a new generation of interdisciplinary neuroscientists with strong quantitative skills. A second goal is the incorporation of computational and data analytic principles into the field of neuroscience through enhanced training at the undergraduate and graduate level. Trainees will work in vertically integrated, cross-disciplinary research teams. Graduate students will take courses in cognitive neuroscience, neurophysiology, and systems neuroscience; they will satisfy a depth requirement in quantitative methodology of their choice (involving computer science, engineering, mathematics, and/or statistics); they will have extended experience in at least one experimental laboratory; and they will take part in journal clubs and seminars within the large Pittsburgh computational neuroscience community. Year-long undergraduates will take courses in mathematics, computer programming, statistics, and neuroscience; they will take an additional course in neuroscience or psychology and a course in computational neuroscience; and they will complete a year-long research project. In addition, they will complete the summer program. Undergraduate trainees in the summer program will sit through a series of lectures on topics in computational neuroscience, including tutorials in Matlab, statistical methods, fundamentals of differential equations, and ideas of neural coding, and will complete a research project. All trainees will receive training in responsible conduct of research. Across 5 years of funding, TPCN will support 20 NRSA graduate students, 10 non-NRSA graduate students, 30 undergraduate year-long fellows, and 60 undergraduate summer fellows.

The workshop "Modeling Neural Activity: Statisics, Dynamical Systems, and Networks (MONA)" will be held June 26-28, 2013, in Lihue, Hawaii. Computational neuroscience has grown, in distinct directions, from the success of biophysical models neural activity, the attractiveness of the brain-as-computer metaphor, and the increasing prominence of statistical and machine learning methods throughout science. This has helped create a rich set of ideas and tools associated with ``computation'' to studying the nervous system, but it has also led to a kind of balkanization of expertise. There is, especially, very little overlap between mathematical and statistical research in this area. Important breakthroughs in computational neuroscience could come from research strategies that are able to combine what are currently largely distinct approaches. A workshop "Modeling Neural activity: Statisics, Dynamical Systems, and Networks (MONA)" will be held June 26-28, 2013, in Lihue, Hawaii, with the purpose of exploring fruitful interactions of modeling ideas that come from mathematics, statistics, and biophysics. An additional purpose of the workshop is to bring together U.S. and Japanese researchers in this area. While computational neuroscience is represented strongly in both the U.S. and Japan there has been too little concrete communication and interaction between research groups across our two countries. Interaction across American and Japanese researchers should facilitate the advance of cross-disciplinary work.

Many disorders, such as ADHD, autism, and schizophrenia, as well as stroke and various neurodegenerative diseases, are thought to involve dysfunction of neural networks. Because computational neuroscience aims to supply principles for understanding the activity of individual and collective neural firing patterns, its successes can help in formulating mechanistic descriptions of pathophysiology. The workshop ``Modeling Neural Activity: Statisics, Dynamical Systems, and Networks (MONA)" is at the interface between mathematics, statistics, and neural network analysis, and has as its goal to generate new and productive lines of research.

What make a neuron become active? This question, central to our understanding of brain processes, is both a biophysical question about underlying biological mechanisms, and a statistical question about the features of incoming stimuli to which a neuron responds. The overall goal of this project is to forge a link between the biological mechanisms of neuronal activity and the computational process by which neurons encode features of incoming stimuli. More specifically, this project seeks to understand the biological underpinnings of stimulus coding by neurons.

Dynamical models of neurons that incorporate detailed information about the ion channels that these cells express provide a detailed, biophysical account of neuronal activity. These kinds of models have been used widely and can incorporate and constrain an impressive amount of biological detail. Unfortunately they provide little insight into the meaning of neuronal activity or into the kinds of computations and transformations of stimuli that neurons are performing. On the other hand, models derived from statistical approaches are able to capture the often-noisy and complex relationships between neural activity and the stimuli that a neuron receives. These models provide insight into how specific features of incoming stimuli are extracted and combined by populations of neurons.

These approaches will be combined through collaboration of a team at Carnegie Mellon University (Urban and Kass) and one at Bar-Ilan University (Korngreen) with expertise in the application of statistical and biophysical models to single neuron data. The work will focus on two neuron types that have several important features in common. Olfactory bulb mitral cells and layer 5 neocortical pyramidal cells are two classes of large neurons that receive distinct sources of input inputs onto different divisions of their elaborate dendritic trees. To forge this connection between dynamic and statistical models, this project will develop detailed biophysical models using recently described methods and extend the framework of current statistical models to allow the interpretation of the functional consequences of ion channels and their localization on specific classes of inputs. Applying these improved methods, and examining the consequences of changing biophysical properties on the ability of neurons to robustly and effectively represent stimuli will generate a novel account of the linkage because biological mechanisms and single neuron computation. A companion project is being funded by the Israel Binational Science Foundation (BSF).

The workshop Statistical Analysis of Neural Data (SAND7) will take place May 27-29, 2015, at the Center for the Neural Basis of Cognition, run jointly by the Carnegie Mellon University and the University of Pittsburgh, in Pittsburgh PA. Major advances in neural recording and imaging technologies have put into the hands of investigators wonderful tools for conducting previously unimagined experiments, yielding rich data sources that can shed new light on basic neuroscience and its clinical implications. The data sets are, however, often large and complex, so that novel methods of analysis are needed if the wealth of new information is to be turned into useful knowledge. (SAND7) will bring together euro-physiologists, statisticians, physicists, and computer scientists who are interested in quantitative analysis of neuronal data. The scientific lectures will be given by 6 keynote speakers, and 12 junior investigators. Each keynote lecture will be followed by an invited discussion of the topic. There will also be a poster session. Authors will be encouraged to submit papers to the Journal of Computational Neuroscience.

SAND7 is the seventh workshop in a series that began in 2002. The objectives of the workshop are to define important problems in neuronal data analysis and useful strategies for attacking them; foster communication between experimental neuroscientists and those trained in statistical and computational methods; and provide further dissemination of the findings presented at the workshop via a set of peer-reviewed articles. Other objectives are to encourage young researchers, including graduate students, to present their work; expose young researchers to important challenges and opportunities in this interdisciplinary domain, while providing a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues; and include as participants women, under-represented minorities and persons with disabilities who might benefit from the small workshop environment. See http://sand.stat.cmu.edu/sand for further information.

? DESCRIPTION (provided by applicant): SAND7, the seventh workshop on Statistical Analysis of Neural Data, a series that began in 2002, will take place May 27-29, 2015, in Pittsburgh PA. The workshop is organized through the Center for the Neural Basis of Cognition, which is run jointly by Carnegie Mellon University and the University of Pittsburgh. The objectives of the workshop are to define important problems in neuronal data analysis and useful strategies for attacking them; foster communication between experimental neuroscientists and those trained in statistical and computational methods; and provide further dissemination of the findings presented at the workshop via a set of peer- reviewed articles. Other objectives are to encourage young researchers, including graduate students, to present their work; expose young researchers to important challenges and opportunities in this interdisciplinary domain, while providing a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues; and include as participants women, under-represented minorities and persons with disabilities who might benefit from the small workshop environment. The scientific lectures will be given by 6 keynote speakers, and 12 junior investigators. Each keynote lecture will be followed by an invited discussion of the topic. There will also be a poster session, and al presenters will be encouraged to submit papers to the Journal of Computational Neuroscience.

This award supports participation in the conference on Modeling Neural Activity: Statistics, Dynamical Systems, and Networks (MONA2) held June 22-24, 2016 in Lihue, Hawaii. Many disorders, such as ADHD, autism, and schizophrenia, as well as stroke and various neurodegenerative diseases, are thought to involve dysfunction of neural networks. Because computational neuroscience aims to supply principles for understanding the activity of individual and collective neural firing patterns, its successes can help in formulating mechanistic descriptions of pathophysiology. This conference will bring together statisticians and computational neuroscientists from the US and Japan in order to enhance collaborations between scientists in the two countries. NSF funding will help support the involvement of the US researchers.

Computational neuroscience has grown, in distinct directions, from the success of biophysical models of neural activity, the attractiveness of the brain-as-computer metaphor, and the increasing prominence of statistical and machine learning methods throughout science. This has helped create a rich set of ideas and tools associated with "computation" to study the nervous system, but it has also led to a kind of balkanization of expertise. There is, especially, very little overlap between mathematical and statistical research in this area. Important breakthroughs in computational neuroscience could come from research strategies that are able to combine what are currently largely distinct approaches. This award seeks to encourage the creation and enhancement of collaborations between scientists from the US and Japan. More information can be found on the conference web site http://www.stat.cmu.edu/mona2.

SAND8, the eighth international workshop on Statistical Analysis of Neural Data, a series that began in 2002, will take place May 31-June 2, 2017, in Pittsburgh PA. The workshop is organized through the Center for the Neural Basis of Cognition, which is run jointly by Carnegie Mellon University and the University of Pittsburgh. The objectives of the workshop are to define important problems in neuronal data analysis and useful strategies for attacking them; foster communication between experimental neuroscientists and those trained in statistical and computational methods; and provide further dissemination of the findings presented at the workshop via a set of peer-reviewed articles. Other objectives are to encourage young researchers, including graduate students, to present their work; expose young researchers to important challenges and opportunities in this interdisciplinary domain, while providing a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues; and include as participants women, under-represented minorities and persons with disabilities who might benefit from the small workshop environment. The scientific lectures will be given by 9 keynote speakers, 6 panelists, 6 invited discussants, and 12 junior investigators. There will also be a poster session, where we anticipate more than 50 posters, an informal discussion session aimed at helping newcomers establish personal connections with senior researchers, and a lunch for women in computational neuroscience. All presenters will be encouraged to submit papers to the Journal of Computational Neuroscience.

SAND9, the ninth international workshop on Statistical Analysis of Neural Data, a series that began in 2002, will take place May 21-23, 2019, in Pittsburgh PA. The workshop is organized through the Center for the Neural Basis of Cognition, which is run jointly by Carnegie Mellon University and the University of Pittsburgh. The objectives of the workshop are to define important problems in neuronal data analysis and useful strategies for attacking them; foster communication between experimental neuroscientists and those trained in statistical and computational methods; and provide further dissemination of the findings presented at the workshop via a set of peer-reviewed articles. Other objectives are to encourage young researchers, including graduate students, to present their work; expose young researchers to important challenges and opportunities in this interdisciplinary domain, while providing a small meeting atmosphere to facilitate the interaction of young researchers with senior colleagues; and include as participants women, under-represented minorities and persons with disabilities who might benefit from the small workshop environment. The scientific lectures will be given by 8 keynote speakers, 5 panelists, 8 invited discussants, and 12 junior investigators. There will also be a poster session, where we anticipate 25 to 50 posters, an informal discussion session aimed at helping newcomers establish personal connections with senior researchers, and a lunch for women in computational neuroscience. All presenters will be encouraged to submit papers to the Journal of Computational Neuroscience.

Project Summary Much mental health research uses neurophysiological measurements to describe the way neural activity within and across brain regions is related to behavioral function and dysfunction. One kind of signal, known as a spike train, comes from an individual neuron. Another, the local field potential (LFP), is based on activity from large numbers of neurons within specified parts of the brain. For both kinds of data, scientifically rigorous statistical analysis must accommodate unstable fluctuations, associated with movement or thought, known in statistics as non- stationarity. The continuing research program of this grant is to develop methods for analyzing non-stationary neural data. Of particular interest is the description of interactions among two or more brain areas. This application is for an administrative supplement to support an under-represented minority PhD student for two years. As documented by, among others, the National Science Foundation, people of African ancestry are severely under-represented in the sciences. The training provided to the candidate, under this supplement, would serve to elevate the candidate's research profile, and would ultimately contribute to enhancing diversity in the STEM workforce. The candidate's research concerns methods for identifying the flow of information from one brain area to another based on neural spike trains. Two major complications are, first, the noisiness of spike trains as conveyors of information and, second, the large numbers of neurons that must be considered simultaneously. Statistical methods developed very recently, through research supported by this grant, suggest very promising approaches to reducing the effects of noise and grappling with large networks of neurons. Based on these ideas, the candidate will develop a PhD thesis topic, and pursue it, with support from this supplement.