318 Hanes Hall, CB #3260 Chapel Hill, NC 27599-3260
919-962-1329

Consulting

Consulting

UNC Statistical / Data Science Consulting Center

The Department of Statistics and Operations Research offers free statistical consulting services, in the context of a course on statistical consulting, STOR 765 (formerly Stat 190).  This graduate level course aims to both serve the university community, and to instruct students in the art of consulting.

Course particulars
The instructor for the consulting course is Professor J.S. Marron. Credits are 1.5 course hours per semester for two semesters.

For Students
Students typically work on two projects per year, either alone, or as part of multidisciplinary teams when appropriate. Students are expected to attend client presentations, to contribute to projects, to document their results and findings, and to give occasional project status updates to the entire class.

For prospective clients
We welcome inquiries from potential users on or off campus, though preference is given to those on campus. Professors, research staff, and postdocs are welcome to contact us directly; graduate students working on PhD projects are also welcome but should first obtain the approval of their advisers.

Our normal method of operation is to invite, after a preliminary interview, our “client” to give a presentation at one of our Thursday afternoon sessions. This can be very informal, and we encourage open discussion among the class, but it should give the background of the research problem in enough detail for us to discuss where the quantitative problems arise. Sometimes the consultation can be concluded in a single session, but more often than not, consultation includes further work done by one of the students. This is then carried out under Professor Marron’s supervision, possibly in collaboration with one or more colleagues. A written report is an expected outcome of the consultation.

At present, fees are not charged for the use of this service. We view its function as primarily educational, to both the client and the student doing the work. On the other hand, we do not guarantee our results in any way.

All projects must be finished by the end of classes. For example, on occasion the consulting service has led to a student being employed by another department. If you need some statistical consulting but are not sure whether it falls within the bounds of the consulting service, please contact Professor Marron who will be happy to discuss the problem with you.

Constraints and policies
There are some constraints on the kinds of problems we consider. First, the project cannot be too large. We prefer projects that can be completed by a small team in 1 to 2 months. Although we will do statistical computing when appropriate, we do not encourage projects requiring large data-crunching efforts.

Our policy is not to compete with other established groups on campus that offer statistical consulting. Primarily, this means the Odum Institute and the Biostatistics Department. Odum Institute personnel have a wide range of expertise in social sciences, and also in the use of packages such as SAS and SPSS. ATN also offers a service to help with statistical packages. In general, we do not offer assistance in the use of packages: our expertise is in the formulation of research problems in statistical terms, or in problems that cannot be addressed by a standard software package. As far as Biostatistics is concerned, they are the established department on campus to provide statistical assistance to the Medical School and the School of Public Health. However, it has been agreed with the Biostatistics Department that we may accept work from these schools provided it does not create any conflict with them.

Contact information
To contact the consulting service: recommended approach is to send an email message to Professor Marron, at marron@unc.edu. Phone messages may be left at 962-2188, although these are checked less frequently.

Education and Public Service: Helping Organizations Analyze and Improve Their Operations

Introduction
The purpose of this webpage is to acquaint North Carolinians with a no-cost service that has provided technical assistance to government, industry, and other organizations within North Carolina since 1988.  It links highly-qualified graduate students in the Department of Statistics and Operations Research at the University of North Carolina with these organizations on a one-semester project with the goal of analyzing a specific area of organizational or operational importance to that organization.

What is Operations Research?
Operations Research – also known as Management Science or Industrial Engineering — may not a familiar term, in spite of the fact that its principles underlie the running of almost every sufficiently large organization.  It is the science of optimal decision-making applied to organized (and sometimes unorganized) operating environments.  Quantitative models provides the basis for formulating optimal operating strategies and highly efficient computational software supply the means for converting the implications of these formulations into readily accessible decision tables for executive decision-making.  Scheduling, routing, and control problems all benefit from analysis via operations research and the design and management of telecommunication networks, manufacturing systems, and transportation networks are several of the greatest beneficiaries of these efforts.  Capital budgeting and supply chain management in business, network layout and switching in transportation and telecommunications, patient scheduling and tracking in health care management, and fisheries and water resource management also have benefited from operations research analysis.  Operations research has also been applied to solve problems in other basic areas such as data mining, medical and biological research, and computer design.

Operations Research at UNC
In 1968 the University of North Carolina at Chapel Hill formed the Operations Research Curriculum in recognition of the expanding importance of the OR in decision-making for businesses and organizations throughout North Carolina.   The curriculum became a department in 1985, and then in 2003 merged with the Statistics Department to become the current Statistics and Operations Research Department.  The department offers graduate degree programs in Operations Research, Statistics, and several interdisciplinary tracks, as well as an undergraduate program in Mathematical Decision Sciences.  Graduates work in many diverse areas in industry and government, or serve on university faculties throughout the United States and abroad.  OR faculty in the department work in many interdisciplinary research areas, including telecommunications, health sciences, biology, and medicine.

The Operations Research Practice Course
The OR Practice Course, STOR705, was instituted in 1988 to provide its students with a hands-on experience in solving real-world problems using the techniques of operations research.  Students are assigned, problems from clients in government, industry, and administrative and operating units within as well as outside the university who request help in addressing their organizational problems. Students formulate these problems in quantitative terms and identify appropriate methods for solution.  They also identify data needs, arrange to obtain and analyze the data, and develop the software required to generate solutions.  They consult with clients and their staffs on a regular basis for problem clarification and suitability of proposed solutions.  At the end of the project, the student provides the client with a written report and an oral presentation of the solution.

At regular course sessions during the semester, each student periodically describes her or his progress, with the course coordinator and other students assessing the project’s development and providing assistance in solving associated problems.  All department faculty are available the students as consultants with regard to problem formulation, methodology, and interpretation of results.  The emphasis throughout the course is on having the student assume responsibility for virtually all aspects of her or his project.

During the past 25 years, student consultants have solved many diverse problems for their clients in the areas of:

  • equipment replacement strategies
  • relieving congestion
  • facilities expansion
  • information organization
  • inventory management
  • staffing
  • transportation and routing
  • scheduling
  • waste collection and recycling
  • service control

Setting Up an OR Practice Course Project
The OR Practice Course runs through spring semester each year, and the number of projects depends upon the number of students available each year. The project descriptions need to be finalized and assigned to the student by the end of fall semester (early to mid-December).  We are interested in organizational, management or decision-making problems that are appropriate for solution by OR methods.  Each project host or client will be assigned a graduate student (free of charge) to work on her or his suggested project.  In consultation with the host and the operations research faculty, the student will develop a proposal of substance and scope appropriate to a one-semester time frame. The student will then devote 5 to 10 hours a week to solving the problem during the year. Clients have the responsibility to make themselves, or others on their staff in a position of authority, available to the student on a daily or weekly basis, and to provide the necessary information and data for them to conduct a meaningful analysis.