- Can I send my application materials directly to the department?
- What background do I need for the program?
- Can I jump into doing research right away?
- I have been assigned a first year advisor. Does this mean I will be working with this professor on my dissertation?
- What should I do the summer before my first semester to prepare for the Ph.D. Program?
- Should I purchase a laptop or personal computer for use during the Ph.D. program?
- Is there an orientation for incoming students before Fall semester starts? If so, when is it?
- What classes should I register for in my first semester?
- Can I take classes from UNC or NC State if they turn out to be useful to my research? If so, how can I do that?
- How and when do I register for classes?
- How do I create a personal webpage?
- Do I need to know C, C++, or another programming language?
- What type of operating system do computers in the department use?
- What do I have to do to receive the financial aid specified in my acceptance letter?
- How will the financial aid specified in my acceptance letter be paid?
- Can I receive financial aid if I am a research assistant (RA)?
- Because financial support is paid over the 9 month school year, what do I do about summer funding?
- Do I have to be a teaching assistant (TA) to receive financial aid? If so, what responsibilities will I have as a TA?
- Where can I find housing information for on-campus and off-campus housing?
- Do I need to get a Duke Parking Pass?
- What do international students typically do for housing?
- When during the summer should I plan on moving to Durham?
- Should I live on-campus or off-campus?
- Should I plan on attending the orientation for international students?
- What should international students do about social security numbers?
Applicants should NOT send any application material to the department. Just follow the detailed Graduate School admission instructions. Any additional material (writing samples, papers, etc etc) sent to the department will be ignored.
Our students come from a range of disciplines. A strong background in advanced multivariate calculus and linear algebra is most important, and prior exposure to mathematical analysis at the level of the Duke course MATH 531 Basic Analysis (in the Duke Mathematics department) is recommended. Prior research experience is always a factor in admission decisions. Prior use of computing in statistical/scientific problems is valuable since there is a major emphasis on statistical computation in modern statistical research. Check the "Resources" link at the departmental Graduate Consultative Committee web pages, for a FAQ document and other material provided by current students.
At Duke, jumping into research right away is definitely possible. Of course, conducting research during your first year is contingent upon your background and interests. In terms of funding, faculty mentoring, and peer support, Duke provides an environment very supportive of research from day one. If you are interested in doing research right away, you should talk with faculty as soon as you arrive (or earlier via email) about projects they are working on. However, doing research requires quite a bit of statistical background and hence, most students start research after their first year exam. Regardless of your statistical background, you are encouraged to begin talking with different professors about research opportunities as soon as you arrive. This will help you identify potential professors you would want to work with during your time at Duke. Students should have identified who they would like to work with by the end of the first year.
I have been assigned a first year advisor. Does this mean I will be working with this professor on my dissertation?
No. Your first year faculty advisor is your advisor for your first year only. Their responsibility is simply to give you any support you need throughout your first year. During your first year, you are expected to actively seek another advisor with whom you can begin doing research. This may or may not be your first year faculty advisor.
The first year of the Ph.D. program can be intense. However, with adequate preparation you can make the transition from undergraduate to graduate work smoother than it would otherwise be. It will help your first semester (and every semester thereafter) go smoother if you are already familiar with Linux, LaTex, R, and MATLAB before you begin your first semester. As Duke is primarily a Bayesian department, there is a good chance you will need some C or C++ programming at some point during your course of study. However, learning Linux, LaTex, R and MATLAB is of much higher importance than learning low level languages as you will use them immediately upon commencement of the program. As you will most likely be a TA for undergraduate classes during your first year, it would be very helpful to review basic statistical principles such as confidence intervals, hypothesis testing, counting techniques, basic probability, central limit theorem, distributions (e.g. normal, binomial, t, etc.), finding expected values and variances, and other selected topics suitable for an introductory statistics course. In order to prepare for first year course work, you can also spend time studying statistical topics such as simple and multiple linear regression, mathematical statistics, Bayesian inference, and real analysis. Also, reviewing calculus and linear algebra topics as needed is definitely encouraged. Suggested reading and study material include Statistical Inference by Casella and Berger, Applied Linear Regression by Weisberg, Bayesian Data Analysis by Gelman, Carlin, Rubin, and Stern, Matrix Algebra from a Statistician's Perspective by Harville, and other books on the above topics encountered during your undergraduate study or elsewhere. Last, and certainly not least, take time to relax and enjoy the summer. The Ph.D. program is very intense at times, and often summers are needed to catch up on research, attend conferences, etc. After enrolling in the Ph.D. program, your summers will typically be spent either doing an internship or working on your thesis work and/or research projects. Take time the preceding summer to relax because you may not have time to relax once you commence the program.
You will find it very helpful to have a personal laptop. If you do not have a laptop, contact the DGS to look into borrowing one from the department. The department also maintains desktop computers that can be remotely accessed by any computer via Virtual Computing Network (VNC) or secure shell (ssh) on Unix or Linux based platforms.
There are three orientations that occur for incoming students. The first is held by the international house, the second is held by the graduate school, and the third is held by the department of statistics. The international house orientation is typically two weeks before the first week of the semester. Both the graduate school and the department orientation are held the week prior to the first week of school. All students (especially international students) are encouraged to attend all orientation events and should plan their arrival in Durham accordingly. Information regarding the graduate school and international house orientation will be mailed to you or can be found on the graduate school orientation website. The graduate consultative committee (GCC) is responsible for holding a department orientation. It is typically held the week before the Fall semester starts (the same week as the graduate school orientation) but after the graduate school orientation. The GCC will contact you via email about when and where this orientation will be held.
The courses you elect to take for your first semester will depend on your background. Three of the classes offered in Fall are covered on the First Year Exam (STA 601, STA 721, and STA 711) so you should begin by considering these classes. Students generally choose THREE of the following classes to take their first semester:
- STA 611 Introduction to Statistical Methods - This class is taught from the first half of Statistical Inference by Casella and Berger. This class covers topics such as basic probability theory, transformations, expectations, common families of distributions, multivariate random variables, and sampling distributions. If you have little or no mathematical statistics background then be sure to take this class. Most first-years will probably find this class unnecessary, but if you feel like you need some review, you may want to consider auditing.
- STA 601 Modern Statistical Data Analysis - This class introduces students to classical and Bayesian statistical thought. This class also introduces students to basic statistical analysis (such as exploratory and graphical analysis) using R. This class will also touch on LaTex. Some first-years will not need this class.
- STA 721 Linear Models - A thorough introduction to linear regression, with a focus on Bayesian modeling and computation. Model selection, Bayesian model averaging, and other topics. Most (not all) first-years decide to take this class.
- STA 711 Probability and Measure Theory - STA 205 is an introductory class on probability from a measure theoretic viewpoint. Topics include rigorous treatment of Lebesgue measure and integration, convergence of random variables, Lebesgue's dominated convergence theorem, etc. Almost all first-years take this class.
- MATH 241 Real Analysis - The topics covered in Math 241 are also covered in STA 711 (205), so many students take one or the other. If you really like probability (mathematical theory) and want to work mostly in statistical theory, then taking MATH 241 at some point is suggested.
- MATH 216 Applied Stochastic Processes - Discusses Markov chains, martingales, Brownian motion, etc.
- STA 841 Generalized Linear Models - Covers topics such as log-linear models, Poisson regression, probit models, logit models, models for longitudinal, clustered, and multivariate data, latent factor models, stochastic search algorithms, etc. Generally for students who are familiar with Bayesian methods such as Gibbs sampling, Metropolis-Hastings, and have had an advanced course in linear models.
A simple suggestion would be to begin with STA 601, 721 and 711. STA 841 is a permission number course so you'll need to talk to your advisor or the instructor to determine if you are qualified. A "typical" course of study can be found on our Ph.D. Requirements' page.
Can I take classes from UNC or NC State if they turn out to be useful to my research? If so, how can I do that?
While it is possible for students at Duke to take classes at UNC or NC State, most students find the selection of courses within Duke to be sufficient for their research interests. If you are interested in taking a class at UNC or NC State, then you will need to get approval from your advisor and the director of graduate studies.
Sometime during the summer, Duke will send you your NetID in the mail. Although you can register as soon as you have your NetID, you do not need to register until after you come to campus and speak with your first year advisor as well as other students. Many students still add or drop classes during the first week of school. To register, once you have your NetID and password, you can log onto the registrar's website registrar.duke.edu/ and click on "DukeHub." Sign in using your NetID and password, then click on the "Registration" tab at the top of the screen. The first time you register you will be required to enter personal information such as official name, address, etc. You will be required to verify this information the first time you register for a new semester. You will also be required to enroll for continuation (CTN) each Fall and Spring semester; this may be done automatically. If you are a research assistant during the summer, you will also be required to manually register for CTN in the summer. The best way to register is to go to your "Bookbag" which is a tab under the "Registration" tab in ACES. From here click "search", select the appropriate semester, click on the first letter of the department you are searching for (for example, click "S" for Stat classes), and click the green arrow next to the department name. This will list all the classes offered by that department in a given semester. To add a class to your bookbag, click the green arrow next to the class and select "add to bookbag." At this point you still have not registered for the class. You can officially register for all the classes in your bookbag simultaneously or one at a time by clicking the appropriate link. Some classes may require permission numbers. If this is the case you will need to obtain the permission numbers from Karen Whitesell or from the instructor (usually this can be accomplished over email). Once the class has been moved to the "class schedule" section, you are officially registered for the class.
Everyone with an account in the Department of Statistical Science will have space for a personal website in their home directory with a url of http://www2.stat.duke.edu/~user/ where "user" is your DSS username.
Maybe. As the department is primarily Bayesian, your PhD dissertation will probably involve sophisticated models and potentially complex algorithms for learning parameter estimates and other quantities of interest. R and MatLab are excellent languages for prototyping algorithms and may be fine for some problems. C, C++ and FORTRAN are among the best (fastest) languages for programming loops and numerical operations, but typically have a higher cost in programming time compared to R or MatLab. C, C++ or FORTRAN can be called from R or MatLab allowing you to eliminate bottlenecks in your programs, and increase the computational efficiency of your code, while providing an easy to use user interface. More efficient code means more time to work on other topics, so more papers and hopefully a better job at the end! If you have the opportunity to learn a language like C or C++, we would encourage you to take advantage of it before coming to Duke, although you can pick it up later if and when you need it.
Most desktops in the department are running Scientific Linux 6 (SL6), a freely available linux distribution. Linux offers several Graphical User Interfaces (GUI), such as KDE, Gnome, XFCE that provide customizable desktop environments with toolbars, windows, folders, and icons like in Windows or Mac OS X environments, while providing a command line shell for more traditional unix based commands.
About half of the financial aid specified in your acceptance letter will be given to you without you having to do anything except maintaining good academic standing. The other half is contingent upon you being a teaching assistant (TA) or research assistant (RA) within the department.
Your tuition, health fee, and continuation fee will be paid for automatically. You are responsible to pay the recreation and activity fee (about $50). Additionally, your financial aid package will cover the cost of your medical insurance. If you are a TA, you will be paid monthly on two separate checks. The first check is for your TA work and will be paid the 25th of every month starting in September and continuing through May. The second check is from you maintaining good academic standing and will be paid on the last working day of each month starting in September and continuing through May. If you are an RA, you will be paid once per month on the 25th from September through May. PLEASE NOTE that as a first year student you will not be paid until the 25th of September, so you will need to keep enough money in your bank account to survive until then. Please plan ahead financially so you don't get into financial trouble prior to your first payment.
Yes. Most students starting in their second or third year will be paid on grants of the professor for whom they are an RA. This money will replace what you would have received had you been a TA.
Students typically choose to get summer funding from one of three sources: internships, research, or teaching. During the summer, a lot of students choose to do an internship in industry or research groups. Internships are typically arranged between January and March, though it certainly will not hurt to begin looking earlier. A list of internships will be posted on the AMSTAT website, generally in November. Additionally, you will receive emails throughout the year about various internship opportunities available to students. If there are any internships you are particularly interested in, be sure to talk to the faculty to see if they have any contacts with the company. This can increase your odds significantly. Students nearing graduation typically choose to spend the summer working on their dissertation research. Therefore, their summer funding comes from grants awarded to professors. A third option is to teach a class during the summer semester for the department. The statistics department offers several introductory undergraduate courses that graduate students teach during the summer semester. If you want teaching experience, you are encouraged to teach a class during the summer and you will be compensated for your work.
Do I have to be a teaching assistant (TA) to receive financial aid? If so, what responsibilities will I have as a TA?
No. HOWEVER, if you are not a TA or an RA for the department you will not receive that portion of the financial aid specified in your acceptance letter (this is about half of the aid specified in your acceptance letter). As a TA your responsibilities include: (1) grading, (2) holding office hours, (3) holding review sessions for exams, (4) doing whatever professors need you to do. Additionally, some courses have a computing lab component that is run by a TA. There is more information regarding TA responsibilities on our website.
NearDuke.com was established to help graduate students find either on-campus or off-campus housing in the Durham area. You can also use traditional search engines such as Google, Yahoo, etc. to help you find housing. Many students also suggest using Craig's List to find housing. If you have sufficient finances to make a trip to Durham to search for housing, it would be a good idea to visit the apartments you are considering before actually moving here. However, if this is not an option you can feel free to ask your student mentor to help you out by answering questions about locations you are considering. If you are considering off-campus housing, students generally suggest to avoid apartments that have the word "Duke" or "University" in the title of the apartment complex. These particular apartment complexes have been known to have a bad reputation. Another apartment complex to avoid is called "Chapel Tower."
Yes, but only if you have a car and plan on driving to campus everyday. However, Duke parking passes are very expensive and parking lots can be a long walk from the department building. Some students find that living closer to campus and riding a bicycle, taking the bus, or walking is more convenient than driving to campus everyday. An alternative to a car is to drive a motorcycle or moped. Motorcycle parking passes are cheap and you can park almost anywhere on campus (including right next to the statistics building). To avoid purchasing a parking permit, some students find it convenient to park their cars along the Duke commuter bus routes and take a (free) bus to campus. Additionally, if you live with/near other students, you may consider a carpool permit. The carpool permits tend to be much cheaper than indidivudal passes and can often be attained for parking lots that would otherwise be considered full. Access the Duke Parking and Transportation site for more information.
The Graduate School arranges priority on-campus accommodation for all incoming, new overseas students in Central Campus apartments. Some international students stay on campus for a year in order to become accustomed to life in the United States. Other first year students prefer off-campus accommodation; there are lots of options very close to campus. Although the on-campus housing tends to be more expensive, current students have found that on-campus apartments provide a good chance to meet other graduate students. Feel free to contact some of our current international students (or your student mentor) for insider information. The Graduate School has full details about housing.
The short answer is: whenever is most convenient for you. Many students choose to move to Durham in July or early August in order to get situated before a new semester begins. However, you can move to Durham right up until the day before the first day of school. It is up to you. You are, however, encouraged to attend the various orientations and should probably plan on arriving in Durham prior to the orientation events.
Many international students prefer to live on campus during their first year so that they can become accustomed to life in the U.S. before living off campus. However, it is certainly not a requirement for international students to live on-campus their first year. Most U.S. students choose to live off-campus. Off-campus housing is easy to come by in Durham as there are many apartment complexes and condominiums near campus. If you have a bicycle or car there are many apartment complexes within a short commute to Duke. Advantages to on-campus apartments: (1) fully furnished, (2) fast Ethernet connections, (3) close to bus stops, (4) can be paid for via direct deposit from your bursars account, and (5) quiet hours. Disadvantages include expenses as many on-campus housing options are twice as expensive as off-campus counterparts. Also, the number of on-campus apartments available for graduate students is small, making them difficult to come by. One thing to consider when thinking about on-campus vs. off-campus housing is your mode of transportation. If you do not have a car then you will want to live either on or very close to campus. If you do have a car (make sure to read the section on parking passes) then your commute will be reasonable anywhere in the Durham area. Regardless of whether you live on-campus or off-campus, use common sense by locking your door, not walking home late at night, and use cabs if necessary. While Durham is generally quite a safe city, there are incidents which occur close to campus and students are encouraged to take the proper precautions.
Yes. They cover everything that international students need to know to survive in graduate school and will provide a much better orientation than this question and answer document. During the orientation the International House will also cover any legal issues that may arise from being an international student (e.g. visas).
Issues regarding social security numbers (SSNs) will be handled during orientation. Students can also visit the International House to go to the social security office to obtain social security cards if needed. More information about SSNs and other topics can be accessed in the informational handouts provided by the International House.