Hey Robert, Is originality more important than usefulness when it comes to a dissertation project? It feels like I have to come up with something obscure that hardly anyone is going to use to develop something that I feel could be useful to a range of people. Secondly, I feel like this topic is focused. I mean, I could start by just adding other distributions to the statistics toolbox. Thanks for the help. - Clark
On Jun 25, 1:14 pm, Robert Dodier <robert.dod...@gmail.com> wrote: > On Jun 24, 11:27 am, cjkogan111 <cjkogan...@gmail.com> wrote: > > > I am a statistics graduate student interested in working on sympy for > > a thesis project. I thought it would be interesting to try to give the > > statistics module some of the features of mathstatica (an addin for > > mathematica.) The department I am part of seems concerned about: > > a) Lack of a stateable thesis > > b) Lack of an advisor knowledgeable in this area > > c) Topic does not seem it would lead to publishing in a journal > > Well, I think you can overcome the objections of your dept. > > (a) select a narrow, focused topic. Create a framework > for general functionality but fill in only enough of it to > make your particular application workable. > > (b) you become the resident expert. When people (e.g. > your advisor) ask what you're working on, you have a > an explanation ready as to why it's interesting and useful. > > (c) Focus on what's original. See (a). > Also, it seems helpful to find some outsider (e.g. in > engineering or someone in the sciences) who has > a problem they need to solve. You solve it for them -- > presto, your publication. > > About (a), my advice is to emphasize the symbolic > aspects to try to drive towards an exact solution, > but revert to numerical approximations when necessary. > (I've peddled this idea in various forums without attracting > much interest. If you want I can send you a paper which > expresses some ideas I had.) > > An example could be exact and approximate inference > in some class of generalized Markov models. > (Just a random example. I 'm sure there are many others.) > > Hope this helps! > > Robert Dodier --~--~---------~--~----~------------~-------~--~----~ You received this message because you are subscribed to the Google Groups "sympy" group. To post to this group, send email to sympy@googlegroups.com To unsubscribe from this group, send email to sympy+unsubscr...@googlegroups.com For more options, visit this group at http://groups.google.com/group/sympy?hl=en -~----------~----~----~----~------~----~------~--~---
