I would think that a thesis project with a more hefty CAS aspect would be inclusion in SymPy of methods for deriving distributions that are functions of other distributions. I mean the techniques that are dealt with in chapter 4 of the Mathstatica book (Rose & Smith, Mathematical statistics with Mathematica, 2001 edition): transformation method and moment generating functions (MGF) method. Practical publishable applications can probably, a.o., be found in the study of measurement uncertainty. Inspiration might be found in papers in Metrologia (many freely available at www.bipm.int) and other metrological journals. A subject for a publication can be comparing uncertainty analysis using a conventional approach (Law of Propagation of Uncertainties ans Central Limit Theorem LPU/CLT) an analytical approach using convolution of pdf's and the numerical approach using Monte Carlo techniques. All the best, Janwillem
On Jun 25, 4:42 pm, cjkogan111 <cjkogan...@gmail.com> wrote: > Good idea Ondrej. I can motivate the creation of a general stat module > as a tool for a specific problem. > Clark > > On Jun 24, 6:43 pm, Ondrej Certik <ond...@certik.cz> wrote: > > > On Wed, Jun 24, 2009 at 6:36 PM, cjkogan111<cjkogan...@gmail.com> wrote: > > > > Thanks Robert & Ondrej, > > > I appreciate the helpful comments. I think that might be a good idea > > > to focus, even though what I think would be most helpful to the > > > community is just to make a general stat module. > > > Indeed. But you can do both -- a general stat module and in particular > > something that can also be published. > > > Ondrej > > --~--~---------~--~----~------------~-------~--~----~ 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 -~----------~----~----~----~------~----~------~--~---
