Mathematica 9 is now available
Services & Resources / Wolfram Forums / MathGroup Archive
-----

MathGroup Archive 2008

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: Mathematica 6.0: good choice statistics for an MD thesis?

  • To: mathgroup at smc.vnet.net
  • Subject: [mg93222] Re: [mg93179] Mathematica 6.0: good choice statistics for an MD thesis?
  • From: "Mauricio Esteban Cuak" <cuak2000 at gmail.com>
  • Date: Fri, 31 Oct 2008 03:08:23 -0500 (EST)
  • References: <200810300701.CAA00601@smc.vnet.net>

Hi.I've used mathematica for some basic statistic stuff...monte carlo
simulations mostly.
I think it's great for graphic output...no problem there.
Data managing I've found to be more challenging, but maybe that's because
I'm used to standard econometric packages (Stata for example).
If your planning to do sophisticated tests that mathematica doesn't include,
then you'll probably use up a lot of time
programming and double-checking your assumptions.
You learn a lot, but it takes a lot of time and it's certainly something to
consider.
Just my two cents.

Kind regards,

cd

2008/10/30 Marc Heusser <marc.heusser at byeheusser.commercialspammers.invalid>

> I need to collect data, do statistical analyses and create graphics for
> the results for my MD thesis (suicides in elderly people).
>
> This means maybe 1500 cases with many variables known like age,
> residence address, religion, method etc (most nominal, not continuous
> variables). I would like to find clusters of similar cases, and find
> predictive factors etc. I have data on some 20 years.
>
> The data must be collected, ie exists in paper form only.
>
> I just got Mathematica 6, and found nice user interface options.
>
> Would you recommend using Mathematica to build a data collection mask
> (ie one case, with drop boxes for most data, checking eg birth date for
> validity etc), and collecting those 1500 cases with it in a notebook or
> external file - what data structure?
> Then I would need to combine this with some statistical base facts like
> number of inhabitants in a city (from census data).
> And then using the data for statistical tests to see whether we can
> prove an patterns, create clusters, and do a factor analysis of
> contributing factors?
> And last present the data in a graphically strong form to present
> results?
>
> If anyone has done parts of this task, especially created a small form
> to collect data in a structure that can be used for the statistical
> tests, I'd be very grateful for some example code to get me started.
> The same goes for data structures and running some built-in statistical
> tests.
>
> I have used Mathematica before, older versions, but for very different
> tasks, I have never done statistics in Mathematica before.
>
> Thank you in advance.
>
> Marc
>
> --
> remove bye and from mercial to get valid e-mail
> <http://www.heusser.com>
>
>


-- 
Por favor eviten enviarme archivos adjuntos de Word o Powerpoint (
http://www.gnu.org/philosophy/no-word-attachments.es.html )



  • Prev by Date: Re: Mathematica 6.0: good choice statistics for an MD thesis?
  • Next by Date: Re: compelling evaluation
  • Previous by thread: Mathematica 6.0: good choice statistics for an MD thesis?
  • Next by thread: Re: Mathematica 6.0: good choice statistics for an MD thesis?