Stat software

Replies to This Discussion

Permalink Reply by Biswajit Nayak on September 11, 2009 at 4:21am

Hi Dirk, This is Biswajit represent StatSoft India, StatSoft.com. You may explore Statistica Automate Neural Network (SANN) one of the most proven ease of use for Time Series , Classification, Regression & Cluster Problem.Anticipate & expect delivers true Value for money. If we could be any of your assistance please let us know.

Thanks.
Biswajit.

▶ Reply to This

Permalink Reply by Joseph Foutz on September 11, 2009 at 10:10am

First I’d say to try JMulTi. It’s free and easy to use, so if it can accomplish what you want to accomplish...

As far as commercial software: Stata, Stata, and then maybe Stata.

▶ Reply to This

Permalink Reply by John Johnson on September 11, 2009 at 10:46am

R.

▶ Reply to This

Permalink Reply by Joseph Foutz on September 14, 2009 at 2:14pm

For the packages you listed, EViews is the least expensive, and I might venture a guess that SPSS is the most robust in terms of model autofitting.

SAS: $6K+ first year, $2K+ each additional year (estimates for Base & ETS)
SPSS: $2,798 (Base & Forecasting)
EViews: $975 (Standard)
Stata: $1,245 (IC)

As a diehard Stata user, obviously I’m partial to it. Biswatjit mentioned Statistica - I haven't got a clue how Statistica is priced, so if someone else wants to jump in... I'm guessing it's more than EViews.

There are, of course, many other time series packages out there such as the open source gretl, JMulTi, and R, and commercial packages BMDP, GAUSS, RATS… At $500, RATS is the least expensive commercial product I know of.

The reason I’m putting a second post here is not just to flesh out my previous response, but also because it got me thinking about just how crowded the marketplace is with time series software. Some of them were academic packages to start (e.g. SPSS & BMDP), but most started out as commercial ventures. I suppose it is a testament to the entrepreneurial spirit. Fundamentally though, I haven’t got a clue why we need so many different choices or how all of these companies can survive in the market. (Especially when most of them do essentially the same things.)

Thoughts?

▶ Reply to This

Permalink Reply by Jaap Vink on September 14, 2009 at 5:21pm

As of Version 18 of PASW Statistics (f.k.a. SPSS Statistics) modules can also be bought 'stand alone'. In this case only PASW Forecasting™ 18 (US price for ESD from the webstore $999.00). See also http://www.spss.com/statistics/

▶ Reply to This

Permalink Reply by Alexander Lazarin on September 16, 2009 at 6:23am

To make the crowd even bigger I would also mention Ox which has a free version for academic users.

▶ Reply to This

Permalink Reply by Faisal on October 19, 2009 at 8:50am

hey all,
I hope all doing well....
I wandering if anybody help me about software which used in population genetics.
especially full likelihood calculation?

▶ Reply to This