Some comments that I hope may be of use - Yes the STATA manuals are very good. At $495 per set they should be. Buying individual volumes is not an option as there are many cross-references between different volumes and the price of the set is discounted relative to buying individual volumes. The online manuals are just a basic summary of the syntax of the commands and are terrible. Other commercial packages that I know (e.g. RATS, EVIEWS, MATLAB, GAUSS, ) have much better help files and distribute their manuals in pdf format along with the product. I have switched to R for most of my econometrics partly for reason of $$ but also for the simple reason that I can get my analysis done in R. For simple econometrics I do return to simpler products or a product that has a specific purpose (eg GRETL for basic econometrics , RATS for time series analysis etc.).
R and STATA are both superb products. Both are so large that most people will be familiar with only a small part of each. Both are programmable. Modern or experimental methods can be implemented in both. Which programming language you prefer is probably a matter of taste. If you can find a person who is working in your field and is familiar with one of the languages and is willing to help you then my advice would be to use his expertise regardless of the package that he is using. One area where R is much better than STATA would be in finance where R has the advantage of the superb package Rmetrics. Any person choosing between R and STATA should look for similar packages in their expertise. The Task Views on CRAN are very good summaries or R facilities in the areas of econometrics and finance. I have added empirical content to a statistics course for mathematics masters students using R. I teach empirical econometrics using STATA and MATLAB (for institutional reasons) but would prefer yo use R. On 22/11/06, Robert Duval <[EMAIL PROTECTED]> wrote: > > I'll answer the ones I know of: > > > 4. Manuals (theory included in the manuals). > Stata manuals are superb. The online help manuals are really minimal, > but the complete set of manuals for sale is really good. Not only they > discuss the Stata implementetation, but they give a concise > theoretical discussion of what the statistical methods are actually > doing. > > While they don't get to talk much about the inner workings of Stata, > (as some of the R manuals do) I like them much better to the R ones. > > Many of the statistical procedures are illustrated with examples using > the datasets included with the software > > > 5. Support (in this aspect there is no comparison with R, > > the R list is the best known support). > > R list has a better support than Statalist, but still Statalist is > quite active and helpful. > Plus they are more polite... no RTFM or stuff like that. > If you own a Stata license, you can get direct support from somebody > at StataCorp (in addition to Statalist). This is specially relevant if > you have questions on how Stata is estimating something, bugs, etc. > > > > 6. Numerical stability. > Quite stable. The only glitch I've observed is that after new releases > their routines are not very reliable... meaning they sometimes change > the way something is being computed and might they mess up something > that previously was running fine. > > Right now Stata 9 is pretty stable, but if Stata 10 would come up in > the market now, I would probably wait for a couple of months and make > sure everything is well tested. > > > One last thing, while I abandoned the Stata world to move to R (due to > $$), I have to say that the only thing I really miss about it is its > ability to handle large datasets. Stata comes with great Data > management routines, and it can hold large amount of data in its > memory. > Here R is light years behind. This is particularly relevant if you > have to "clean-up" large datasets before you actually start doing > statistics. > > hope this helps > robert > > On 11/21/06, Kenneth Cabrera <[EMAIL PROTECTED]> wrote: > > Hi R users: > > > > I want to know if any of you had used > > Stata or Statgraphics. > > > > What are the advantages and disadvantages with > > respect to R on the following aspects? > > > > 1. Statistical functions or options for advanced > > experimental design (fractional, mixed models, > > greco-latin squares, split-plot, etc). > > 2. Bayesian approach to experimental design. > > 3. Experimental design planing options. > > 4. Manuals (theory included in the manuals). > > 5. Support (in this aspect there is no comparison with R, > > the R list is the best known support). > > 6. Numerical stability. > > 7. Implementation of modern statistical approaches. > > > > Thank you for your help. > > > > Kenneth > > > > -- > > > > ______________________________________________ > > [email protected] mailing list > > https://stat.ethz.ch/mailman/listinfo/r-help > > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > > and provide commented, minimal, self-contained, reproducible code. > > > > ______________________________________________ > [email protected] mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > -- John C Frain Trinity College Dublin Dublin 2 Ireland www.tcd.ie/Economics/staff/frainj/home.html mailto:[EMAIL PROTECTED] mailto:[EMAIL PROTECTED] [[alternative HTML version deleted]] ______________________________________________ [email protected] mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
