Results 1 to 4 of 4

Thread: For statiticians

  1. #1

    Post For statiticians

    For the hell of it, I thought I'd see if I could stir something up. Do you use R, State, SPSS, SAS or something else and why? Are you a frequentist of a Bayesian?

    I'm a Stata guy; it's user-friendly and does everything I need it to do (for the most part). I'm also dabblingin Bayesian, but I'm predominantly a frequentist.

  2. #2


    I did some Statistic Modules at college, I have no idea what your on about though. Other than to say, no. I don't think I use anything in particular with statistics.

  3. #3


    Quote Originally Posted by harris View Post
    For the hell of it, I thought I'd see if I could stir something up. Do you use R, State, SPSS, SAS or something else and why?
    It depends where I am / what I'm doing.

    Let me explain:
    Typically, I'll have a pile of data slopped around in several sources. I use JMP or Excel to quickly join it up under a common key, and then I can start analysis.

    • R is powerful and runs on Apple as well as PC, but I haven't learned it.
    • I've seen Stata and it looks straight-forward, but I've not worked with it and am not sure if there's an Apple build.
    • SPSS is quick and good for running very fast descriptives and cross-tabs. It also runs on both PC and Apple platforms.
    • I'll use SAS if I want to run a quick procrsquared on a set, OR if I'm doing some more involved data-mining.

    I also use LISREL/AMOS to build Structural Equation Modeling (SEM) runs. I typically look to data mining for both exploratory and confirmatory analysis, and for that I tend to use WEKA.

    When I'm feeling like it, I do like the ANN toolkit that I have for Matlab (an old version; 14, I think - I'm sure we're up to 16 or so by now).

    The argument I'm making above boils down to, "best (or easiest, anyway) tool for the job." I'm not married to any one package, though if I absolutely had to choose, I'd likely go SPSS for its ease and cross-platform capability. Besides, it's for ME (Social Scientist)!

  4. #4


    Wow. Quite the plethora. I've used SPSS, and I think it has some great attributes. But I'll stick to Stata primarily because you it has the pull-down menu convenience of SPSS with the programability to R. And with so many programs already available on the Stata website, which the help section of Stata automatically searches, it does everything I need it to do. Even better is the ability to cut and paste lines of codes. Everytime you run a test from the pull down menu, the code is automativally displaed next to the results. You can copy and paste the code into what's called a Do file, save the file, and then hit "run" and it will run all the tests automatically and put the results into a separate file. Convenient.

    In terms of data management, Excel is easier to move things around with, but Stata has a number of ways to create variables, whether continuous or non-continuous. It can even code a binary variable for every continuous value.

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  • - the Adult Baby / Diaper Lover / Incontinence Support Community. is designed to be viewed in Firefox, with a resolution of at least 1280 x 1024.