orgtheory.net

how to choose your statistical software, by jeremy

with 9 comments

From Scatter:

The analogy in my mind is that Stata is to the iPhone as R is to Android, as far as social science data analysis goes. I guess SAS would be BlackBerry, insofar as it’s dated and propped up by a strong lock-in among government employees. And SPSS is a Nokia phone that has a slick interface for dialing your friends but requires you to push dozens of extra buttons in a non-intuitive sequence if you want to call anyone new.

Any other tips on seizing up available software?

Advertisement

Written by fabiorojas

June 29, 2011 at 12:49 am

Posted in fabio, mere empirics

9 Responses

Subscribe to comments with RSS.

  1. Hmm, not sure I buy it as most R users I know have iPhones and R is leading the way in innovation, not constantly playing second fiddle to the flashier Stata.

    Trey

    June 29, 2011 at 1:12 am

  2. [...] how to choose your statistical software, by jeremy [...]

  3. Hey Prof. Rojas, have you heard of Dedoose? It’s a new qualitative and mixed-methods research tool from a UCLA psychologist person or something. I went to a talk where the creator was promoting it and I thought it was pretty interesting – one of the audience members said “so tell me if I’m wrong, does this program allow me to do multi-level modeling but with qualitative data?” and the creator was like “exactly.” I’m not fully sure how that is so, but I was kinda impressed – perhaps you should take a look and then pop my bubble!

    dedoose.com

    Andrew

    June 29, 2011 at 5:19 am

  4. @trey: Phone-wise, I will insert the anecdote that my partner and I bought smartphones on the same day for comparable prices (and on the same plan), and I’ve had more occasions of envying her Android phone than she has had of envying my iPhone. So no analogic disrespect to R. But I think if one were posed the question, “Which stats package is more like a walled garden whose owners are very concerned about keeping your kids safe from porn?”, the answer would be Stata.

    Jeremy

    June 29, 2011 at 3:04 pm

  5. Good point.

    trey1

    June 29, 2011 at 3:12 pm

  6. Curses with the mixed logins.

    trey1

    June 29, 2011 at 3:12 pm

  7. My infatuation with R and my Android phone are further confirmation.

    Jesse

    June 29, 2011 at 3:42 pm

  8. SAS and STATA seem to be used for different purposes. I myself am a STATA user, but currently work in a government office where SAS is quite popular among the staff, who are mostly economists. However, most people here would never use SAS for statistical estimation / econometrics. These features in SAS seem to be less sophisticated than in STATA, whereas STATA corp is very good about incorporating new features into their program (e.g. stuff like GMM, quantile regression, clustered standard errors). Instead the staff here prefer it for manipulating/cleaning/merging datasets, particularly when those datasets are extremely large, e.g. 30gb or so. Big datasets are problematic for STATA because you have to load the entire thing into memory. Plus, in SAS you can use SQL queries, which are quite a bit more flexible than STATA’s programming language.

    Taylor Spears

    June 29, 2011 at 5:17 pm

  9. “Any other tips on seizing up available software?”

    Run Windows.

    kweed

    June 29, 2011 at 7:49 pm


Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Connecting to %s

Follow

Get every new post delivered to your Inbox.

Join 272 other followers