How can I learn SPSS?
March 22, 2014 4:45 PM Subscribe
I want to learn SPSS. What are my options?
This is for professional reasons. I come from a humanities background (PhD) and do not have any background in stats. But, I think learning SPSS could be helpful for my current career path in private sector research. I enrolled in a MOOC on baseball analytical (I love baseball and find sabermetrics fascinating) but it uses R, not SPSS. What are some good resources for me to get a grasp of the fundamentals?
This is for professional reasons. I come from a humanities background (PhD) and do not have any background in stats. But, I think learning SPSS could be helpful for my current career path in private sector research. I enrolled in a MOOC on baseball analytical (I love baseball and find sabermetrics fascinating) but it uses R, not SPSS. What are some good resources for me to get a grasp of the fundamentals?
Best answer: In addition to the Lynda class (or something similar), as you go through your Sabermetrics MOOC, try and figure out how to do the same tasks in SPSS.
posted by mskyle at 5:12 PM on March 22, 2014 [1 favorite]
posted by mskyle at 5:12 PM on March 22, 2014 [1 favorite]
I know there is a rule against answering questions other than the one asked, but in all practicality
I think this matters: are you sure that you will have access to SPSS when you need it as your career progresses? If that career has a freelance or portfolio aspect, or any other situation where you might find yourself in need of an SPSS license and not be able to afford one, then I'd really strongly recommend starting off down the R road. If you're sure that SPSS is the tool for your job - and I know it has significant sectoral support/inertia/lock-in - then great...
... but have a read of this article, and in particular the comment down the page from Joseph Hilbe:
"For what its worth, I’ve seen a lot of software over the years, From 1997 to 2009 I was Software Reviews Editor for The American Statistician, and received free stat software to review and use for 12 years and pretty much still ongoing. I turn 70 this year, so have watched the development of statistics and statistical software for quite awhile. I would not purchase stock in SPSS, nor in SAS for that matter. SAS is ingrained in the pharmaceutical and healthcare industry, and in much of “big” business, folks have jobs as SAS programmers, or SAS analysts. Too much is invested by business to simply drop it. But that’s not the case as much with SPSS. With more Revolution-like businesses developing in the next decade, I believe R will predominate as the Franca Lingua statistical software."
posted by cromagnon at 6:46 PM on March 22, 2014 [2 favorites]
I think this matters: are you sure that you will have access to SPSS when you need it as your career progresses? If that career has a freelance or portfolio aspect, or any other situation where you might find yourself in need of an SPSS license and not be able to afford one, then I'd really strongly recommend starting off down the R road. If you're sure that SPSS is the tool for your job - and I know it has significant sectoral support/inertia/lock-in - then great...
... but have a read of this article, and in particular the comment down the page from Joseph Hilbe:
"For what its worth, I’ve seen a lot of software over the years, From 1997 to 2009 I was Software Reviews Editor for The American Statistician, and received free stat software to review and use for 12 years and pretty much still ongoing. I turn 70 this year, so have watched the development of statistics and statistical software for quite awhile. I would not purchase stock in SPSS, nor in SAS for that matter. SAS is ingrained in the pharmaceutical and healthcare industry, and in much of “big” business, folks have jobs as SAS programmers, or SAS analysts. Too much is invested by business to simply drop it. But that’s not the case as much with SPSS. With more Revolution-like businesses developing in the next decade, I believe R will predominate as the Franca Lingua statistical software."
posted by cromagnon at 6:46 PM on March 22, 2014 [2 favorites]
An anecdotal warning for you: I thought I could get through my university statistics course by focusing on SPSS rather than the theory. I got good at SPSS but failed the major exam and only passed by the skin of my teeth.
Sounds like you're on the right track with the stats course, but you might want to get through it first and worry about switching from R to SPSS later.
(Of course this is a sample size of 1).
posted by fonetik at 6:46 PM on March 22, 2014 [1 favorite]
Sounds like you're on the right track with the stats course, but you might want to get through it first and worry about switching from R to SPSS later.
(Of course this is a sample size of 1).
posted by fonetik at 6:46 PM on March 22, 2014 [1 favorite]
Raynald Levesque's site spsstools.net is fabulous. On the front page he has links to a newbies corner and to many tutorials. In addition, he's written a book called SPSS Programming and Data Management which is available for free downloading.
posted by jasper411 at 9:47 PM on March 22, 2014
posted by jasper411 at 9:47 PM on March 22, 2014
Learn to use R. It's the default in the world of stats professionals. (Source: I've taught graduate-level statistics for nearly 15 years.)
posted by anaphoric at 10:00 PM on March 22, 2014 [2 favorites]
posted by anaphoric at 10:00 PM on March 22, 2014 [2 favorites]
I found that pasting each operation before I ran it helped me understand exactly what I was doing.
posted by Cheese Monster at 3:25 AM on March 23, 2014
posted by Cheese Monster at 3:25 AM on March 23, 2014
Every few years, there is a statistical analysis program that promises to fly higher and faster than anything before. I tend to think of the comparison between CDs and MP3s. The quality of the audio between them is almost indistinguishable even though the format has changed. With that said, there's this:
Robert Muenchen, the author of R for SAS and SPSS Users, has published this week an article in which he compares the popularity/market-share of many of the common statistical packages including R, SAS, SPSS and many others.
The full article is available on r4stats.com at: ”The Popularity of Data Analysis Software“
In his article, Robert compares the statistical packages using various matrices (and graphics), detailing:
•Sales & Downloads
•Language Popularity Measures:◦Internet Discussion (mailing lists, forums…)
◦Blogs (were he mostly relies on R-bloggers and SAS-x)
◦Internet Search
◦Web Site Popularity
◦Surveys of Use
◦Impact on Scholarly Activity
•Growth in Capability
•IT Research Firms
•Job Market
Robert concludes his articles with the following words:
"By most of the measures discussed here, R is competing well with the commercial software vendors. However, I advise not over generalizing from this data. SAS and SPSS continue to dominate the corporate world and Stata is doing quite well in the scholarly arena. Each of these packages is dominant in one market or another.
posted by CollectiveMind at 9:27 AM on March 23, 2014
Robert Muenchen, the author of R for SAS and SPSS Users, has published this week an article in which he compares the popularity/market-share of many of the common statistical packages including R, SAS, SPSS and many others.
The full article is available on r4stats.com at: ”The Popularity of Data Analysis Software“
In his article, Robert compares the statistical packages using various matrices (and graphics), detailing:
•Sales & Downloads
•Language Popularity Measures:◦Internet Discussion (mailing lists, forums…)
◦Blogs (were he mostly relies on R-bloggers and SAS-x)
◦Internet Search
◦Web Site Popularity
◦Surveys of Use
◦Impact on Scholarly Activity
•Growth in Capability
•IT Research Firms
•Job Market
Robert concludes his articles with the following words:
"By most of the measures discussed here, R is competing well with the commercial software vendors. However, I advise not over generalizing from this data. SAS and SPSS continue to dominate the corporate world and Stata is doing quite well in the scholarly arena. Each of these packages is dominant in one market or another.
posted by CollectiveMind at 9:27 AM on March 23, 2014
Response by poster: Thanks for all the advice. Regarding the suggestions for R, the sabermetrics course I've signed up for covers the basics. However, there's good reason I'm looking at SPSS as well.
posted by synecdoche at 1:53 PM on March 23, 2014
posted by synecdoche at 1:53 PM on March 23, 2014
This thread is closed to new comments.
posted by jadepearl at 5:00 PM on March 22, 2014