- Joined
- Jan 30, 2009
- Messages
- 4,218
- Reaction score
- 13
Do any of y'all use sas in addition to or in place of SPSS? I learned SPSS in undergrad and am learning SAS now and, well.... Code? Really? Are there any redeeming features to SAS over SPSS?
SAS vs SPSS
- Thread starter loveoforganic
- Start date
- Joined
- Sep 6, 2009
- Messages
- 1,504
- Reaction score
- 993
When I use SPSS I use syntax anyway, so I don't really mind programming in SAS. I like a full record of all the analyses I do. I primarily use SAS but also occasionally use other programs.
Even though I primarily use SPSS (and yes, it is definitely easier), I actually wish we would move away from it as a field and just make everyone learn SAS or R. Yes, the learning curve is steeper but I actually think it helps people better understand their analyses and it opens a lot more doors. I keep telling myself I'm going to find time to sit down to REALLY learn SAS and R well enough I can abandon SPSS. Thus far, it hasn't happened and at my current state it is just much easier to pop into SPSS if I just need to do something basic.
SPSS has a lot of limitations and is usually at least a couple years behind SAS on implementing new things. If you get into more advanced techniques, you will quickly run into things that are difficult/impossible to do in SPSS. If all you plan on doing is ANOVA/Regression/etc. though it really doesn't matter. If you want to run a 3-level generalized linear mixed model....I'd look to SAS for that one.
Edit: Also agree with the above, even if you stick to SPSS definitely use the syntax. Even if you pull things up through the menu system and "paste" it rather than writing it yourself (I still do that for many things), it is incredibly helpful to have a record of what you did if it was in any way non-standard.
SPSS has a lot of limitations and is usually at least a couple years behind SAS on implementing new things. If you get into more advanced techniques, you will quickly run into things that are difficult/impossible to do in SPSS. If all you plan on doing is ANOVA/Regression/etc. though it really doesn't matter. If you want to run a 3-level generalized linear mixed model....I'd look to SAS for that one.
Edit: Also agree with the above, even if you stick to SPSS definitely use the syntax. Even if you pull things up through the menu system and "paste" it rather than writing it yourself (I still do that for many things), it is incredibly helpful to have a record of what you did if it was in any way non-standard.
- Joined
- Jan 30, 2009
- Messages
- 4,218
- Reaction score
- 13
Thanks for the replies 🙂 Really happy to know SAS isn't just a non-user friendly version of SPSS. Will help pushing through learning some of it somewhat more bearable
- Joined
- Mar 15, 2010
- Messages
- 25
- Reaction score
- 0
If you are looking for a resource for learning SAS, I found "The Little SAS Book: A Primer" to be quite helpful. While I hated learning SAS, now that I have it down I find that it is so useful and definitely worth the learning time. It also provides a good basis for learning the others (R, etc). Good luck!
- Joined
- Apr 26, 2003
- Messages
- 943
- Reaction score
- 155
I was somewhat forced to learn SAS because it is what my advisor uses, but I am quite pleased that I did (I haven't learned R yet, but it is on the agenda). In my master's thesis I had a big missing data problem, and it was great being able to do multiple imputation in SAS. You can't do much more than mean imputation in SPSS without paying $500 for an add-on. As others have mentioned, SAS gives you access to the latest analyses, which can certainly help you get your work published, or get it published in a more prestigious journal!
