Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

I'm going to school to be an actuary and I am just now starting to learn the basics of different statistical software packages. I have used both STATA and R, and I'm not sure which I like better. If there are any actuaries out there reading this what do you prefer? I currently use STATA for my econometrics class, and I have used R in my previous statistics class, and I must say I'm not sure which I like better. However I am very interested in improving my knowledge about whichever is most commonly used for the field I'm looking to go into. So any advice?

And I appologize to anyone that doesn't like my question because of the topic but I don't know where else to post it to get real advice.

share|improve this question
If you are not sure, choose R, it's free software. If you will learn how to do analysis with R, there will be no problems switching to STATA. – jem77bfp Nov 8 '12 at 9:58
R is about to become more useful to actuaries with this book: (Disclaimer: I authored one chapter.) – Rob Hyndman Jan 17 '14 at 3:12
up vote 13 down vote accepted

I passed a few of the actuarial exams before deciding that I did not want to be an actuary, so I don't work as an actuary, but as a statistician (and I hire statisticians). I use R, but Stata is a good program as well (I like R in that for the same low price I can have it installed on my work computer, my laptop, my home computer, the computer at church, etc.).

My sister who is an FSA (retired now) primarily used Excel for her work, but we get along despite this.

Why do you feel the need to focus on only one? When I interview prospective employees, if they only know one program (even if it is my favorite) I don't know if they can learn another if needed (or learn different parts of that one that they don't know yet). But, if they know 3 programs (I don't expect full expertise in all) even if my favorite is not included, then I am fairly confident that they can learn another if needed and learn more about the ones that they do know. So when I look at job candidates (granted not actuaries, but statisticians) I am more impressed by bredth in knowing multiple packages than depth in only 1 package. So I would recommend rather than choosing one to focus on that you develope your skills in both and probably add some basic knowledge in a 3rd (SAS would be good based on its history and wide spread use, but others could fill the 3rd slot as well).

share|improve this answer
thank you for that insight, that's a very good point and I will definitely do that. Do you know if SAS is made for Mac? I was told it wasn't. – Kyle Nov 15 '12 at 22:58
I believe that JMP is available for Mac, but not regular SAS. – Greg Snow Nov 17 '12 at 19:46
What other statistical software programs would you recommend to get a start on learning that are used in this kind of industry? I have 2 years of college left and I'd like to go out knowing a little bit about hopefully say... 3 or 4 programs. I'd definitely like to learn more about Stata and R. Is JMP a fairly good program? – Kyle Nov 23 '12 at 23:38
I imagine that the real actuaries use neither Stata nor R, but their own idiosyncratic industry tools that are certified for use by whatever professional board. SAS is more likely to have that than Stata or R; you would hate it though after having learned these two modern packages. – StasK Dec 11 '12 at 1:52
@StasK: Just noticed this comment. How true. SAS is based on punched cards and JCL from the 1970's or earlier. I've never gotten far with it because of the smell. Just bought Stata 13 yesterday and I really like it, though as a programmer I find it's not as flexible as R. (The whole dataset versus return variables thing makes me a bit claustrophobic.) Still, it's my second statistical tool now and I'd recommend it. – Wayne Jul 17 '13 at 20:47

Not an actuarial, but in case none wander by and answer your question...

What software does your school use? What software does your school offer classes in? Does your school help you to get STATA at a student price? When you read actuarial journals and textbooks, what tools do they use?

As jem77bfp said, R is free and you can continue to use it and explore it all you want. Professionals in most fields use multiple tools, and you can't tell what future employers might require (SAS, SPSS, etc), so it might be a good idea to branch out a bit now.

It wouldn't be unusual for a professional economist/statistician to use R for general-purpose analysis and graphing, JAGS/BUGS/STAN for MCMC analysis, ArcGIS for spatial data, Gephi or some other program for analyzing graphs, etc.

But the bottom line is that R is free and has a LOT of packages to do particular types of analysis. A couple of years ago I was in a graduate machine learning class where the teacher did everything in Matlab and recommended Matlab toolkits. (The school also sold student discount Matlab in the school store.) But I used R and did very well, while other students used Stata, Java, etc. I wasn't going to get any help from the teacher or TA's -- or even other students -- if I had a problem doing something in R, but that wasn't a concern for me.

share|improve this answer
Thanks for the insight, it's much appreciated. In all of my statistics classes almost all of my professors have varied from R, Excel, Stata, so I don't think there is a standard one that they use. But thanks for the info about the different programs that do different functions! – Kyle Nov 15 '12 at 22:59
There's a tradeoff between using too many tools and using the proper tool for the task at hand. But a stable of tools is always good, and if there's no standard in school and you don't see an overwhelming standard in the profession, R is free and flexible. Good luck! – Wayne Nov 16 '12 at 15:33

Look at job listings. SQL is the buzzword that comes up most often. I have seen some R listed, and I can't remember seeing Stata mentioned, that might be because my mind glosses over it since I've never used it.

share|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.