Question about statistics

[Buckeye]

Hi all,

I'm not exactly sure of the question I want to ask. I'm planning on pursuing a master's program for statistics beginning in the fall. But I have not committed yet. I joined this forum with the hope of seeing the application of statistics. But I've been seeing more of "which test to run when" without much elaboration of what's actually being studied. And these are questions that I haven't encountered yet. It's normal for things to seem mundane if I haven't studied them yet? I hope this makes sense. So, I guess what I'm asking is: is there a journal or magazine that would be better suited for me? In terms of keeping my interest in subject.

It's been a few years since I've taken an undergraduate statistics course (I've taken two). But I've been doing some self study to prepare myself. I currently tutor mathematics. So, I'm not completely removed from the concepts. Any advice is appreciated.

 

[spunky]

I feel this is very much discipline-dependent and what you're actually doing.

For instance, in my job, this is literally what I do all day. If I find a project interesting enough I usually ask the person to share the data with me so I can do the analysis myself and get something out of it (coauthorship in a publication, conference presentation or sometimes I just do it because I've never encountered the problem before and I want to learn about it). But if it's very straightforward/not very interesting (which is like 95% of the other projects) then it's really just pointing people to the right test or method and what they should be looking for before analyzing data.

But Statistics is a very, very vast field so I'm sure whatever people do with it depends on what they are working on. For instance, I find it hard to believe that a statistician or data scientist working for Google or Facebook is concerned with whether this or that data should be analyzed using a t-test or not.

 

[ondansetron]

I think you're getting a biased view from this forum. I joined this primarily with the intention of being able to help other people and with the benefit that I would learn a few things along the way. If you're at a university, your library should have journal access to many publications. Try looking up some stuff from the American Statistical Association. They have a myriad of journals from technical to practical. Chance and Significance are two practical publications I can think of off the top of my head. If you want, you could buy a student membership for around 20 bucks to the ASA. You'll get access to a bunch of their message boards where there's heavy involvement from PhD statisticians in various fields. They have some interesting discussions that are good to read, but the journal access is what I primarily like.

Long story short: I think this forum has more of a tutoring aspect because of the fact that anyone can stumble upon it on Google--just as I did. You get the homework questions, but you're not going to learn a ton about the actual project. I think you'll learn a lot more of the why and how in an MS Stats program whereas the lower-level stuff is focused on general "what test" kind of stuff. The higher level learning will help you know when that general rule doesn't work, or why it's a general rule. This is mostly my experience from the few grad stats classes I've taken. You understand the way it works and why and then you get a better idea of when you can use it.

Hopefully I addressed some part of your post

 

[Buckeye]

Thank you very much for the replies. ondansetron: I will look into ASA. I think that will be very helpful. Sometimes I have to remind myself of why I like this subject and it's because of the questions that are answered. Not necessarily the math. Any more insight is appreciated.

 

[ondansetron]

Thank you very much for the replies. ondansetron: I will look into ASA. I think that will be very helpful. Sometimes I have to remind myself of why I like this subject and it's because of the questions that are answered. Not necessarily the math. Any more insight is appreciated.

If you're doing an MS, you'll need the math and your background will certainly be helpful, but you can definitely take an applied approach to what you do with the degree. I think many MS programs include a couple consulting seminars or courses, which I would take one or two if I were in the position, even if it meant paying a little extra for additional credit hours. I think the math will let you really understand what's going on and how you can get creative in new situations (or just realize that certain things can be applied in different ways). At least, that's what I've felt has worked in my experience.

I think it was in an issue of Chance or Significance where they did some stuff to look at winning tennis tournaments (or other sports related topics with modeling and simulations) and another article on some guy allegedly winning millions of dollars at a casino using a unique betting strategy (seeing if it was reasonably probable to do as he claimed). Then, of course, you can find original papers on methods we use (like Kruskal-Wallis H-test) in the more technically oriented publications. I hope you're able to find some answers, but if not, maybe try to meet with some people at the program you're looking to attend. They might be able to let you do a ride along with some industry friends (bring-a-prospective-student-to-work day ) or they might be able to give you background on what they've done both in academia and in the general market.

 

[Buckeye]

I'm visiting the campus this weekend in fact. So, this will help me. I became interested in statistics because of it's application. After a BS in theoretical math, I realized that the proof writing and such wasn't for me. Although, I'll see some theory in the program I'm pursuing.