Relearning Statistics

[radspamultra]

Hi all,

I've never joined a forum and introduced myself, but I feel like I want to be part of this community.

As a bit of background, I am about 10 years out of college where I obtained a BS in Statistics. I found my calling in another field and pursued an advanced degree outside of statistics. I'm now working in another field (medical imaging) and considering a research tract with possible machine learning. I never applied what I learned in Statistics to real world problems or data sets and I constantly feel regretful for it. I feel as though I have a sense of the vocabulary used in statistical methods but wouldn't be able to accurately apply them if needed.

I want this to change. I guess I'm curious if anyone else has been in this situation and successfully revitalized their statistics skills. I understand at this point it will primarily rely on self motivation. However, I feel there are a lot of good resources out there. I'm curious if there are good question sets with solutions to help solidify the theory as well as math component. I'm upset at myself for not reinforcing such a useful skill, but I don't think it's too late! This seems like a vibrant and robust community and looking forward to talking with you guys.

 

[hlsmith]

Hello @radspamultra

Welcome to the forum. I am a doctorate-level epidemiologist obsessed with (bio)stats and machine learning. I got a decent biostats intro at University, but I have found myself studying stats almost everyday since - so a slightly different track, but I definitely fall under the self-study label. I am mostly applied that is why I try to study the principles regularly. Looking forward to seeing your contributions and questions.

 

[noetsi]

I spent much of my life in graduate programs and learned most of my statistics in books and forums outside of them.

I think the answer to your question is determined by if you want to do academic or organizational statistics. They vary in that most organizations are not going to do cutting edge statistics academics love, but the problem will be unclear and the data will be questionable. And you will spend much of your time getting the data you need....