Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 5 down vote favorite
2

I am looking for a self-study site on the web that will allow me to verify my understanding of some basic probability and stats concepts and operations.

What I would like is a site with data and problems (along with the solutions) that I could use to practice my skills (such as regression methods/analysis, pairwise t-tests, computation and interpretation of confidence intervals, etc.). I've seen workbooks like this, but the data is not available for me to import into R or Excel.

Surely there must be a site like this on the internet, arranged by topics for study, but somehow I have not been able to find it. Also, if anyone knows of a good workbook that comes with data (on CD or via web) I'd be interested in it too.

Re tools, I'll be using R and Excel - so pointers re these would be great too.

Thanks!

share|improve this question
Shouldn't this question be made CW? – chl♦ Mar 15 '11 at 11:33
I'm still somewhat new to this site .. what does it mean to make something a Community Wiki (question?) ? I understand it doesn't contribute to reputation(?) but other than that, does it matter? (I have been reading the FAQ, but some of the mechanics of this site are still a bit unclear to me). Thanks. – Levon Mar 15 '11 at 12:48
It's just that there might not be a "best" or good response, and that arguments can be made arbitrarily subjective. It doesn't mean, however, that the question in not interesting per se; asker/users won't earn rep from it, but they still get the opportunity to gain badges and the like. – chl♦ Mar 15 '11 at 13:57

3 Answers

up vote 5 down vote accepted

The Statistics topic area on Wikiversity is worth a look. It's got a long way to go before it's a comprehensive stand-alone syllabus, to be honest, but some of the Courses are more advanced than others, and when there's not much material as yet there are often links to free online resources.

share|improve this answer
up vote 6 down vote

If you are interested in Statistical Machine Learning, which seems to be THE thing these days, Tibshirani, Hastie, and Friedman's book is an invaluable resource. It is the latest edition and has a self contained website devoted to it.

share|improve this answer
up vote 3 down vote

I realise that this may not be what you are looking for, but R core and all packages come with data sets on which to practice the functionalities in each package. Many of these data sets are quite famous, and often a link is given to the paper in which the data are described. You could use these datasets in R and then after you finish your analysis look at what the authors of the paper did with the same data.

That being said, its rare for there to be a right answer in any real data analysis problem, mostly one learns by realising that your techniques were not appropriate and re-iterating until one reaches some level of statisfaction. Obviosuly this is a moving target though, as your skills increase an older dataset may yield new insights.

share|improve this answer
1  
In line with your response, the HSAUR textbook deserves some attention. – chl♦ Mar 15 '11 at 11:41
@chl thats totally correct, i'd forgotten about that. The books on CRAN generally are often quite good. – richiemorrisroe Mar 15 '11 at 11:49

Your Answer

 
discard

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.