Me, for example. I ran across the notion of a stratified space at one point, for example, and found a convenient definition on wikipedia. It’s suprisingly reliable and extensive for math topics (here’s a nice description of exotic spheres, for example). Why should everything there be at an introductory level?
The pages on statistics you linked to look fine to me. Wikipedia is an online reference book, not a tutorial or textbook. Expecting it to teach you statistics is like expecting an encyclopedia to have sample problems and solutions.
The way I see it, an encyclopedia article should be accessible to anyone who picks it up, regardless of prior knowledge. Which means that explanation is integrated into the meaning of information.
What about things that just aren’t accessible to a random person, like the articles on stratified spaces and exotic spheres above? They’re useful to me and other mathematicians, and wikipedia does a pretty good job as a repository of definitions and results that aren’t as convenient to look up in textbooks or professional papers.
Actually I think Wikipedia does that well. From the article on regression analysis;
“In statistics, regression analysis includes any techniques for modeling and analyzing several variables, when the focus is on the relationship between a dependent variable and one or more independent variables. More specifically, regression analysis helps us understand how the typical value of the dependent variable changes when any one of the independent variables is varied, while the other independent variables are held fixed”
This is clearly an explanation as is the entire first section of the article. That first section contains a number of links that give clarification of several terms such as “dependent variable” and “independent variable” so that the reader can investigate subjects they might not be comfortable with.
If the article were to contain all of those sub-topics it would be unnecessarily lengthy and off topic and would significantly lose value for those readers who are the appropriate audience. If you are not comfortable with the article, Wikipedia has provided the links you need to review and come back when you have your side questions answered.
I think the problem is that you are expecting a simple, easily accessible discussion of a topic that is neither of those things. As I said earlier, you need to have the necessary foundational understanding to build upon – you can’t jump in the (semi) deep end and then blame the messenger for the fact that you don’t get it.
Actually I have more background than you think. I went to Wikipedia as a second step when I found my textbooks insufficiently clear or lacking sufficient examples. The test here should be whether the article is instructive to someone who doesn’t already understand the subject and I’ve found most of Wikipedia’s article on statistics deficient with regard to that standard.
Of course, if you think the wiki articles suck, you are but a click away from rewriting them to your satisfaction.
But as a math guy myself, the articles you linked are pretty much on level with learning the alphabet - they are already written as trivially as is possible to cover the subject,
Wow, that would be a neat trick, wouldn’t it? Why would I have bothered consulting it if I had already understood the subject well enough to rewrite the article?
I didn’t mean to insult and if it came off that way I’m sorry.
However;
We disagree here. I think the article does a very good job of explaining the subject in the first section and goes even further to provide links to supporting information. I really don’t understand what else the article could expand upon without becoming an tutorial complete with example problems and an answer key.
Which is probably why the only people who add stuff are the ones who are really hardcore about it. Everyone else either doesn’t click or doesn’t understand enough to add to it.
You could try Academic Earth that has online lectures (videos) on a lot of topics. They have several Khan Academy lectures as mentioned by Dangerosa above.
I haven’t looked into their material on economics and statistics, but their astronomy courses (from lecture series at Yale) are great, so you might find something.
Well, I’m confused, then. I’m looking over the first few paragraphs on the confidence interval article, and – although the prose isn’t very pretty – I can’t see how you’re required to know the topic already.
Okay, yes, it’s badly worded, but it doesn’t step beyond the technical grasp of someone who only has only basic statistical knowledge. A confidence interval is a procedure for obtaining lower and upper bounds that would contain the true parameter value some set proportion of the time. If that explanation completely loses someone, then I suggest that he wouldn’t get much out of knowing what a confidence interval is (just yet).
The article on regression doesn’t seem much worse. I could see the article on (say) the normal distribution confusing a complete layman, but that’s why there are links to, e.g., the articles on probability distributions, random variables, &c. Now – granted – there is material in all of these articles that would go over the head of the layman, but I just don’t see how some amount of that is or should be avoidable.