Ten fold

« first day (1704 days earlier) ← previous day next day → last day (3599 days later) »

amoeba

00:14

@January's question about David Colquhoun's recent paper on p-values stats.stackexchange.com/questions/143325 where I posted an answer some days ago, drew attention of @DavidColquhoun himself, resulting in a long discussion between us in the comments. Perhaps it will be of interest to some. If anybody reads that, I would be interested to know what you think.

5 hours later…

Howcan

05:16

Hi guys!

4 hours later…

Glen_b

08:54

@Howcan hi ... were you after anything, or just wanting to say hi?

Howcan

@Glen_b
Both! I was wondering whether there are any research areas for someone with an introductory knowledge of statistics, calculus and linear algebra. I know that this isn't reasonable—I don't mean research research, just a possible project that deals with theory more than practice.

We're required to do a final project for my statistics class which is generally obtaining some data, running tests, and what not. I wanted to focus on something more mathematical rather than applied. Like I said, I know that I don't have nearly enough knowledge for any legitimate (or even bad) research. I'm …

1 hour later…

Glen_b

10:00

I'm really not sure I can offer helpful advice.

1 hour later…

Glen_b

11:18

Here:

Q: Test for differences in distributions; three samples; multimodal distributions

Here is a question on how to test for differences in distribution between three samples of multimodal distributed data. I have conducted a dictator game (http://en.wikipedia.org/wiki/Dictator_game) where respondents have been randomized into three treatment groups. All samples show bimodal/multi...

Strictly speaking, a correct answer to: Do you know if there is a version of the K-S test that tests for differences in distributioins across >2 samples? is either "yes, I do", or "no, I don't".

Maybe I should edit to "Is there a version ..." which would at least invite more useful answers.

3 hours later…

Andy

14:14

Does somebody have an idea as to why my flag of this post (stats.stackexchange.com/a/146881/26338) was disputed? Clearly this is just an edit to the question which ended up as an answer and does not provide an actual answer to the question. Also Xian had remarked this.

1 hour later…

Andy

15:41

Just to give my reason for the flag: the question was about the interpretation of probabilities that sum to more than one in a choice model (does it imply misspecification?) and whether some normalization is required. The current answer says "if I press that button instead of the other then it looks fine" but without any explanation which would benefit future readers.

8 hours later…