Tagging - 2020-09-19

7:51 AM

new-tag Three new tags contingency-tables, odds and odds-ratio were created by Michael Hardy.

0

Q: Elegance rather than dumb brute force in the solution of a simple probability problem

ok, I did this problem in a plodding pedestrian way, and now I have two questions: Is there an intelligent and elegant way? (I suspect there is.) What's the quick, intelligent, and elegant way to see that only one of the two solutions of a certain quadratic equation satifies the constraints impo...

Contingency table

In statistics, a contingency table (also known as a cross tabulation or crosstab) is a type of table in a matrix format that displays the (multivariate) frequency distribution of the variables. They are heavily used in survey research, business intelligence, engineering and scientific research. They provide a basic picture of the interrelation between two variables and can help find interactions between them. The term contingency table was first used by Karl Pearson in "On the Theory of Contingency and Its Relation to Association and Normal Correlation", part of the Drapers' Company Research Memoirs...

Odds ratio

An odds ratio (OR) is a statistic that quantifies the strength of the association between two events, A and B. The odds ratio is defined as the ratio of the odds of A in the presence of B and the odds of A in the absence of B, or equivalently (due to symmetry), the ratio of the odds of B in the presence of A and the odds of B in the absence of A. Two events are independent if and only if the OR equals 1, i.e., the odds of one event are the same in either the presence or absence of the other event. If the OR is greater than 1, then A and B are associated (correlated) in the sense that, compared...

With respect, I don't think this question requires the creation of three new tags. — Integrand 10 hours ago

@Integrand : But possibly those are tags that ultimately ought to exist, since they are standard names of standard concepts. $\qquad$ — Michael Hardy 10 hours ago

Possibly, but I'm quite skeptical 'odds' and 'odds-ratio' are sufficiently distinct. I don't want to go off on a tangent from this question- maybe we could move this conversation to chat or meta- but do you think there are enough questions about similar concepts on this site to warrant the tags? — Integrand 10 hours ago

@Integrand : You're wrong. They are quite distinct in standard usage, and you should read the two definitions above before you say more about that. It makes the distinction clear. $\qquad$ — Michael Hardy 10 hours ago

@Integrand : Maybe there ought to be enough such questions. — Michael Hardy 10 hours ago

Integrand

1:36 PM

This is an unusual question. I looked at the link MH posted in the comments and it's plausible but kind of a stretch to tag this as alg.geo. More relevant are the creation of odds and odds-ratio; I think at least one of these needs to be eliminated, and possibly merged with probability.

As for [tag:contingency-tables], there are 127 questions that mention it, most tagged either just [tag:probability] or [tag:statistics]. So maybe there's something there.

Tl;dr: eliminate [tag:odds-ratio] for certain, probably eliminate [tag:odds] soon

Martin Sleziak

I see that I missed the comments related to algebraic-geometry for that question.

I don't understand where the part of this problem that leads to the tag algebraic-geometry is. Could you clarify why you think this problem relates to algebraic geometry? — KReiser 16 hours ago

@KReiser : In population genetics, one uses algebraic geometry to understand the nature of the probabilistic dependences among the random variables in $n_1 \times \cdots\times n_k $ contingency tables. See _Algebraic Statistics for Computational Biology_ by Pachter and Sturmfels. $\qquad$ — Michael Hardy 15 hours ago

Integrand

I think it would help MH's case if he clarified and generalized the question substantially

Martin Sleziak

@Integrand IIRC markdown doesn't work for multiline messages. They have also disadvantage that links do not work in transcript. I have tested this in Sandbox a bit: chat.stackexchange.com/transcript/1/2020/9/19

This is why odds-ratio and other tags are not displayed as tags in that message.

Integrand

Like, if he wants to have a question about the theory of Grobner bases and mention the applications to population genetics, and then make a case for contingency-tables and so forth, that would be better

Martin Sleziak

As far as these specific tags go, it would definitely be useful to hear from people who frequent questions related to probability. That is well out of my area, so I won't be able to give some advice there. Let's hope somebody else will notice the discussion about these tags.

Integrand

1:43 PM

As is, it looks like overkill for a somewhat straightforward question. (Thanks for the advice @MartinSleziak)

Martin Sleziak

We are discussing several of these tags here in chat: everyone is welcome to join — Integrand 1 min ago

As a side note, if you use link like this, it would link to today's transcript: chat.stackexchange.com/transcript/3740/2020/9/19

The link which you have used links simply to this room - so if somebody used it a week or two later, they will go into the room which contains already some different discussion. (But it is certainly not too important - maybe after a week or two the comments will already be gone.)

I have collected a few comments on various possibility how to link to chat here: chat.stackexchange.com/rooms/19138/conversation/links-to-chat (Sorry for the digression from the topic - this was mainly about using chat and not about tags.)

I have some other things to do (and I do not have much to contribute to the topic at hand). See you later!

Feeds

4:55 PM

0

Q: Proposing several synonyms

I am using this thread to draw more attention to two synonyms I proposed on the tag management thread. Make finite-difference-methods a synonym of finite-differences. The new tag (methods) was created about three years ago; the old one (differences) has been around for almost 10 years. Methods...

support tag-management

Martin Sleziak

5:40 PM

I'll just repeat the same thing which I have mentioned also in chat. Tag synonyms are approved by users only rarely, AFAICT there are only 26 synonyms on this site. More typical scenario is that a synonym is discussed on meta (or in chat) and when the mods eventually approve the synonym if they see a consensus or they consider the synonym reasonable. (The fact that most synonyms goes through meta rather than just through voting ... — Martin Sleziak 15 mins ago

... also has some advantages, since on meta it is possible for users to discuss those synonyms - while there is no possibility to leave a comment on the voting page with the proposed tag synonym.) This is meant as a comment on tag synonyms in general - no specifically on the synonyms mentioned in this post. — Martin Sleziak 14 mins ago

KReiser

7:12 PM

My perspective on the algebraic-geometry tag on this question: I made a cursory review of the book MH mentioned in the comments, and it does appear that some algebraic geometry is actually used in this field. I am still somewhat skeptical of the tag's application to this question - it doesn't appear like there are direct applications to this question (from the post, it seems like the only algebraic geometry present in this question is solving a system of 3 linear equations and a quadratic).

Integrand

7:54 PM

@KReiser I agree. How do you feel about contingency-tables and the odds ones? I would be ok with tables but neither of the odds.

KReiser

8:19 PM

@Integrand I am very far from being a probabilist and do not really feel qualified to judge whether these should exist as independent tags or not.

Transcript for

$Mathematics$ Tagging