Timeline for Tags around categorical data coding / representation
Current License: CC BY-SA 3.0
43 events
when toggle format | what | by | license | comment | |
---|---|---|---|---|---|
Jun 11, 2020 at 14:30 | history | edited | CommunityBot |
Commonmark migration
|
|
Oct 26, 2017 at 18:31 | vote | accept | ttnphns | ||
Oct 26, 2017 at 16:01 | history | edited | amoeba | CC BY-SA 3.0 |
added 146 characters in body
|
Oct 26, 2017 at 15:38 | comment | added | amoeba | @gung I can't because it's started by ttnphns :) But I will ping him. Cheers! | |
Oct 26, 2017 at 15:13 | comment | added | gung - Reinstate Monica Mod | o-h is now a synonym, @amoeba. I agree about c-v; I didn't do that one. If you think we gotten everything we need to, you could accept this answer & indicate this thread is complete. | |
Oct 26, 2017 at 14:47 | comment | added | amoeba | @gung Thanks! I would perhaps create [one-hot] too. The second suggestion was [contrast-variables], but given that we have [contrasts] tag I am not sure if it's going to be helpful or rather confusing to have [contrast-variables] as a separate tag (mapped to c-e). | |
Oct 26, 2017 at 14:19 | comment | added | gung - Reinstate Monica Mod | @amoeba, I believe I can create a tag & make it a synonym at the same time. I have removed d-v as a synonym from c-d & made it a synonym of c-e. I also made i-v a synonym of c-e (see here). What are the other 2 synonyms you need? | |
Oct 26, 2017 at 12:54 | comment | added | amoeba | @gung Now that you are a mod, would you help finishing this? In particular, [dummy-variables] should be uncoupled from categorical-data and mapped to categorical-encoding instead (ttnphns explicitly agreed to this in the last comments under his answer). Apart from that, we could create up to three other synonyms listed in my answer, but this is rather optional; would we need to first edit some Qs to create these tags or can mods create synonym tags that do not yet exist? | |
Jul 28, 2017 at 13:07 | comment | added | mdewey | Amoeba I have tagged a few more questions found by searching for "indicator function". I only looked at ones with $>2$ votes and I only tagged them if they seemed to me to be about indicator functions rather than just using them as a notation. We now have 15 tagged. | |
Jul 28, 2017 at 0:55 | comment | added | Glen_b Mod | Since I agree with almost all of what is here I upvoted, but I also upvoted ttnphns' answer since I find myself in agreement with it (mostly out of considerations of how people will actually use the tags -- we have similar situations with a number of tags in the regression-constellation) | |
Jul 27, 2017 at 7:56 | comment | added | ttnphns | @mdewey, please come to share your opinion for my proposal to have "dummy-variables" tag. | |
Jul 27, 2017 at 7:55 | comment | added | ttnphns | @gung, please come to share your opinion for my proposal to have "dummy-variables" tag. | |
Jul 26, 2017 at 16:46 | comment | added | ttnphns | @amoeba, answer made | |
Jul 26, 2017 at 14:13 | comment | added | amoeba | @ttnphns We don't "have to be reconciled", but if you want to make your case for releasing [dummy-variables] as a stand-alone tag then post your own answer in this thread suggesting this course of action so that people could upvote/downvote it. Currently my answer is suggesting otherwise, and it already has 5 upvotes and 0 downvotes, so it looks like it has some support. If you choose NOT to post your own answer, then I would say yes, "we will have to be reconciled" with what I proposed :-) | |
Jul 26, 2017 at 12:01 | comment | added | ttnphns | @amoeba, if you say that we will have to be reconciled with the perspective of "dummy-variables as synonym of [categorical-encoding] tag" then, I say, all these tags: [contrast-variables], and [dummy-variables] = [indicator-variables] = [one-hot] might be made junior synonyms of [categorical-encoding]. | |
Jul 26, 2017 at 11:56 | comment | added | ttnphns |
@amoeba, make dummy-variables a synonym of our new [categorical-encoding] tag . I would repeat that I was never fully comfortable with that you proposal. My way was - and will be - to release [dummy-variables] and make it a separate, valid tag.
|
|
Jul 26, 2017 at 11:51 | comment | added | ttnphns | @amoeba, I see. You are asking about reserving some junior synonyms to tag [categorical-encoding]. Yes, [contrast-variables] is that candidate. I can create it, if you bid me. | |
Jul 26, 2017 at 11:49 | comment | added | amoeba | @ttnphns. [dummy-variables] exists and is a synonym of [categorical-data]. We need moderator help to remove this synonym mapping and make dummy-variables a synonym of our new [categorical-encoding] tag (see bullet point #1 in this answer). I am going to ask one of the mods to do this. My question to you is if we want to create any other synonyms of categorical-encoding (bullet points #2-4)? | |
Jul 26, 2017 at 11:47 | comment | added | ttnphns | @amoeba, I was thinking [dummy-variables] is the best because it is the oldest historically and most heard of. [contrast-variables] won't do because it is a wider meaning and the (almost) exact synonym to tag [categorical-encoding] which we already have. [indicator-variables] and [one-hot] are just synonyms to dummy variables. I think we could create those tags but make them to map into [dummy-variables], - here's my way. What do you say? | |
Jul 25, 2017 at 20:28 | comment | added | amoeba | @ttnphns Which of the following synonyms do you think are going to be useful to have: [indicator-variables], [contrast-variables], [one-hot]? Whatever you think is appropriate, could you please create these tags by applying them to 1 old thread, and then suggest them as synonyms here: stats.stackexchange.com/tags/categorical-encoding/synonyms? Then we can ask others to upvote. | |
Jul 25, 2017 at 20:25 | history | edited | amoeba | CC BY-SA 3.0 |
added 106 characters in body
|
Jul 25, 2017 at 11:43 | comment | added | mdewey | amoeba I have created it, re-tagged some, created tag excerpt and entry, will re-tag the rest later and then go on a hunt for any which need the tag as you suggest. | |
Jul 23, 2017 at 20:10 | comment | added | amoeba | @mdewey I don't have a strong opinion on that. Creating [indicator-function] is fine with me, but then we'd need to put this tag on some other questions that are not presently tagged with indicator-variables, e.g. stats.stackexchange.com/questions/149698 and stats.stackexchange.com/questions/145945 (I quickly searched for "indicator function"). | |
Jul 22, 2017 at 12:43 | comment | added | mdewey | Amoeba I have decided to retag the ones which i was sure about to categorical-encoding. This leaves six which are about indicator functions. I am not sure whether we need a new tag for them or whether we should just delete the tag from them. Thoughts? | |
Jul 18, 2017 at 11:56 | comment | added | mdewey | I will restart but if there are any about which I have doubts I shall leave them for discussion (actually I had already done that for some). | |
Jul 17, 2017 at 21:06 | comment | added | amoeba | @mdewey See last messages in chat. The misunderstanding is cleared, I think we can proceed, but feel free to join the discussion with whuber in chat if you want. | |
Jul 16, 2017 at 21:50 | history | edited | amoeba | CC BY-SA 3.0 |
added 50 characters in body
|
Jul 15, 2017 at 19:34 | comment | added | amoeba | @mdewey I see. I will ping whuber (who rolled back a couple of your edits) about it. | |
Jul 13, 2017 at 16:01 | comment | added | mdewey | Amoeba there does not seem to be general agreement about this as some of the ones where I deleted [indicator-variable] have had it restored. I think we may need a rethink so I have stopped work. | |
Jul 12, 2017 at 12:55 | comment | added | ttnphns | Amoeba, I created tag [categorical-encoding] and did the tagging of questions with it. | |
Jul 12, 2017 at 12:22 | comment | added | mdewey | [indicator-variables[ is now in progress | |
Jul 12, 2017 at 11:45 | comment | added | amoeba | @mdewey I think you can go ahead with [indicator-variables]. I'd say remove/replace this tag from abstract mathematical questions about indicator function, but leave it on questions about categorical-encoding (i.e. encoding categorical variables for statistical analysis). Once finished, we'll aim to make it a synonym. | |
Jul 10, 2017 at 12:14 | comment | added | amoeba |
@ttnphns Nobody objects to [categorical-encoding] , so we could use that. If you want to go ahead, I would suggest the following course of action: first of all, you create this tag and put it on 10-20 (or maybe 30-40, as you see fit) old threads that are "most important" in this topic (are well upvoted etc.). Once this is done and the tag is established, we will ask the mods to uncouple [dummy-variables] from categorical-data and to map it to categorical-encoding. In the meantime, mdewey can sort the [indicator-variables] tag. But creating+populating [categorical-encoding] is the first step.
|
|
Jul 3, 2017 at 15:22 | comment | added | ttnphns | @gung, just to mention it again - I personally don't like very much [coding-categorical-data] because - as I've said - people think coding = labeling by codes and will take the tag for that; while we are speaking of and mean a special...ehh.. "transformation". | |
Jul 3, 2017 at 15:10 | comment | added | gung - Reinstate Monica |
@ttnphns, any of these are about as good from my point of view. The ideal would be [coding-categorical-data] , but I think that's too long. If people prefer [categorical-encoding] , that's all right with me.
|
|
Jul 3, 2017 at 14:23 | comment | added | ttnphns | amoeba, they might as well use "encoding". Saying "encode" we simply stress the directional and completeness (or totality) nature of the action, thansitional process, not simply a symbolic substitution dictionary.com/browse/encode. "Coding" is all right, but "encoding" might sound better, for me. Maybe @gung shares his opinion? | |
Jul 3, 2017 at 13:31 | comment | added | amoeba | @ttnphns I am fine with categorical-encoding instead of categorical-coding, but note that terms like "effects coding", "dummy coding" etc. use the word "coding"... | |
Jul 2, 2017 at 13:36 | comment | added | ttnphns | @gung, yours is fine too. Still, after some hesitation, I'd stand for [categorical-encoding]. Reasons are subtle. 1) We better keep word "categorical" to keep immediate reference to "categorical-data", while "categories" might sound too general. 2) "Categories" might prompt (a layman) to think we are recoding each category independently, while in fact its not so, we recode a set of categories (a variable) into a set of encoded "contrast" variables where codes (values) are specially interdependent - depending of the type we choose (dummy, deviance, Helmert etc.) | |
Jul 2, 2017 at 13:00 | comment | added | gung - Reinstate Monica |
+1 this seems like a reasonable path forward for this difficult topic. Re the new name, @ttnphns's concern makes sense. I wonder if [encoding-categories] would be a viable option.
|
|
Jul 2, 2017 at 11:10 | comment | added | mdewey | Happy to look at the indicator variables ones if this goes ahead. | |
Jul 2, 2017 at 0:12 | comment | added | ttnphns | Let us wait a little while for somebody to enter the discussion. Then if we state we agree, I'd suggest you to perform the tags creation/(de)synonymizing (if you don't mind) while I then sort out questions to them. | |
Jul 1, 2017 at 23:33 | comment | added | ttnphns | Thank you a lot for the thorough response. 1) I'd vote then for [categorical-encoding], not [categorical-coding]. "Coding" is ambiguous, could be thought of as coding (labeling) categories by integers 1,2,.. or letters A,B,.., while we are speaking of the recoding a categorical variable into a set of elementary variables encoding the categories. 2) Though I personally think we better mark out [dummy-variables] as a separate tag too, I could change it for your opinion, especially if others support it. 3) Agree with all the rest points. | |
Jul 1, 2017 at 22:56 | history | answered | amoeba | CC BY-SA 3.0 |