Timeline for How to get correlation between two categorical variable and a categorical variable and continuous variable?
Current License: CC BY-SA 3.0
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 30, 2021 at 11:08 | comment | added | Recap_Hessian | aov(y~x) is analogous to lm(y~x) in interpretation, and the p-value for lm model output is interpreted as whether there is relationship between x and y, i.e. smaller the p-value, stronger the relationship (or higher the correlation). Then I fail to see how p-value here can be taken as the "measure of correlation" as you stated.... | |
| Mar 1, 2020 at 15:55 | comment | added | Loochie | Mann-Whitney-U is a non-parametric test. It can be used in case the data is not normally distributed and is too small to apply Independent Samples t-test(as categorical variable is binary). | |
| Aug 29, 2018 at 19:40 | comment | added | ebrahimi |
Besides, could you please let me know If the categorical feature is a binary one, Mann-Whitney-U test should be used?
|
|
| Aug 29, 2018 at 19:28 | comment | added | ebrahimi |
@AlexeyGrigorev If our data is not normally distributed, should kruskal-wallic be used instead of one-way anova? Thanks in advance.
|
|
| S Aug 6, 2017 at 19:44 | history | suggested | AvidLearner | CC BY-SA 3.0 |
Updated broken link
|
| Aug 6, 2017 at 19:30 | review | Suggested edits | |||
| S Aug 6, 2017 at 19:44 | |||||
| Mar 13, 2017 at 18:35 | comment | added | gented | Your first example is NOT about categorical vs categorical, rather it is categorical vs numerical, in fact you are looking at city against number of males (females, respectively) which is numerical. Categorical vs categorical would be, say, city vs colour of the eyes or shapes or anything else, but by no means would it be the number of representative of the gender. | |
| Nov 3, 2016 at 16:56 | history | edited | Alexey Grigorev | CC BY-SA 3.0 |
deleted 7 characters in body
|
| Oct 3, 2016 at 5:22 | comment | added | KarthikS | Fasntastic answer by @Alexey. I read up polychoric/polyseries correlations online after reading your comment. They are technique for estimating the correlation between two latent variables, from two observed variables. I don't think that is what you asked for, and it is not comparable to Alexey's answer. | |
| Sep 23, 2014 at 2:51 | vote | accept | GeorgeOfTheRF | ||
| May 15, 2015 at 17:17 | |||||
| Aug 17, 2014 at 14:04 | comment | added | Alexey Grigorev | I'm not aware of these things, sorry. | |
| Aug 17, 2014 at 9:58 | comment | added | GeorgeOfTheRF | Thanks Alexey for the details. Based on more research i found about polyserial and polychloric correlation. How is your approach better than these? Please explain | |
| Aug 5, 2014 at 15:55 | history | edited | Alexey Grigorev | CC BY-SA 3.0 |
added crammer's v
|
| Aug 4, 2014 at 9:42 | history | answered | Alexey Grigorev | CC BY-SA 3.0 |