This code

>>> import seaborn as sns; sns.set(style="ticks", color_codes=True)
>>> iris = sns.load_dataset("iris")
>>> g = sns.pairplot(iris)

gives this figure

enter image description here

The seaborn doc gives this explanation about the figure above.

Draw scatterplots for joint relationships and histograms for univariate distributions.

I understand covariance or correlation describes some kind of relationships between multiple random variables.

I cannot understand what is joint relationships.

Are "joint relationships" and "relationships" the same, in the context of probability distribution?

Is "joint relationship" a canonical statistics term?

Are covariance and correlation this kind of joint relationships?

Is this set of scatterplots a visualization of covariance or correlation?

I googled "joint relationship" and find nothing explains whether "joint relationships" and "relationships" are the same.

  • $\begingroup$ Replace "joint" with "paired". There is no deeper meaning. $\endgroup$ – user2974951 Oct 2 '19 at 11:11
  • 1
    $\begingroup$ Generally "joint" means "among two or more." Through its use of univariate and bivariate plots, this scatterplot matrix gives some, but not all, information about the joint relationship of four variables: it sheds little light on the three-variate or four-variate relationship. $\endgroup$ – whuber Oct 2 '19 at 13:49
  • $\begingroup$ @user2974951 Thanks for your comment. Does "paired" mean "pairwise" $\endgroup$ – whnlp Oct 3 '19 at 0:45
  • $\begingroup$ @whuber Thanks for your comment. Are "joint relationships" and "relationships" the same, in the context of probability distribution? $\endgroup$ – whnlp Oct 3 '19 at 0:49
  • $\begingroup$ @whnlp You can say pairwise - relationship between two variables. $\endgroup$ – user2974951 Oct 3 '19 at 6:35

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.