Skip to main content

You are not logged in. Your edit will be placed in a queue until it is peer reviewed.

We welcome edits that make the post easier to understand and more valuable for readers. Because community members review edits, please try to make the post substantially better than how you found it, for example, by fixing grammar or adding additional resources and hyperlinks.

5
  • $\begingroup$ There is a legitimate question of whether, and to what degree, these curvilinear fits improve on a model of independence. Now that you have established (at least visually) that the residuals are nicely behaved--symmetric, short-tailed, no outliers--why not formally test your regression against the intercept-only null? $\endgroup$ Commented 10 hours ago
  • $\begingroup$ @whuber, what is the best tool/function to test this? $\endgroup$ Commented 9 hours ago
  • $\begingroup$ For these data, the standard linear regression F test would work fine. If you want a nonparametric solution (requiring fewer assumptions), a permutation test inspired by the standard test would be excellent. $\endgroup$ Commented 8 hours ago
  • $\begingroup$ @whuber I am happy to regard these tests as suggestions for the OP. My point is only to guess that different techniques will confirm the general shape. $\endgroup$ Commented 7 hours ago
  • $\begingroup$ Well, sure--but that doesn't imply that the "general shape" is an indicator of non-independence. The issue is whether this shape might have arisen through chance by sampling a pair of independent variables. $\endgroup$ Commented 7 hours ago