The analogy here: If what happened was that the ball happened to land near the right of the plinko board, then putting the ball through the same board isn’t going to make it on average go to the right again. Since some component of height is not determined by the genes passed on, that component is like our little ball.
If a family has consistently tall members though, this suggests that the cause is basically genetic enough that they’ll have tall kids again.
As tailcalled says in another comment:
their children will exhibit some regression to the mean … but … the children of the children will have the same expected trait level as the original children [as in: average children level = average grandchildren level, not children level = average grandchildren level]
You can think of this as the plinko board part being rerandomized already the first time, so what’s left in the average is just the stable non-plinko part.
The analogy here: If what happened was that the ball happened to land near the right of the plinko board, then putting the ball through the same board isn’t going to make it on average go to the right again. Since some component of height is not determined by the genes passed on, that component is like our little ball.
If a family has consistently tall members though, this suggests that the cause is basically genetic enough that they’ll have tall kids again.
As tailcalled says in another comment:
You can think of this as the plinko board part being rerandomized already the first time, so what’s left in the average is just the stable non-plinko part.