[R] Variance of multiple non-contiguous time periods?

[Jim Lemon]

On Fri, 31 Oct 2014 07:19:01 AM Jim Lemon wrote:
> On Wed, 29 Oct 2014 05:12:19 PM CJ Davies wrote:
> > I am trying to show that the red line ('yaw') in the upper of the two
> > plots here;
> > 
> > http://i.imgur.com/N4Xxb4f.png
> > 
> > varies more within the pink sections ('transition 1') than in the 
light
> > blue sections ('real').
> > 
> > I tried to use var.test() however this runs into a problem because
> > although the red line doesn't vary much *within* any particular 
light
> > blue section, it does vary a lot *between* light blue sections.
> > 
> > For example, in the light blue section around t=90 the red line
> 
> doesn't
> 
> > move much & likewise in the light blue section around t=160 the
> 
> red line
> 
> > doesn't move much. But between these two sections the red line
> 
> has moved
> 
> > substantially.
> > 
> > So if I simply subset the data according to pink/light blue & then 
put
> > those resultant subsets into var.test(), the answer does not show
> 
> the
> 
> > relationship that I want it to.
> > 
> > Can anybody shed some light on a sensible method of solving 
this?
> 
> Hi CJ,
> If your dataset has the transition type coded for each observation:
> 
> rotation	transition
> 90		blue
> 90		blue
> 115		pink
> -10		pink
> 30		green
> ...
> 
> you could aggregate all the observations within each transition type
> and test that.
> 
> Jim
> 
Oops,
What I meant was aggregate all the _deviations_ within each transition 
type.

Jim