Devon McCormick wrote:
is quarterly - and
> I want to find the correlation between the two series. I thought of three
> ways to do this:
> 1) I could reduce the monthly series and run the correlation between the
> quarterly and every third monthly;
Throws away data: not good.
> 2) I could linearly interpolate the quarterlies to get pseudo-monthlies;
If you are doing interpolation, linear may not be the best. However, you
don't end up with any more real data than when you started.
> 3) I could compound the monthlies to make them quarterly.
Looks better: at least the expected values are the same.
> So, please figure which way you think is the best and demonstrate why.
I would try correlating a series against itself.
compareCorrQvsM2=: 3 : 0
NB. qtrly=. <:+:?y$0
moly=. <:+:?0$~3*y
qtrly=.(+/%#)"1 ]_3 ]\ moly
cc=. 3{.corrCoeff qtrly,.moly#~1,2~:/\<.((#moly)%~#qtrly)*i.#moly
cc=. (corrCoeff (,2 linterpolate"0 qtrly),.moly) 1}cc
cc=. (corrCoeff qtrly,._3 aggrets\moly) 2}cc
NB.EG compareCorrQvsM 33
)
compareCorrQvsM2 33
0.521715 0.46196 0.903864
Best wishes,
John
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm
