-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
I'm using J a lot more these days and very happy. Yet today I came up
with a problem that's bugging me.
load jpath '~addons/stats/base/multivariate.ijs'
t=: 2 8 $ ? 16 # 10
t
0 7 8 9 2 2 5 5
5 3 8 0 0 5 9 6
_2 <\"1 t
┌───┬───┬───┬───┐
│0 7│8 9│2 2│5 5│
├───┼───┼───┼───┤
│5 3│8 0│0 5│9 6│
└───┴───┴───┴───┘
2 <\"1 t
┌───┬───┬───┬───┬───┬───┬───┐
│0 7│7 8│8 9│9 2│2 2│2 5│5 5│
├───┼───┼───┼───┼───┼───┼───┤
│5 3│3 8│8 0│0 0│0 5│5 9│9 6│
└───┴───┴───┴───┴───┴───┴───┘
1 lsfit 0 7,: 5 3
5 _0.285714
(1 & lsfit) 0 7,: 5 3
5 _0.285714
1 lsfit t
4.56643 _0.013986
So far, so good.
What I want to do is to see how the fit has changed over time (I'm
actually fitting to a second-order polynomial, but this is easier to
demonstrate).
I think I'd like to use prefix to apply lsfit to successive parts of the
right argument.
Yet
2 (1 & lsfit) \"1 t
7 1.28 1.24615 0.243902 1.2 3 1.15385
0.692308 3.2 0 0 5 2.07692 0.731707
and the first pair output doesn't match up with 5 _0.285714 above. I
figure I'm missing something with regard to rank, but neither thinking
nor trying has turned up anything good so far.
What am I missing? Any thoughts on the process, too?
Thanks,
Bill
- --
Bill Harris http://facilitatedsystems.com/weblog/
Facilitated Systems Everett, WA 98208 USA
http://facilitatedsystems.com/ phone: +1 425 337-5541
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.9 (GNU/Linux)
iEYEARECAAYFAkmskakACgkQ3J3HaQTDvd8Y/wCfeRx2ykAg+9EoV9MNYFJgEC2+
V5kAn11/0l1PqKl0zREdGxt5jPgg015F
=/Pew
-----END PGP SIGNATURE-----
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm
