# Re: Prediction with splines

From: <arthur.gilmour_at_DPI.NSW.GOV.AU>
Date: Wed, 7 Nov 2007 11:44:57 +1100

Dear Kevin,
Hi

re:
David, I have a question about a quirk with predictions in asreml-r.
I thought about asking this on the mailing list, but other people may
not be interested in this particular question. If you prefer that I
ask this on the mailing list so that it is archived, just let me know.

Here is the situation:

tree1 <- subset(orange, Tree==1)
m1 <- asreml(circ ~ 1 + lin(x) , random= ~ spl(x), data=tree1)
m1 <- update(m1)
p1 <- predict(m1, classify="x",
predictpoints=list(x=seq(from=118, to=1582, length=20)))
p1 <- p1\$predictions\$x\$pvals
p1

Notes:
- The cells of the hypertable are calculated from all model terms
constructed
solely from factors in the averaging and classify sets.

x predicted.value standard.error est.status
1 118.0000 30.76666 6.044057 Estimable
2 195.0526 37.89921 5.270393 Estimable
3 272.1053 45.02535 4.689576 Estimable
4 349.1579 52.13864 4.312880 Estimable
etc.

My question is: sometimes in the "Notes" section of the predicted
values I see output similar to:
"lin(x) evaluated at average value of 5.500000"

This time, however, there is no such note. I have not figured out
when I see this note about 'x evaluated at average value' and when I
don't.

Is there a reason for this that I have overlooked, or maybe this is
just missing in some (which?) models?

Best,

Kevin

****************
The message "lin(x) evaluated at average value of 5.500000"
and its equivalent in ASReml, is produced when x is a fixed factor
but has not been given a list of values at which it is to be predicted.
In this example, predictpoints=list(x=seq(from=118, to=1582, length=20)
specifies the list of values of x to be predicted, so these values are
used.
x is not included in the header meassage because it is explicit in the
predict table.

The header messages are intended to specify how factors/variates not
explicit
in the predict table are treated (ignored if random factors, averaged if
fixed factors,
evaluated at average value if fixed covariates).

Best wishes.

May Jesus Christ be gracious to you,

Arthur Gilmour, His servant .

Mixed model regression mapping for QTL detection in experimental crosses.
Computational Statistics and Data Analysis 51:3749-3764 now available at
http://dx.doi.org/10.1016/j.csda.2006.12.031

Personal website: http://www.cargovale.com.au/

mailto:Arthur.Gilmour_at_dpi.nsw.gov.au, arthur_at_cargovale.com.au
Principal Research Scientist (Biometrics)
NSW Department of Primary Industries
Orange Agricultural Institute, Forest Rd, ORANGE, 2800, AUSTRALIA

fax: 02 6391 3899; 02 6391 3922 Australia +61
telephone work: 02 6391 3815; home: 02 6364 3288; mobile: 0438 251 426

ASREML 2 is now available from http://www.VSNi.co.uk/products/asreml
The ASReml discussion group is at ASREML-L_at_dpi.nsw.gov.au
To join it, mailto:arthur.gilmour_at_dpi.nsw.gov.au
Archives are at
https://gatekeeper.dpi.nsw.gov.au/Listserv/archives/asreml-l.html
Cookbook: http://uncronopio.org/ASReml

Proposed travel:
UK 28 Jan
USA 11-15 Feb
><><><><><><><><><><><><><><><><><><><><><><><>
Received on Sun Nov 07 2007 - 11:44:57 EST

This webpage is part of the ASReml-l discussion list archives 2004-2010. More information on ASReml can be found at the VSN website. This discussion list is now deprecated - please use the VSN forum for discussion on ASReml. (These online archives were generated using the hypermail package.)