[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

*To*: "Peter M. Saama" <saama@pilot.msu.edu>*Subject*: Re: Interpretation of Components for Splines*From*: "B. Cullis" <cullisb@wagsun.agric.nsw.gov.au>*Date*: Mon, 3 May 1999 09:32:02 +1000 (EST)*cc*: asreml@ram.chiswick.anprod.csiro.au*In-Reply-To*: <4.1.19990430111517.00c0e5e0@gogreen.ans.msu.edu>*Sender*: asreml-owner@ram.chiswick.anprod.csiro.au

On Fri, 30 Apr 1999, Peter M. Saama wrote: > >The component for spl(time) is a variance component, but it controls the > >amount of smoothing. If this component (actually the ratio gamma) tends > >to zero, the spline fit tends to a straight line, as it gets large the > >fit tends to interpolation. The additional variance component, ie > >dev(time), allows for the presence of group effects, and can only be > >fitted if there is replication at each (or most) time point. This is in > >line with the usual one-way random effects analysis where you would fit > >y~ mu !r group > >in asreml to get correct analysis ie estimating both an error and between > >groups variance. > > > >The usual roughness penalty that is described in most smoothing texts is > >actually lambda = 1/gamma(spl). > > Thank you for your remarks. As you know, it is customary to specify > heritability as a function of the genetic and total variability. In > formulating linear functions of the variance components, should the > components for spl(time) and dev(time) be considered a part of the total > variability or should one include them in the genetic variation? yes well this opens up another issue. The text book formula for h^2 is hard to apply for more general situations. I prefer to calculate h^2 from prediction error variances (pev) of BLUPS. Roughly, pev = sigma^2_g * ( 1 - h^2) pev can be calc'd form the .vrb file from the asreml job. I have functions to do this. it's actually better to use the average pairwise variance. The above takes account of the other sources of variation, such as spatial/temporal/ etc cheers > > Peter / > >........................................................................... > .... > > Brian Cullis Tel: 02 6938 1855 > > NSW Agriculture Fax: 02 6938 1809 > > Wagga Agricultural Institute email: brian.cullis@agric.nsw.gov.au > > Pine Gully Rd > > WAGGA WAGGA NSW 2650 > > -- > Asreml mailinglist archive: http://www.chiswick.anprod.csiro.au/lists/asreml > ............................................................................... Brian Cullis Tel: 02 6938 1855 NSW Agriculture Fax: 02 6938 1809 Wagga Agricultural Institute email: brian.cullis@agric.nsw.gov.au Pine Gully Rd WAGGA WAGGA NSW 2650

**Follow-Ups**:**Re: Interpretation of Components for Splines***From:*bsouthey@iastate.edu

- Next by Date:
**Re: Interpretation of Components for Splines** - Next by thread:
**Re: Interpretation of Components for Splines** - Index(es):