posum.pop.matrix {posum}R Documentation

Population/Death surface evaluation matrices

Description

These two routines find the matrices mapping the model parameter vector to either the population surface or the total death rate surface. posum.pop.matrix also deals with adults. The routines are primarily designed as internal service routines.

Usage

 posum.pop.matrix(b,d,t0=0,point.wise=TRUE)

posum.death.matrix(b,d,fd)

Arguments

b A fitted gam object for a posum model with at least the extra variables target.dt and model.type.
d A data frame defining the ages/times at which evaluation is required. It should contain variables:
a
array of ages at which evaluation is required.
t
array of times at which evaluation required.
juvenile
by variable for juveniles.
adult
by variable for adults.

The latter two are not always required.
t0 The initial time (posum.pop.matrix only).
point.wise If this is true then the surfaces at each age, time point are evaluated with spearate calls to predict.gam, which saves memory. If false then there is just one call to predict.gam with one large data frame: this is faster, but uses a large amount of memory. (posum.pop.matrix only).
fd finite difference interval to use for obtaining death rates from type 1 models.

Details

The required matrices are obtained by calls to predict.gam() which obtain matrices mapping parameters to evaluations of the model at particular age, time points. Appropriate quadrature formulae are then applied to the matrix rows.

Value

The functions return the required matrices.

WARNING

Author(s)

Simon N. Wood snw@st-and.ac.uk

References

Gu and Wahba (1991) Minimizing GCV/GML scores with multiple smoothing parameters via the Newton method. SIAM J. Sci. Statist. Comput. 12:383-398

Wood (2000) Modelling and Smoothing Parameter Estimation with Multiple Quadratic Penalties. JRSSB 62(2):413-428

Wood (2003) Thin Plate Regression Splines in press JRSSB

http://www.ruwpa.st-and.ac.uk/simon.html

See Also

posum age.max, cm.splinefun, death.surface, hyman.filter, pcdr, population, population.data, population.surface, posum.atplot, posum.check, posum.con, posum.fit, posum.options, posum.plot, posum.stage, posum.stage.plot, posum.X, rec, sim.age.bound, spl.coef.conv, stage.bound, survival,


[Package Contents]