PSANOVA: Define a two-dimensional penalised tensor-product of marginal...

In SpATS: Spatial Analysis of Field Trials with Splines

Define a two-dimensional penalised tensor-product of marginal B-Spline basis functions based on the P-spline ANOVA (PSANOVA) approach.

Description

Auxiliary function used for modelling the spatial or environmental effect as a two-dimensional penalised tensor-product of marginal B-spline basis functions with anisotropic penalties on the basis of the PSANOVA approach by Lee et al. (2013).

Usage

PSANOVA(..., nseg = c(10,10), pord = c(2,2), degree = c(3,3), nest.div = c(1,1), 
	center = FALSE)

Arguments

...	a list of the covariates that this smooth component is a function of. Currently, only two-dimensional tensor-product smoothers are implemented: the first covariate is assumed to define the x-spatial coordinate (e.g., column position) of each plot in the field, and the second argument the y-spatial coordinate (i.e., the row position). Both covariates should be numerical.
nseg	numerical vector of length 2 containing the number of segments for each marginal (strictly nseg - 1 is the number of internal knots in the domain of the covariate). Atomic values are also valid, being recycled. Default set to 10.
pord	numerical vector of length 2 containing the penalty order for each marginal. Atomic values are also valid, being recycled. Default set to 2 (second order). Currently, only second order penalties are allowed.
degree	numerical vector of length 2 containing the order of the polynomial of the B-spline basis for each marginal. Atomic values are also valid, being recycled. Default set to 3 (cubic B-splines).
nest.div	numerical vector of length 2 containing the divisor of the number of segments (nseg) to be used for the construction of the nested B-spline basis for the smooth-by-smooth interaction component. In this case, the nested B-spline basis will be constructed assuming a total of nseg/nest.div segments. Default set to 1, which implies that nested basis are not used. See SAP for more details.
center	logical. If TRUE, the fitted spatial trend (2D surface) will be centered at zero for the observed data (i.e., the average of the fitted spatial trend will be zero at the observed data). By default FALSE (for compatibility with versions of the package previous to 1.0-13.

Details

The approach implemented here represents an alternative method to the SAP function. In this case, the smooth bivariate surface (or spatial trend) is decomposed in five different components each of them depending on a single smoothing parameter (see Lee et al., 2013).

References

Gilmour, A.R., Cullis, B.R., and Verbyla, A.P. (1997). Accounting for Natural and Extraneous Variation in the Analysis of Field Experiments. Journal of Agricultural, Biological, and Environmental Statistics, 2, 269 - 293.

Lee, D.-J., Durban, M., and Eilers, P.H.C. (2013). Efficient two-dimensional smoothing with P-spline ANOVA mixed models and nested bases. Computational Statistics and Data Analysis, 61, 22 - 37.

See Also

SpATS, SAP

Examples

library(SpATS)
data(wheatdata)
wheatdata$R <- as.factor(wheatdata$row)
wheatdata$C <- as.factor(wheatdata$col)

# Without nested basis
m0 <- SpATS(response = "yield", spatial = ~ PSANOVA(col, row, nseg = c(10,20)), 
 genotype = "geno", fixed = ~ colcode + rowcode, random = ~ R + C, data = wheatdata, 
 control =  list(tolerance = 1e-03))

summary(m0)

# With nested basis
m1 <- SpATS(response = "yield", spatial = ~ PSANOVA(col, row, nseg = c(10,20), nest.div = 2), 
genotype = "geno", fixed = ~ colcode + rowcode, random = ~ R + C, data = wheatdata, 
control =  list(tolerance = 1e-03))

summary(m1)

SpATS documentation built on Nov. 10, 2022, 5:58 p.m.