selec_bestsub: best-subset model selection

In yorickuser/contselec: Model selection procesure by contracting explanatry variables, with check of each explanatry variable's strength.

Description

This function conducts best-subset model selection

Usage

selec_bestsub(data0, data1, group, pos_x = NULL, pos_y = NULL,
  edge_param_number = 3, repeatn = 100, family,
  check_spa_cor = FALSE, target = "", use_pforeach = TRUE,
  perm = TRUE, daic = 2, check_spa_cor_nmodel = 50, nrep = 10000)

Arguments

data0	data.frame : uncontracted data
data1	data.frame : constracted data
group	(list(gid,gid_data1,ngid,vname1_orig,vname0_orig)) : information about contraction of "data0" into "data1".
pos_x	array of numeric : x-coordinates of spatial position for each sampled data in "data0".
pos_y	array of numeric : y-coordinates of spatial position for each sampled data in "data0".
edge_param_number	real number: this parameter constrains the number of explanatory variables in the subset model selection and stepwise model selection, so that [sample size]/[number of free parameter] >= "edge_param_number".
repeatn	integer : the number of model evaluations proccessed as a single job for each CPU core (This parameter is meaningfur only when parallel proccessing is conducted by library "pforeach").
family	character : error distribution. Possible choices are "glmm_poisson", "poisson","gaussian".
check_spa_cor	TRUE/FALSE : if TRUE, the best model with residuals significantly correlated with c(pos_x, pos_y) are removed repeatedly until the correlation becomes non-significant.
target	character : arbitrary name for explained variable "y".
use_pforeach	TRUE/FALSE : if TRUE, pforeach is used instead of foreach.
perm	TRUE/FALSE : if TRUE, permutation tests for explained variables are conducted.
daic	numeric : models with Delta-AIC no more than "daic" are examined. Default value is 2.0.
nrep	integer : number of resampling in the permutation test.

Details

Details.

Value

list(result=result,bestmodels=aa,bestmodel=bestmodel, n_model=n_model,n_model_total=n_model_total)

Author(s)

Hiroshi C. Ito

Examples

data(Cars93, package = "MASS");
data=Cars93;
data=data[complete.cases(data),];
data=data[,sapply(data[1,],is.numeric)];
con=contract(data,edge_cor=0.9,edge_explain=0.6,target="Horsepower");
data1=con$data1;
for(i in 2:ncol(data1))data1[,i]=(data1[,i]-min(data1[,i]))/(max(data1[,i])-min(data1[,i]));

res=selec_bestsub(con$data0,data1,con$group,edge_param_number=3,repeatn=50,family="gaussian",target=con$target, use_pforeach=FALSE,perm=TRUE,daic=2.0);

print(res$result);

yorickuser/contselec documentation built on July 25, 2021, 8:14 a.m.