check_dominance: Dominance control

In Iannacks/SP.Survey: SP survey

Dominance control

Description

It provides the dominated choice tasks of the experimental design based on a-priori beta assumptions.

Usage

check_dominance(sign,design,attribute.names)

Arguments

sign	A character vector of length equal to the attributes number. A value can assume value "-" if the utility function decrease and value "+" for the opposite. Sign can be also a vector of length 0, if one wants to consider only total dominance without a-priori considerations. In this case sign=NULL
design	An experimental design obtained from the function des_function
attribute.names	A list containing attributes names and levels

Details

The function provides the dominated choice tasks of an ortogonal or fractional factorial design obtained with the function des_function. The parameter sign defines the type of dominance that the function has to check. If sign is NULL, the function provides the choice tasks completely equal apart from an attribute level. If a-priori coefficients are provided, dominance are calculated based on these assumptions. A fondamental assumption on coefficients is that the utility function for each attribute, considered as an ordinal attribute, is monotone (increasing or decreasing function)

Value

starting_des	The experimental design data.frame
task_dominated	The index of the dominated choice tasks, observed on the starting_des object
dominance	The percentage of dominated task

Author(s)

Gabriele Iannaccone

References

Federov, V.V. (1972). Theory of optimal experiments. Academic Press, New York. Aizaki H (2012). Basic Functions for Supporting an Implementation of Choice Experiments in R.Journal of Statistical Software, 50(C2). doi:10.18637/jss.v050.c02. Wheeler, R.E. (2004). AlgDesign. The R project for statistical computing. (http://www.r-project.org).

Examples

#create the experimental design
design1<-des_function(alt=2,typology=0,attribute.names=list(prezzo = c("1.5","3","4.5"),
        tempo = c("30m","1h"),comfort=c("basso","alto")),set=3,block=2,seed=802)
#check the dominance
dom_design_type2<-check_dominance(sign=c("-","-","+"),design=design1,attribute.names=list(
   prezzo = c("1.5","3","4.5"),tempo = c("30m","1h"),
   comfort=c("basso","alto")))

Iannacks/SP.Survey documentation built on May 18, 2023, 11:23 a.m.