#**************************************************************************
# Conjoint analysis: a case study on the quality of banana
# Le, Le & Nguyen - SPISE2014
# verR.3.1.2 - Update: 05.12.2014
#**************************************************************************
# install.packages("conjoint") # Traditional conjoint analysis
# with multiple linear reg.
# install.packages("AlgDesign") # Fractional factorial design
# install.packages("clusterSim") # segmentation
# install.packages("agricolae") # design Graeco design
# Load packages -----------------------------------------------------------
library(FactoMineR)
library(SensoMineR)
library(ggplot2)
library(scales)
library(reshape2)
library(holos)
library(knitr)
library(conjoint)
library(AlgDesign)
library(clusterSim)
## Loading required package: cluster
## Loading required package: MASS
rm(list=ls())
options(max.print=5.5E5) # Max print
# wd <- "C:/Users/Tam Minh Le/Dropbox/10. Project/26. Banana/02. Data"
wd <- "C:/Users/LE Minh-Tam/Dropbox/10. Project/26. Banana/02. Data"
# Create data frame: Experimental design ----------------------------------
exp.design <- matrix(c(1, 1, 1, 1,
1, 2, 3, 2,
1, 3, 2, 3,
2, 1, 3, 3,
2, 2, 2, 1,
2, 3, 1, 2,
3, 1, 2, 2,
3, 2, 1, 3,
3, 3, 3, 1), ncol=4, nrow=9, byrow=TRUE)
rownames(exp.design) <- paste("prof.", 1:9, sep="")
colnames(exp.design) <- c("color", "shape", "bruise", "cigar")
exp.design <- as.data.frame(exp.design)
# Create data frame: levels -----------------------------------------------
color <- c("green", "green-yellow", "yellow")
shape <- c("high.heterogeneity", "heterogeneity", "homogeneity")
bruise <- c("high.bruise", "bruise", "non.bruise")
cigar.end.rot <- c("high.cigar", "med.cigar", "non.cigar")
lev.names <- data.frame(c(color, shape, bruise, cigar.end.rot))
colnames(lev.names) <- "levels"
lev.names
## levels
## 1 green
## 2 green-yellow
## 3 yellow
## 4 high.heterogeneity
## 5 heterogeneity
## 6 homogeneity
## 7 high.bruise
## 8 bruise
## 9 non.bruise
## 10 high.cigar
## 11 med.cigar
## 12 non.cigar
# Create data frame: quality score ----------------------------------------
# nha:
setwd(wd)
ba.qual <- read.csv("quality.csv", sep=";", dec=".", header=TRUE, row.names=1)
quality <- ba.qual[,seq(1, ncol(ba.qual), by=3)]
quality$id <- rownames(quality)
qual <- as.data.frame(melt(quality), quote=FALSE) # long.table
## Using id as id variables
qual.score <- qual[,3]
## Classification based on quality score
res.PCA <- PCA(quality[,1:32], graph=FALSE)
# HCPC(res.PCA$ind$coord, nb.clust=3, consol=TRUE)
# Conjoint analysis -------------------------------------------------------
Conjoint(qual.score, exp.design, lev.names)
##
## Call:
## lm(formula = frml)
##
## Residuals:
## Min 1Q Median 3Q Max
## -723,31 -131,70 -2,73 127,70 657,75
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 451,594 12,267 36,813 < 2e-16 ***
## factor(x$color)1 -43,500 17,349 -2,507 0,0127 *
## factor(x$color)2 16,688 17,349 0,962 0,3369
## factor(x$shape)1 -2,656 17,349 -0,153 0,8784
## factor(x$shape)2 -106,385 17,349 -6,132 2,95e-09 ***
## factor(x$bruise)1 -173,125 17,349 -9,979 < 2e-16 ***
## factor(x$bruise)2 -71,240 17,349 -4,106 5,29e-05 ***
## factor(x$cigar)1 -16,500 17,349 -0,951 0,3424
## factor(x$cigar)2 28,146 17,349 1,622 0,1059
## ---
## Signif. codes: 0 '***' 0,001 '**' 0,01 '*' 0,05 '.' 0,1 ' ' 1
##
## Residual standard error: 208,2 on 279 degrees of freedom
## Multiple R-squared: 0.4922, Adjusted R-squared: 0.4776
## F-statistic: 33.8 on 8 and 279 DF, p-value: < 2,2e-16
## [1] "Part worths (utilities) of levels (model parameters for whole sample):"
## levnms utls
## 1 intercept 451,5938
## 2 green -43,5
## 3 green-yellow 16,6875
## 4 yellow 26,8125
## 5 high.heterogeneity -2,6562
## 6 heterogeneity -106,3854
## 7 homogeneity 109,0417
## 8 high.bruise -173,125
## 9 bruise -71,2396
## 10 non.bruise 244,3646
## 11 high.cigar -16,5
## 12 med.cigar 28,1458
## 13 non.cigar -11,6458
## [1] "Average importance of factors (attributes):"
## [1] 17,68 23,45 45,62 13,25
## [1] Sum of average importance: 100
## [1] "Chart of average factors importance"
# caSegmentation(qual.score, exp.design, 2)
# ShowAllUtilities(qual.score, exp.design, lev.names) # estimating all models
# utility <- ShowAllUtilities(qual.score, exp.design, lev.names)
# Conjoint analysis by hand -----------------------------------------------
## A experimental design for 32 subjects
design <- exp.design
design$id <- rownames(design)
df <- design[rep(1:nrow(design),each=32),]
rownames(df) <- NULL
# df
## A vector of quality score for 32 subjects
t.hedo <- t(ba.qual[,seq(1, ncol(ba.qual), by=3)])
hedo.anova <- as.matrix(t.hedo)
hedo <- melt(hedo.anova, id=1)
colnames(hedo) = c("subject","product","score")
hedo.plan <- cbind(df, hedo)
## model1: variables are considered as continuous variables
## For understand, dont use
# model1 <- aov(score ~ color + shape + bruise + cigar, data=hedo.plan)
# summary(model1) # factors: bruise > shape > color
## model2: varibales are considered as dummy variables
model2 <- lm(score ~ factor(color) + factor(shape) + factor(bruise) + factor(cigar),
data=hedo.plan)
summary(model2)
##
## Call:
## lm(formula = score ~ factor(color) + factor(shape) + factor(bruise) +
## factor(cigar), data = hedo.plan)
##
## Residuals:
## Min 1Q Median 3Q Max
## -723.31 -131.70 -2.73 127.70 657.75
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 451.594 12.267 36.813 < 2e-16 ***
## factor(color)1 -43.500 17.349 -2.507 0.0127 *
## factor(color)2 16.688 17.349 0.962 0.3369
## factor(shape)1 -2.656 17.349 -0.153 0.8784
## factor(shape)2 -106.385 17.349 -6.132 2.95e-09 ***
## factor(bruise)1 -173.125 17.349 -9.979 < 2e-16 ***
## factor(bruise)2 -71.240 17.349 -4.106 5.29e-05 ***
## factor(cigar)1 -16.500 17.349 -0.951 0.3424
## factor(cigar)2 28.146 17.349 1.622 0.1059
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 208.2 on 279 degrees of freedom
## Multiple R-squared: 0.4922, Adjusted R-squared: 0.4776
## F-statistic: 33.8 on 8 and 279 DF, p-value: < 2.2e-16
# Sorting -----------------------------------------------------------------
ba.sort <- read.csv("sorting.csv", sep=";", dec=".", header=TRUE, row.names=1)
dat.sort <- ba.sort[,seq(3, ncol(ba.sort), by=3)]
res.fast <- fast(dat.sort, sep.words=";")
## Number of different words : 137
#********************************* END *************************************