d-perform-the-preference-mapping.Rmd
library(sensoreport)perform_prefmap(): Perform the preference mapping
With perform_prefmap(), you can perform the preference
mapping.
This is based on the results of the MCA provided by the
perform_senso_mapping() function (see vignette c -
Perform the multidimensional sensory analysis (mapping) for more
details).
The graph of individuals (i.e. products) is discretized to form a
grid of fictitious products. For each x * y
coordinate of these fictitious products, the liking score is predicted
for each panelist. A linear regression model
liking ~ coordinate dim 1 + coordinate dim 2 + coordinate dim 1 * coordinate dim 2
is used to predict the liking score for each panelist.
Then, the fictitious product is stamped “liked” if its predicted score is greater than or equal to the average of the liking scores given by the panelist. Otherwise, it is stamped “unliked”. The proportion of panelists who liked each fictitious product in the grid is then calculated. This value is projected onto the map using a response surface.
This graph is displayed in an interactive format.
data("data_sensory_toy")
data("data_products_toy")
data("data_hedonic_toy")
res_mapping <- perform_senso_mapping(
data_sensory = data_sensory_toy,
data_products = data_products_toy
)
perform_prefmap(
res_mapping = res_mapping,
data_hedonic = data_hedonic_toy
)