ham: Conjoint Study of Dry Cured Ham
In lmerTest: Tests in Linear Mixed Effects Models

Description Usage Format References Examples

One of the purposes of the study was to investigate the effect of information given to the consumers measured in hedonic liking for the hams. Two of the hams were Spanish and two were Norwegian, each origin representing different salt levels and different aging time. The information about origin was given in such way that both true and false information was given. Essentially a 4x2 design with 4 samples and 2 information levels. A total of 81 Consumers participated in the study.

data(ham)

Consumer: factor with 81 levels: numbering identifying consumers.
Product: factor with four levels.
Informed.liking: numeric: hedonic liking for the products.
Information: factor with two levels.
Gender: factor with two levels.
Age: numeric: age of Consumer.

T. Næs, V. Lengard, S. Bølling Johansen, M. Hersleth (2010) Alternative methods for combining design variables and consumer preference with information about attitudes and demographics in conjoint analysis, Food Quality and Preference, 10-4, 368-378, ISSN 0950-3293, https://doi.org/10.1016/j.foodqual.2009.09.004.

# Simple model for the ham data:
fm <- lmer(Informed.liking ~ Product*Information + (1|Consumer) , data=ham)

# Anova table for the fixed effects:
anova(fm)

## Not run: 
# Fit 'big' model:
fm <- lmer(Informed.liking ~ Product*Information*Gender*Age +
             + (1|Consumer) + (1|Consumer:Product) +
             (1|Consumer:Information),
           data=ham)
step_fm <- step(fm)
step_fm # Display elimination results
final_fm <- get_model(step_fm)

## End(Not run)