The TVbo dataset has kindly been made available by the Danish high-end consumer electronics company Bang & Olufsen. The main purpose was to assess 12 different TV sets (products) specified by the two attributes Picture and TVset. 15 different response variables (characteristics of the product) were assessed by a trained panel with 8 assessors.
data(TVbo)factor with 8 levels assessors.
product factor with 3 levels.
product factor with 4 levels.
In addition the following 15 numeric (response) variables are the characteristics on which the TV sets (products) are assessed:
Coloursaturation, Colourbalance, Noise, Depth, Sharpness, Lightlevel, Contrast, Sharpnessofmovement, Flickeringstationary, Flickeringmovement, Distortion, Dimglasseffect, Cutting, Flossyedges, Elasticeffect.
fm <- lmer(Coloursaturation ~ TVset + Picture + (1|Assessor:TVset) +
(1|Assessor), data=TVbo)
ranova(fm)
#> ANOVA-like table for random-effects: Single term deletions
#>
#> Model:
#> Coloursaturation ~ TVset + Picture + (1 | Assessor:TVset) + (1 | Assessor)
#> npar logLik AIC LRT Df Pr(>Chisq)
#> <none> 9 -287.88 593.76
#> (1 | Assessor:TVset) 8 -308.89 633.78 42.021 1 9.03e-11 ***
#> (1 | Assessor) 8 -287.92 591.85 0.090 1 0.7643
#> ---
#> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
anova(fm)
#> Type III Analysis of Variance Table with Satterthwaite's method
#> Sum Sq Mean Sq NumDF DenDF F value Pr(>F)
#> TVset 31.411 15.7056 2 14 17.2246 0.0001682 ***
#> Picture 11.216 3.7387 3 165 4.1003 0.0077352 **
#> ---
#> Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1