Um pesquisador tem interesse em comparar dois métodos, a saber Karlruhe (K) e Lehigh (L), para prever a resistência ao cisalhamento entre traves planas metálicas. Os dois métodos são aplicados a 9 traves especı́ficas.
library(tidyverse)
library(planex)
data(vigas)
glimpse(vigas)
#> Rows: 9
#> Columns: 2
#> $ K <dbl> 1.186, 1.151, 1.322, 1.339, 1.200, 1.402, 1.365, 1.537, 1.559
#> $ L <dbl> 1.061, 0.992, 1.063, 1.062, 1.065, 1.178, 1.037, 1.086, 1.052
df <- vigas %>%
mutate(
viga = as.factor(1:nrow(vigas))
) %>%
pivot_longer(
cols = 1:2,
names_to = "metodo",
values_to = "resistencia"
)
fit <- aov(resistencia ~ viga + metodo, data = df)
summary(fit)
#> Df Sum Sq Mean Sq F value Pr(>F)
#> viga 8 0.1171 0.0146 1.604 0.259529
#> metodo 1 0.3376 0.3376 36.990 0.000295 ***
#> Residuals 8 0.0730 0.0091
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
with(vigas, t.test(K,L, paired = "TRUE"))
#>
#> Paired t-test
#>
#> data: K and L
#> t = 6.0819, df = 8, p-value = 0.0002953
#> alternative hypothesis: true mean difference is not equal to 0
#> 95 percent confidence interval:
#> 0.1700423 0.3777355
#> sample estimates:
#> mean difference
#> 0.2738889