[…] all models are approximations. Essentially, all models are wrong, but some are useful. However, the approximate nature of the model must always be borne in mind […]— George Box (1987, Empirical Model-Building and Response Surfaces, p. 424)
t5.16 <- Table5.16 %>%
as_tibble() %>%
mutate(
A = factor(TotalAngle),
B = factor(CuttingSpeed)
)
modelo <- lm(ToolLife ~ A * B, data = t5.16)
print(anova(modelo))## Analysis of Variance Table
##
## Response: ToolLife
## Df Sum Sq Mean Sq F value Pr(>F)
## A 2 24.333 12.1667 8.4231 0.008676 **
## B 2 25.333 12.6667 8.7692 0.007703 **
## A:B 4 61.333 15.3333 10.6154 0.001844 **
## Residuals 9 13.000 1.4444
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
print(summary(modelo))##
## Call:
## lm(formula = ToolLife ~ A * B, data = t5.16)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5 -0.5 0.0 0.5 1.5
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -1.500e+00 8.498e-01 -1.765 0.11137
## A20 2.500e+00 1.202e+00 2.080 0.06725 .
## A25 1.000e+00 1.202e+00 0.832 0.42691
## B150 -1.776e-15 1.202e+00 0.000 1.00000
## B175 4.000e+00 1.202e+00 3.328 0.00882 **
## A20:B150 1.000e+00 1.700e+00 0.588 0.57077
## A25:B150 6.000e+00 1.700e+00 3.530 0.00641 **
## A20:B175 3.535e-15 1.700e+00 0.000 1.00000
## A25:B175 -4.000e+00 1.700e+00 -2.353 0.04306 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.202 on 9 degrees of freedom
## Multiple R-squared: 0.8952, Adjusted R-squared: 0.802
## F-statistic: 9.606 on 8 and 9 DF, p-value: 0.001337
Examinando os gráficos de diagnísticos não encontramos evidência de problemas severos:
t5.16_mdl <- t5.16 %>%
mutate(Resíduos = resid(modelo),
Ajustado = fitted(modelo))
p1 <- t5.16_mdl %>% ggplot(aes(sample = Resíduos)) +
stat_qq() +
stat_qq_line(color = "red") +
ggtitle("Gráfico de probabilidade Normal") +
labs(x = "Quantis Teórico", y = 'Resíduos')
p2 <- t5.16_mdl %>% ggplot() +
geom_point(aes(x = Ajustado, y = Resíduos)) +
ggtitle("Ajustados vs. Residuos") +
labs(x = "Ajustado", y = "Resíduos")Como o modelo tem fatores quantitativos, podemos ajustar um modelo de segunda ordem
plot_grid(p1, p2)modelo2 <- t5.16 %>%
lm(ToolLife ~
TotalAngle +
CuttingSpeed +
I((TotalAngle-20)^2) +
I((CuttingSpeed-150)^2) +
I((TotalAngle-20)*(CuttingSpeed-150)) +
I((TotalAngle-20)^2*(CuttingSpeed-150)) +
I((TotalAngle-20)*(CuttingSpeed-150)^2) +
I((TotalAngle-20)^2*(CuttingSpeed-150)^2), data = .)
base <- expand_grid(TotalAngle = seq(from = 15, to = 25, length.ou = 100),
CuttingSpeed = seq(from = 125, to = 175, length.out = 100)) %>%
mutate(
`I((TotalAngle-20)^2)` = (TotalAngle-20)^2,
`I((CuttingSpeed-150)^2)` = (CuttingSpeed-150)^2,
`I((TotalAngle-20)*(CuttingSpeed-150))` = (TotalAngle-20)*(CuttingSpeed-150),
`I((TotalAngle-20)^2*(CuttingSpeed-150))` = (TotalAngle-20)^2*(CuttingSpeed-150),
`I((TotalAngle-20)*(CuttingSpeed-150)^2)` = (TotalAngle-20)*(CuttingSpeed-150)^2,
`I((TotalAngle-20)^2*(CuttingSpeed-150)^2)` = (TotalAngle-20)^2*(CuttingSpeed-150)^2,
`I((TotalAngle-20)^2*(CuttingSpeed-150)^2)` = (TotalAngle-20)^2*(CuttingSpeed-150)^2) Além disso, podemos construir uma superficie de resposta:
p1 <- base %>%
mutate(z = predict(modelo2, base)) %>%
mutate(x = TotalAngle, y = CuttingSpeed) %>%
select(x, y, z) %>%
ggplot() +
theme_bw() +
geom_contour(aes(x = x, y = y, z = z)) +
geom_point(aes(TotalAngle, CuttingSpeed), data = t5.16)
p1 %>% ggplotly()base %>%
mutate(z = predict(modelo2, base)) %>%
mutate(x = TotalAngle, y = CuttingSpeed) %>%
select(x, y, z) %>%
plot_ly(z = ~ matrix(z, nrow = 100)) %>%
add_surface(
showscale = FALSE,
contours = list(
z = list(
show=TRUE,
usecolormap=TRUE,
highlightcolor="#ff0000",
project=list(z=TRUE)
)
)
) %>%
layout(showlegend = FALSE,
scene = list(xaxis = list(title = "Angle"),
yaxis = list(title = "Speed"),
zaxis = list(title = "ToolLife")
)
)Referencias
- Montgomery, D. C. (2020). Design and analysis of experiments. New York: John Wiley.