eucalipto

Regressão Linear - Eucalipto - Diâmetro vs Argila

Dados

DIAGRAMA DE DISPERSÃO

CORRELAÇÃO DE PEARSON

tibble [90 × 2] (S3: tbl_df/tbl/data.frame)
 $ dia: chr [1:90] "6.2" "5.1" "5.6" "6.4" ...
 $ arg: chr [1:90] "15.5" "15.1" "15.2" "15.2" ...

    Pearson's product-moment correlation

data:  dados_modelo$dia and dados_modelo$arg
t = 8.6834, df = 88, p-value = 1.84e-13
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 0.5495134 0.7770750
sample estimates:
      cor 
0.6793006 

REGRESSÃO LINEAR + EQUAÇÃO

Call:
lm(formula = dia ~ arg, data = dados_modelo)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.38551 -0.24283  0.02156  0.32166  1.47166 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept) -0.25273    0.76541  -0.330    0.742    
arg          0.42829    0.04932   8.683 1.84e-13 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 0.518 on 88 degrees of freedom
Multiple R-squared:  0.4614,    Adjusted R-squared:  0.4553 
F-statistic:  75.4 on 1 and 88 DF,  p-value: 1.84e-13

Analysis of Variance Table

Response: dia
          Df Sum Sq Mean Sq F value   Pr(>F)    
arg        1 20.230 20.2304  75.401 1.84e-13 ***
Residuals 88 23.611  0.2683                     
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

COEFICIENTE β1, QMR/QME e R²

Coeficiente angular (β1)

Valor-p

QMR = QM da Regressão

QME = QM dos Resíduos

R²

QQ-PLOT E TESTE DE NORMALIDADE DOS RESÍDUOS

-> QQ-Plot

-> Teste de Sapiro-Wilk

    Shapiro-Wilk normality test

data:  residuals(modelo)
W = 0.98476, p-value = 0.3767

RESÍDUOS PADRONIZADOS X VALORES AJUSTADOS