library(caret)
## Carregando pacotes exigidos: ggplot2
## Carregando pacotes exigidos: lattice
getwd()
## [1] "C:/Users/LAFIECO/Downloads"
setwd("C:/Users/LAFIECO/Downloads")
df <- read.csv("DadosModeloMultivariadoSoja.csv", sep=";")
df$Trataments <- as.factor(df$Trataments)
# drop coluna
df <- subset(df, select = -Tratament_numeric)
# Criar variáveis dummy usando dummyVars
dummy_var <- dummyVars(~ Trataments, data = df)
# Transformar os dados originais usando predict
df_dummies <- predict(dummy_var, newdata = df)
# Adicionar as dummies ao conjunto de dados original
df_dummies <- cbind(df, df_dummies)
Deixando váriaveis dummies
Modelo Gamma com link Log
modelo_gammainverse <- glm(Grain ~ TotalBiomass:Trataments, data = df_dummies, family='Gamma'(link='inverse'))
summary(modelo_gammainverse)
##
## Call:
## glm(formula = Grain ~ TotalBiomass:Trataments, family = Gamma(link = "inverse"),
## data = df_dummies)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.1221653 0.0550900 2.218 0.0309 *
## TotalBiomass:TratamentsAmb 0.0002236 0.0062497 0.036 0.9716
## TotalBiomass:TratamentsAmbDrought 0.0254435 0.0110430 2.304 0.0252 *
## TotalBiomass:TratamentsAmbTemp 0.2532254 0.0567660 4.461 4.28e-05 ***
## TotalBiomass:TratamentsElev -0.0030452 0.0027900 -1.092 0.2800
## TotalBiomass:TratamentsElevDrought 0.0115957 0.0067860 1.709 0.0933 .
## TotalBiomass:TratamentsElevTemp -0.0030303 0.0029544 -1.026 0.3097
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for Gamma family taken to be 0.4453516)
##
## Null deviance: 174.08 on 59 degrees of freedom
## Residual deviance: 112.31 on 53 degrees of freedom
## AIC: 313
##
## Number of Fisher Scoring iterations: 7
plot(modelo_gammainverse)
Modelo gamma link inverse
# Explorando um pouco as possibilidades para modelo com resposta binária
pontodecorte = 2
df_dummies$Grain_not0 = 0
df_dummies$Grain_not0[ which(df$Grain > pontodecorte) ] = 1
modelo_binomial <- glm(Grain_not0 ~ TotalBiomass:Trataments, data = df_dummies, family='binomial'(link='logit')) # coloca -1 para o intercepto ser zero e ficar a mesma baseline para todos os tratamentos
## Warning: glm.fit: probabilidades ajustadas numericamente 0 ou 1 ocorreu
summary(modelo_binomial)
##
## Call:
## glm(formula = Grain_not0 ~ TotalBiomass:Trataments, family = binomial(link = "logit"),
## data = df_dummies)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.1117 2.6917 0.042 0.967
## TotalBiomass:TratamentsAmb 2.9583 1050.3721 0.003 0.998
## TotalBiomass:TratamentsAmbDrought 0.1592 0.3502 0.455 0.649
## TotalBiomass:TratamentsAmbTemp -2.8349 1117.1943 -0.003 0.998
## TotalBiomass:TratamentsElev 1.2829 503.5184 0.003 0.998
## TotalBiomass:TratamentsElevDrought 0.1164 0.2452 0.475 0.635
## TotalBiomass:TratamentsElevTemp 1.5319 556.8554 0.003 0.998
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 65.193 on 59 degrees of freedom
## Residual deviance: 19.761 on 53 degrees of freedom
## AIC: 33.761
##
## Number of Fisher Scoring iterations: 20
plot(modelo_binomial) # olhando os residuos do modelo
## Warning in sqrt(crit * p * (1 - hh)/hh): NaNs produzidos
## Warning in sqrt(crit * p * (1 - hh)/hh): NaNs produzidos
Modelo binomial