Tarea Julio 9

Análisis de COVARIANZA, Utilizando Mice

library(readxl)

## Warning: package 'readxl' was built under R version 4.0.5

df_Mice = Datos_Tarea_Julio_9 <- read_excel("D:/Users/Usuario/Desktop/Trabajos Diseno/Datos Tarea Julio 9.xlsx");df_Mice

## # A tibble: 36 x 5
##    Fertilizante    MO Proteína     y     x
##    <chr>        <dbl>    <dbl> <dbl> <dbl>
##  1 D15           2.24     4.15     1     1
##  2 D5            1.99     4.76     2     1
##  3 D5            1.82     5.10     3     1
##  4 D0            2.36     4.99     4     1
##  5 D5            2.32     5.14     5     1
##  6 D5            2.38     5.19     6     1
##  7 D10           2.56     5.70     1     2
##  8 D5            2.59     5.44     2     2
##  9 D0            2.62     5.73     3     2
## 10 D10           2.73     5.76     4     2
## # ... with 26 more rows

Fertilizante=df_Mice$Fertilizante
MO=df_Mice$MO
Proteína=df_Mice$Proteína
X=df_Mice$x
Y=df_Mice$y

#N/A total en la base de datos
sum(is.na(df_Mice))

## [1] 5

#Omitir NA (filas)
df_COV <- na.omit(df_Mice);df_COV

## # A tibble: 31 x 5
##    Fertilizante    MO Proteína     y     x
##    <chr>        <dbl>    <dbl> <dbl> <dbl>
##  1 D15           2.24     4.15     1     1
##  2 D5            1.99     4.76     2     1
##  3 D5            1.82     5.10     3     1
##  4 D0            2.36     4.99     4     1
##  5 D5            2.32     5.14     5     1
##  6 D5            2.38     5.19     6     1
##  7 D10           2.56     5.70     1     2
##  8 D5            2.59     5.44     2     2
##  9 D0            2.62     5.73     3     2
## 10 D10           2.73     5.76     4     2
## # ... with 21 more rows

#NA por columna
colSums(is.na(df_Mice))

## Fertilizante           MO     Proteína            y            x 
##            0            0            5            0            0

library(mice)

## Warning: package 'mice' was built under R version 4.0.5

## 
## Attaching package: 'mice'

## The following object is masked from 'package:stats':
## 
##     filter

## The following objects are masked from 'package:base':
## 
##     cbind, rbind

Columnas <- c("Proteína","MO")
DATOS <- mice(df_Mice[,names(df_Mice) %in% Columnas],m = 1,
  maxit = 1, method = "mean",print=F)
Datos_Completos <- mice::complete(DATOS)
Proteína_2=Datos_Completos$Proteína

Análisis Exploratorio \[y_1 = \beta_0 + \beta_1x_i+\epsilon\]

\[P_1 = \beta_0 + \beta_1MO_i+\epsilon\]

\[E[P_1 |MO_i]= \beta_0 + \beta_1MO_i\]

\[\widehat{P_1} = \beta_0 + \beta_1MO_i\]

Minimos Cuadrados Oridnarios

mod_1 = lm(Proteína~MO)
summary(mod_1)

## 
## Call:
## lm(formula = Proteína ~ MO)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -1.10399 -0.27435  0.09673  0.23745  0.76812 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)   3.6768     0.3822   9.619 1.58e-10 ***
## MO            0.7050     0.1250   5.642 4.27e-06 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.4003 on 29 degrees of freedom
##   (5 observations deleted due to missingness)
## Multiple R-squared:  0.5233, Adjusted R-squared:  0.5069 
## F-statistic: 31.83 on 1 and 29 DF,  p-value: 4.269e-06

coef = round(mod_1$coefficients, 2)

\[Piˆ=3.68+0.7MO\]

shapiro.test(mod_1$residuals)

## 
##  Shapiro-Wilk normality test
## 
## data:  mod_1$residuals
## W = 0.97525, p-value = 0.6723

hist(mod_1$residuals)

plot(mod_1$residuals, pch = 14)

mod_2 = aov(Proteína_2 ~ MO + Fertilizante)
summary(mod_2)

##              Df Sum Sq Mean Sq F value   Pr(>F)    
## MO            1  4.712   4.712  35.706 1.32e-06 ***
## Fertilizante  3  0.944   0.315   2.383   0.0883 .  
## Residuals    31  4.091   0.132                     
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

boxplot(Proteína_2 ~ Fertilizante)