tarea_reg_anova

Los datos se encuentran en la Hoja electrónica adjunta en la tarea de classroom: Tarea_Regresion-Andeva

Para recrear los análisis en su propia computadora, copiar los trozos de código a continuación y pegar en consola de R. No realizar ningún cambio.

if(!require(googlesheets4)){install.packages("googlesheets4")}
if(!require(tidyverse)){install.packages("tidyverse")}
if(!require(ggpubr)){install.packages("ggpbur")}
#
library(googlesheets4); gs4_deauth()
library(tidyverse)
library(ggpubr)

Leyendo / Importando sets de datos

Hoja de datos a

hoja= "a"
rango= "B3:C22"
#
a <- read_sheet("https://docs.google.com/spreadsheets/d/167t2X_sawdlBQ-_hdYP7GNdC1XhzSqQzAnwMlBZJpWg/edit?usp=sharing",
           sheet= hoja,
           range= rango)
a$sexo <- as.factor(a$sexo)

 (S3: tbl_df/tbl/data.frame)
 $ estatura: num [1:19] 160 164 162 158 163 163 156 170 175 165 ...
 $ sexo    : Factor w/ 2 levels "f","m": 1 1 1 1 1 1 1 2 2 2 ...

Hoja de datos b

hoja= "b"
rango= "B3:C38"
#
b <- read_sheet("https://docs.google.com/spreadsheets/d/167t2X_sawdlBQ-_hdYP7GNdC1XhzSqQzAnwMlBZJpWg/edit?usp=sharing",
           sheet= hoja,
           range= rango)
b$grupo <- as.factor(b$grupo)
str(b)

tibble [35 x 2] (S3: tbl_df/tbl/data.frame)
 $ altura: num [1:35] 21.4 18.9 24.9 21.7 21.2 ...
 $ grupo : Factor w/ 5 levels "a","b","c","d",..: 1 1 1 1 1 1 1 2 2 2 ...

Hoja de datos c

hoja= "c"
rango= "C3:D17"
#
c <- read_sheet("https://docs.google.com/spreadsheets/d/167t2X_sawdlBQ-_hdYP7GNdC1XhzSqQzAnwMlBZJpWg/edit?usp=sharing",
           sheet= hoja,
           range= rango)

str(c)

tibble [14 x 2] (S3: tbl_df/tbl/data.frame)
 $ longitud: num [1:14] 67 78 70 78 66 71 74 81 81 78 ...
 $ peso    : num [1:14] 

Hoja de datos d

hoja= "d"
rango= "C4:D54"
#
d <- read_sheet("https://docs.google.com/spreadsheets/d/167t2X_sawdlBQ-_hdYP7GNdC1XhzSqQzAnwMlBZJpWg/edit?usp=sharing",
           sheet= hoja,
           range= rango)
#
str(d)

tibble [50 x 2] (S3: tbl_df/tbl/data.frame)
 $ DI: num [1:50] 8.78 9.45 9.73 9.75 9.89 ...
 $ La: num [1:50] 111 114 114 117 119 ...

Hoja de datos e

hoja= "e"
rango= "D3:E23"
#
e <- read_sheet("https://docs.google.com/spreadsheets/d/167t2X_sawdlBQ-_hdYP7GNdC1XhzSqQzAnwMlBZJpWg/edit?usp=sharing",
           sheet= hoja,
           range= rango)
e$X1 <- as.factor(e$X1)
str(e)

tibble [20 x 2] (S3: tbl_df/tbl/data.frame)
 $ Y1: num [1:20] 145 137 134 139 142 ...
 $ X1: Factor w/ 2 levels "n1","n2": 1 1 1 1 1 1 1 1 1 1 ...

Hoja de datos f

hoja= "f"
rango= "B3:C81"
#
f <- read_sheet("https://docs.google.com/spreadsheets/d/167t2X_sawdlBQ-_hdYP7GNdC1XhzSqQzAnwMlBZJpWg/edit?usp=sharing",
           sheet= hoja,
           range= rango)
f$grupo <- as.factor(f$grupo)
str(f)

tibble [78 x 2] (S3: tbl_df/tbl/data.frame)
 $ y    : num [1:78] 14.7 17.3 15.9 17.3 17.4 ...
 $ grupo: Factor w/ 2 levels "A","B": 1 1 1 1 1 1 1 1 1 1 ...

Plots / Anaysis

Hoja “a”

plot(a$estatura ~ a$sexo)

#
lm.a <- lm(a$estatura~ a$sexo)
summary(lm.a)

Call:
lm(formula = a$estatura ~ a$sexo)

Residuals:
   Min     1Q Median     3Q    Max 
-7.000 -3.500  1.143  3.071  8.000 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  160.857      1.667  96.470  < 2e-16 ***
a$sexom       11.143      2.098   5.311 5.75e-05 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 4.412 on 17 degrees of freedom
Multiple R-squared:  0.6239,    Adjusted R-squared:  0.6018 
F-statistic: 28.21 on 1 and 17 DF,  p-value: 5.749e-05

#
aov.a <- aov(a$estatura ~ a$sexo)
summary(aov.a)

            Df Sum Sq Mean Sq F value   Pr(>F)    
a$sexo       1  548.9   548.9    28.2 5.75e-05 ***
Residuals   17  330.9    19.5                     
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Hoja “b”

plot(b$altura ~ b$grupo)

#
lm.b <- lm(b$altura ~ b$grupo)
summary(lm.b)

Call:
lm(formula = b$altura ~ b$grupo)

Residuals:
    Min      1Q  Median      3Q     Max 
-3.8271 -1.1011  0.0658  1.3286  3.0429 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  22.6871     0.6928  32.746  < 2e-16 ***
b$grupob     12.2770     0.9798  12.530 1.88e-13 ***
b$grupoc      8.1014     0.9798   8.268 3.14e-09 ***
b$grupod     -4.4100     0.9798  -4.501 9.50e-05 ***
b$grupoe     13.9514     0.9798  14.239 6.94e-15 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.833 on 30 degrees of freedom
Multiple R-squared:  0.9458,    Adjusted R-squared:  0.9386 
F-statistic: 130.9 on 4 and 30 DF,  p-value: < 2.2e-16

#
aov.b <- aov(b$altura ~ b$grupo)
summary(aov.b)

            Df Sum Sq Mean Sq F value Pr(>F)    
b$grupo      4 1759.9   440.0   130.9 <2e-16 ***
Residuals   30  100.8     3.4                   
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Hoja “c”

plot(c$peso~c$longitud, pch=20)

#
lm.c <- lm(c$peso ~ c$longitud)
summary(lm.c)

Call:
lm(formula = c$peso ~ c$longitud)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.94423 -0.52548 -0.05817  0.51250  1.82788 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept) 27.56058    3.73448    7.38 8.50e-06 ***
c$longitud   0.64135    0.05042   12.72 2.52e-08 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.064 on 12 degrees of freedom
Multiple R-squared:  0.931, Adjusted R-squared:  0.9252 
F-statistic: 161.8 on 1 and 12 DF,  p-value: 2.518e-08

#
aov.c <- aov(c$peso ~ c$longitud)
summary(aov.c)

            Df Sum Sq Mean Sq F value   Pr(>F)    
c$longitud   1  183.3  183.33   161.8 2.52e-08 ***
Residuals   12   13.6    1.13                     
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Hoja “d”

plot(d$La ~ d$DI, pch=20)

#
lm.d <- lm(d$La ~ d$DI)
summary(lm.d)

Call:
lm(formula = d$La ~ d$DI)

Residuals:
    Min      1Q  Median      3Q     Max 
-7.2301 -4.7238 -0.0456  4.4415  8.5558 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)   8.5170     4.5767   1.861   0.0689 .  
d$DI         11.5948     0.3597  32.235   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 4.839 on 48 degrees of freedom
Multiple R-squared:  0.9558,    Adjusted R-squared:  0.9549 
F-statistic:  1039 on 1 and 48 DF,  p-value: < 2.2e-16

#
aov.d <- aov(d$La ~ d$DI)
summary(aov.d)

            Df Sum Sq Mean Sq F value Pr(>F)    
d$DI         1  24328   24328    1039 <2e-16 ***
Residuals   48   1124      23                   
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Hoja “e”

plot(e$Y1 ~e$X1, pch=20)

#
lm.e <- lm(e$Y1 ~e$X1)
summary(lm.e)

Call:
lm(formula = e$Y1 ~ e$X1)

Residuals:
    Min      1Q  Median      3Q     Max 
-5.8836 -1.5655 -0.3844  1.8105  5.5297 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept) 139.9691     1.0328 135.520   <2e-16 ***
e$X1n2       -0.2548     1.4606  -0.174    0.863    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 3.266 on 18 degrees of freedom
Multiple R-squared:  0.001687,  Adjusted R-squared:  -0.05377 
F-statistic: 0.03042 on 1 and 18 DF,  p-value: 0.8635

#
aov.e <- aov(e$Y1 ~e$X1)

Hoja “f”

plot(f$y ~ f$grupo)

#
lm.f <- lm(f$y ~ f$grupo)
summary(lm.f)

Call:
lm(formula = f$y ~ f$grupo)

Residuals:
   Min     1Q Median     3Q    Max 
-4.479 -1.305  0.003  1.525  4.336 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  15.6117     0.3206  48.694   <2e-16 ***
f$grupoB     -0.8062     0.4477  -1.801   0.0757 .  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 1.976 on 76 degrees of freedom
Multiple R-squared:  0.04092,   Adjusted R-squared:  0.0283 
F-statistic: 3.242 on 1 and 76 DF,  p-value: 0.07573

#
aov.f <- aov(f$y ~ f$grupo)
summary(aov.f)

            Df Sum Sq Mean Sq F value Pr(>F)  
f$grupo      1  12.66  12.664   3.242 0.0757 .
Residuals   76 296.86   3.906                 
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1