Resultados del Anova

Se encontro que en los muestreos, los datos de Hormigas del hormiguero 1 (x=0.00785±0.00955,n=90), hormiguero 2 (x=0.00690±0.00340, n=90), hormiguero 3 (x=0.00725±0.01080, n=90) y hormiguero4(x=0.0040±0.00457, n=90); tienen una distribucion normaled los residuos (p-value<0.05) y una igualdad de las varianzas no significativa (p-value=0.3). Segin la prueba de Fisher tienen ldiferencias significativas (F=7.09, gl=356, p<0.05)

library(readr)
datosh <- read_delim("C:/Users/una/Desktop/datosh1.csv",    ";", escape_double = FALSE, trim_ws = TRUE)
## Parsed with column specification:
## cols(
##   Hormiga = col_double(),
##   Hoja = col_double(),
##   Propor = col_double(),
##   Hormiguero = col_character(),
##   Muestreo = col_character(),
##   Temperatura = col_integer(),
##   Distancia = col_double()
## )
attach(datosh)

tapply(datosh$Hormiga, datosh$Hormiguero, length) 
## H1 H2 H3 H4 
## 90 90 90 90
tapply(datosh$Hormiga, datosh$Hormiguero, median)  
##      H1      H2      H3      H4 
## 0.00785 0.00690 0.00725 0.00440
tapply(datosh$Hormiga, datosh$Hormiguero, sd)
##          H1          H2          H3          H4 
## 0.009553809 0.003404704 0.010803538 0.004567322
shapiro.test(datosh$Hormiga)
## 
##  Shapiro-Wilk normality test
## 
## data:  datosh$Hormiga
## W = 0.53855, p-value < 2.2e-16
shapiro.test(datosh$Hoja)
## 
##  Shapiro-Wilk normality test
## 
## data:  datosh$Hoja
## W = 0.73286, p-value < 2.2e-16
shapiro.test(datosh$Propor)
## 
##  Shapiro-Wilk normality test
## 
## data:  datosh$Propor
## W = 0.40204, p-value < 2.2e-16
str(datosh)
## Classes 'tbl_df', 'tbl' and 'data.frame':    360 obs. of  7 variables:
##  $ Hormiga    : num  0.004 0.06 0.009 0.01 0.0073 0.0179 0.0168 0.0162 0.0041 0.0111 ...
##  $ Hoja       : num  0.0185 0.0068 0.0635 0.0329 0.0356 0.0508 0.0978 0.0974 0.031 0.0105 ...
##  $ Propor     : num  462.5 11.3 705.6 329 487.7 ...
##  $ Hormiguero : chr  "H1" "H1" "H1" "H1" ...
##  $ Muestreo   : chr  "n1" "n1" "n1" "n1" ...
##  $ Temperatura: int  20 20 20 20 20 20 20 20 20 20 ...
##  $ Distancia  : num  6.8 6.8 6.8 6.8 6.8 6.8 6.8 6.8 6.8 6.8 ...
##  - attr(*, "spec")=List of 2
##   ..$ cols   :List of 7
##   .. ..$ Hormiga    : list()
##   .. .. ..- attr(*, "class")= chr  "collector_double" "collector"
##   .. ..$ Hoja       : list()
##   .. .. ..- attr(*, "class")= chr  "collector_double" "collector"
##   .. ..$ Propor     : list()
##   .. .. ..- attr(*, "class")= chr  "collector_double" "collector"
##   .. ..$ Hormiguero : list()
##   .. .. ..- attr(*, "class")= chr  "collector_character" "collector"
##   .. ..$ Muestreo   : list()
##   .. .. ..- attr(*, "class")= chr  "collector_character" "collector"
##   .. ..$ Temperatura: list()
##   .. .. ..- attr(*, "class")= chr  "collector_integer" "collector"
##   .. ..$ Distancia  : list()
##   .. .. ..- attr(*, "class")= chr  "collector_double" "collector"
##   ..$ default: list()
##   .. ..- attr(*, "class")= chr  "collector_guess" "collector"
##   ..- attr(*, "class")= chr "col_spec"
names(datosh)
## [1] "Hormiga"     "Hoja"        "Propor"      "Hormiguero"  "Muestreo"   
## [6] "Temperatura" "Distancia"
aov(Hormiga~Hormiguero, data = datosh)->anova1
summary(anova1)
##              Df   Sum Sq   Mean Sq F value   Pr(>F)    
## Hormiguero    3 0.001279 0.0004263   7.092 0.000122 ***
## Residuals   356 0.021400 0.0000601                     
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
shapiro.test(anova1$residuals)
## 
##  Shapiro-Wilk normality test
## 
## data:  anova1$residuals
## W = 0.53019, p-value < 2.2e-16
fligner.test(Hormiga~as.factor(Hormiguero), data = datosh)
## 
##  Fligner-Killeen test of homogeneity of variances
## 
## data:  Hormiga by as.factor(Hormiguero)
## Fligner-Killeen:med chi-squared = 3.7788, df = 3, p-value = 0.2864