Los datos corresponden a un estudio realizado en n=10 sitios de muestreos, los cuales se visitaron en n=4 meses. En cada uno de los muestreos se realizo una cuantificacion de n=25 variables ambientales. Utilizando la variable que le corresponde segun la imagen anterior, resuelva lo que se solicita a continuacion:

datos<-("https://raw.githubusercontent.com/entomolab/bases_datos/master/base_datos01.csv")
data<-read.csv(datos,sep = ";", header = T, dec = ".")
head(data)
##       ï.. sample var01 var02 var03 var04 var05 var06 var07 var08 var09 var10
## 1 Sitio01      1    50 172.2  0.05   7.3  0.40 49000     8 86.00   3.3     8
## 2 Sitio01      2    54  26.0  0.05   8.5  0.40 49000     8 77.00   2.2    10
## 3 Sitio01      3    45 304.5  0.05   8.9  0.40   490    12 70.00   5.9    15
## 4 Sitio01      4    46  68.2  0.05   8.5  0.40  3300     5 88.00   5.7    10
## 5 sitio03      1    44  81.8  0.05   9.7  1.76   490     6  7.38   3.3     8
## 6 sitio03      2    46  82.6  0.05   7.6  1.69   490    19 85.00   8.0    18
##   var11 var12 var13 var14 var15 var16 var17 var18 var19 var20 var21 var22 var23
## 1    18    36  0.03   0.2  7.10  7.37    93   152  39.0   113  21.2  3.28    42
## 2    18    33  0.03   0.2  7.60  7.69    38    78   4.5    73  19.6  2.48    16
## 3    23    35  0.03   0.2  7.78  7.56    31    84   7.0    77  18.5  8.22    26
## 4    21    39  0.03   0.2  4.96  7.60    43   236  22.0   214  19.0  1,75    30
## 5    24    34  0.15   0.2  7.31  8.20    41   166  38.0   128  21.7  1.79    57
## 6    18    29  0.03   0.2  7.66  7.72    38    96  18.0    78  20.3 11.30    17
##   var24 var25
## 1     5    69
## 2     4    72
## 3     5    70
## 4     6    62
## 5     5    72
## 6     6    69
str(data)
## 'data.frame':    40 obs. of  27 variables:
##  $ ï..   : chr  "Sitio01" "Sitio01" "Sitio01" "Sitio01" ...
##  $ sample: int  1 2 3 4 1 2 3 4 1 2 ...
##  $ var01 : num  50 54 45 46 44 46 36 42 70 62 ...
##  $ var02 : num  172.2 26 304.5 68.2 81.8 ...
##  $ var03 : num  0.05 0.05 0.05 0.05 0.05 0.05 0.05 0.05 0.05 0.05 ...
##  $ var04 : num  7.3 8.5 8.9 8.5 9.7 7.6 6.2 8 18.5 15.7 ...
##  $ var05 : num  0.4 0.4 0.4 0.4 1.76 1.69 1.4 1.22 1.72 1.58 ...
##  $ var06 : num  49000 49000 490 3300 490 490 330 330 1700 4900 ...
##  $ var07 : num  8 8 12 5 6 19 7 10 4 26 ...
##  $ var08 : num  86 77 70 88 7.38 85 63 85 172 122 ...
##  $ var09 : num  3.3 2.2 5.9 5.7 3.3 8 2.6 0.65 3.9 29 ...
##  $ var10 : num  8 10 15 10 8 18 6 4 8 50 ...
##  $ var11 : num  18 18 23 21 24 18 16 20 46 35 ...
##  $ var12 : num  36 33 35 39 34 29 26 35 77 75 ...
##  $ var13 : num  0.03 0.03 0.03 0.03 0.15 0.03 0.03 0.03 0.15 0.03 ...
##  $ var14 : num  0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.2 0.2 ...
##  $ var15 : num  7.1 7.6 7.78 4.96 7.31 7.66 7.83 5.41 7.32 7.78 ...
##  $ var16 : num  7.37 7.69 7.56 7.6 8.2 7.72 7.73 7.77 7.86 7.32 ...
##  $ var17 : num  93 38 31 43 41 38 32 45 86 61 ...
##  $ var18 : num  152 78 84 236 166 96 86 265 212 268 ...
##  $ var19 : num  39 4.5 7 22 38 18 14 16 61 127 ...
##  $ var20 : num  113 73 77 214 128 78 72 240 151 141 ...
##  $ var21 : num  21.2 19.6 18.5 19 21.7 20.3 19.1 18.1 24.8 22.9 ...
##  $ var22 : chr  "3.28" "2.48" "8.22" "1,75" ...
##  $ var23 : num  42 16 26 30 57 17 39 24 69 27 ...
##  $ var24 : int  5 4 5 6 5 6 4 5 5 8 ...
##  $ var25 : int  69 72 70 62 72 69 72 71 70 57 ...
View(data)
  1. Calcule la media, mediana, desviación estándar y coeficiente de variación (%) por sitio de muestreo
s1 <- subset(data, data$ï.. =="Sitio01", "var13")
s1
##   var13
## 1  0.03
## 2  0.03
## 3  0.03
## 4  0.03
means1 <- mean(s1$var13)
means1
## [1] 0.03
medians1 <- median(s1$var13) 
medians1
## [1] 0.03
sds1 <- sd(s1$var13)
sds1
## [1] 0
cvs1 <- ((sds1/means1)*100)
cvs1
## [1] 0
s2 <- subset(data, data$ï.. =="sitio02", "var13")
s2
##    var13
## 37  0.18
## 38  0.25
## 39  0.03
## 40  0.03
means2 <- mean(s2$var13)
means2
## [1] 0.1225
medians2 <- median(s2$var13) 
medians2
## [1] 0.105
sds2 <- sd(s2$var13)
sds2
## [1] 0.1105667
cvs2 <- (sds2/means1)*100
cvs2
## [1] 368.5557
s3 <- subset(data, data$ï.. =="sitio03", "var13")
s3
##   var13
## 5  0.15
## 6  0.03
## 7  0.03
## 8  0.03
means3 <- mean(s3$var13)
means3
## [1] 0.06
medians3 <- median(s3$var13) 
medians3
## [1] 0.03
sds3 <- sd(s3$var13)
sds3
## [1] 0.06
cvs3 <- (sds3/means1)*100
cvs3
## [1] 200
s4 <- subset(data, data$ï.. =="sitio04", "var13")
s4
##    var13
## 9   0.15
## 10  0.03
## 11  0.03
## 12  0.03
means4 <- mean(s4$var13)
means4
## [1] 0.06
medians4 <- median(s4$var13) 
medians4
## [1] 0.03
sds4 <- sd(s4$var13)
sds4
## [1] 0.06
cvs4 <- (sds4/means1)*100
cvs4
## [1] 200
s5 <- subset(data, data$ï.. =="sitio05", "var13")
s5
##    var13
## 13  0.24
## 14  0.38
## 15  0.03
## 16  0.03
means5 <- mean(s5$var13)
means5
## [1] 0.17
medians5 <- median(s5$var13) 
medians5
## [1] 0.135
sds5 <- sd(s5$var13)
sds5
## [1] 0.1714643
cvs5 <- (sds5/means1)*100
cvs5
## [1] 571.5476
s6 <- subset(data, data$ï.. =="sitio06", "var13")
s6
##    var13
## 17  0.30
## 18  0.26
## 19  0.03
## 20  0.03
means6 <- mean(s6$var13)
means6
## [1] 0.155
medians6 <- median(s6$var13) 
medians6
## [1] 0.145
sds6 <- sd(s6$var13)
sds6
## [1] 0.1452584
cvs6 <- (sds6/means1)*100
cvs6
## [1] 484.1946
s7 <- subset(data, data$ï.. =="sitio07", "var13")
s7
##    var13
## 21  0.22
## 22  0.28
## 23  0.03
## 24  0.03
means7 <- mean(s7$var13)
means7
## [1] 0.14
medians7 <- median(s7$var13) 
medians7
## [1] 0.125
sds7 <- sd(s7$var13)
sds7
## [1] 0.1293574
cvs7 <- (sds7/means1)*100
cvs7
## [1] 431.1913
s8 <- subset(data, data$ï.. =="sitio08", "var13")
s8
##    var13
## 25  0.16
## 26  0.03
## 27  0.03
## 28  0.03
means8 <- mean(s8$var13)
means8
## [1] 0.0625
medians8 <- median(s8$var13) 
medians8
## [1] 0.03
sds8 <- sd(s8$var13)
sds8
## [1] 0.065
cvs8 <- (sds8/means1)*100
cvs8
## [1] 216.6667
s9 <- subset(data, data$ï.. =="sitio09", "var13")
s9
##    var13
## 29  0.32
## 30  0.31
## 31  0.03
## 32  0.03
means9 <- mean(s9$var13)
means9
## [1] 0.1725
medians9 <- median(s9$var13) 
medians9
## [1] 0.17
sds9 <- sd(s9$var13)
sds9
## [1] 0.1645955
cvs9 <- (sds9/means1)*100
cvs9
## [1] 548.6515
s10 <- subset(data, data$ï.. =="sitio10", "var13")
s10
##    var13
## 33  0.17
## 34  0.25
## 35  0.03
## 36  0.03
means10 <- mean(s10$var13)
means10
## [1] 0.12
medians10 <- median(s10$var13) 
medians10
## [1] 0.1
sds10 <- sd(s10$var13)
sds10
## [1] 0.1089342
cvs10 <- (sds10/means1)*100
cvs10
## [1] 363.1141
  1. Elabore una tabla de frecuencias para la totalidad de datos de la variable asignada siguiendo el criterio de Scot?
library(fdth)
## Warning: package 'fdth' was built under R version 4.1.3
## 
## Attaching package: 'fdth'
## The following objects are masked from 'package:stats':
## 
##     sd, var
variable13 <- fdt(data$var13, breaks = "Scott") #para tabla de frecuencia de var13
variable13
##     Class limits  f   rf rf(%) cf cf(%)
##  [0.0297,0.1182) 25 0.62  62.5 25  62.5
##  [0.1182,0.2068)  5 0.12  12.5 30  75.0
##  [0.2068,0.2953)  6 0.15  15.0 36  90.0
##  [0.2953,0.3838)  4 0.10  10.0 40 100.0
  1. Elabore un grafico de ggplot en el cual se considere la variable asignada (Eje X) y la variable 23 (Eje y). El grafico debe utilizar el tema clasico.
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.1.3
sd <- sd(data$var23)
sd
## [1] 16.54489
ggplot(data, aes(x=var13, y=var23, group=ï.., color=ï..)) + 
  geom_pointrange(aes(ymin=var23-sd, ymax=var23+sd))