1. Se quiere organizar un indicador complejo de pobreza, asumiendo
que las variables de calidad de techo, pared,piso y la disponibilidad de
agua representa cada una un concepto o variable latente.
names(data)
## [1] "...1" "key"
## [3] "Código" "pared1_Ladrillo"
## [5] "pared2_Piedra" "pared3_Adobe"
## [7] "pared4_Tapia" "pared5_Quincha"
## [9] "pared6_Piedra" "pared7_Madera"
## [11] "pared8_Triplay" "pared9_Otro"
## [13] "pared10_Total" "techo1_Concreto"
## [15] "techo2_Madera" "techo3_Tejas"
## [17] "techo4_Planchas" "techo5_Caña"
## [19] "techo6_Triplay" "techo7_Paja"
## [21] "techo8_Otro" "techo9_Total"
## [23] "piso1_Parquet" "piso2_Láminas"
## [25] "piso3_Losetas" "piso4_Madera"
## [27] "piso5_Cemento" "piso6_Tierra"
## [29] "piso7_Otro" "piso8_Total"
## [31] "agua1_Red" "agua2_Red_fueraVivienda"
## [33] "agua3_Pilón" "agua4_Camión"
## [35] "agua5_Pozo" "agua6_Manantial"
## [37] "agua7_Río" "agua8_Otro"
## [39] "agua9_Vecino" "agua10_Total"
## [41] "elec1_Sí" "elec2_No"
## [43] "elec3_Total" "departamento"
## [45] "provincia" "Castillo"
## [47] "Keiko" "ganaCastillo"
## [49] "countPositivos" "countFallecidos"
dontselect=c("...1" , "key", "Código","elec1_Sí","elec2_No","elec3_Total","departamento","provincia","Castillo","Keiko","ganaCastillo","countPositivos","countFallecidos","pared9_Otro", "techo8_Otro","piso7_Otro","agua8_Otro", "techo9_Total", "pared10_Total","piso8_Total","agua10_Total" )
select=setdiff(names(data),dontselect)
theData=data[,select]
# usaremos:
library(magrittr)
head(theData,10)%>%
rmarkdown::paged_table()
library(polycor)
## Warning: package 'polycor' was built under R version 4.3.3
corMatrix=polycor::hetcor(theData)$correlations
round(corMatrix,2)
## pared1_Ladrillo pared2_Piedra pared3_Adobe pared4_Tapia
## pared1_Ladrillo 1.00 0.65 0.35 -0.03
## pared2_Piedra 0.65 1.00 0.20 -0.05
## pared3_Adobe 0.35 0.20 1.00 0.00
## pared4_Tapia -0.03 -0.05 0.00 1.00
## pared5_Quincha 0.22 0.14 0.15 -0.11
## pared6_Piedra 0.07 0.10 0.18 0.06
## pared7_Madera 0.89 0.50 0.16 -0.09
## pared8_Triplay 0.85 0.50 0.27 -0.09
## techo1_Concreto 1.00 0.65 0.35 -0.02
## techo2_Madera 0.96 0.55 0.26 -0.04
## techo3_Tejas 0.13 0.04 0.45 0.41
## techo4_Planchas 0.92 0.62 0.46 -0.02
## techo5_Caña 0.44 0.24 0.38 -0.13
## techo6_Triplay 0.84 0.49 0.29 -0.10
## techo7_Paja 0.04 0.02 0.08 -0.12
## piso1_Parquet 0.99 0.59 0.31 -0.02
## piso2_Láminas 0.99 0.69 0.30 -0.03
## piso3_Losetas 1.00 0.62 0.36 -0.03
## piso4_Madera 0.57 0.32 0.12 -0.02
## piso5_Cemento 1.00 0.67 0.38 -0.03
## piso6_Tierra 0.69 0.45 0.72 0.14
## agua1_Red 1.00 0.64 0.39 -0.02
## agua2_Red_fueraVivienda 0.99 0.59 0.40 0.01
## agua3_Pilón 0.91 0.84 0.38 -0.02
## agua4_Camión 0.99 0.61 0.33 -0.06
## agua5_Pozo 0.37 0.25 0.45 0.02
## agua6_Manantial -0.05 -0.03 0.27 0.24
## agua7_Río 0.01 0.00 0.06 -0.06
## agua9_Vecino 0.94 0.55 0.41 -0.03
## pared5_Quincha pared6_Piedra pared7_Madera
## pared1_Ladrillo 0.22 0.07 0.89
## pared2_Piedra 0.14 0.10 0.50
## pared3_Adobe 0.15 0.18 0.16
## pared4_Tapia -0.11 0.06 -0.09
## pared5_Quincha 1.00 -0.03 0.17
## pared6_Piedra -0.03 1.00 0.04
## pared7_Madera 0.17 0.04 1.00
## pared8_Triplay 0.45 0.04 0.74
## techo1_Concreto 0.20 0.07 0.88
## techo2_Madera 0.18 0.05 0.94
## techo3_Tejas -0.05 0.00 0.03
## techo4_Planchas 0.43 0.12 0.87
## techo5_Caña 0.16 -0.05 0.31
## techo6_Triplay 0.25 0.03 0.73
## techo7_Paja -0.06 0.26 0.24
## piso1_Parquet 0.17 0.07 0.89
## piso2_Láminas 0.18 0.07 0.88
## piso3_Losetas 0.22 0.06 0.89
## piso4_Madera 0.04 0.02 0.76
## piso5_Cemento 0.24 0.07 0.89
## piso6_Tierra 0.50 0.23 0.58
## agua1_Red 0.24 0.07 0.89
## agua2_Red_fueraVivienda 0.21 0.10 0.90
## agua3_Pilón 0.28 0.11 0.79
## agua4_Camión 0.27 0.06 0.88
## agua5_Pozo 0.07 0.24 0.45
## agua6_Manantial -0.04 0.39 0.00
## agua7_Río 0.47 0.10 0.19
## agua9_Vecino 0.45 0.06 0.86
## pared8_Triplay techo1_Concreto techo2_Madera
## pared1_Ladrillo 0.85 1.00 0.96
## pared2_Piedra 0.50 0.65 0.55
## pared3_Adobe 0.27 0.35 0.26
## pared4_Tapia -0.09 -0.02 -0.04
## pared5_Quincha 0.45 0.20 0.18
## pared6_Piedra 0.04 0.07 0.05
## pared7_Madera 0.74 0.88 0.94
## pared8_Triplay 1.00 0.84 0.79
## techo1_Concreto 0.84 1.00 0.96
## techo2_Madera 0.79 0.96 1.00
## techo3_Tejas 0.04 0.13 0.10
## techo4_Planchas 0.85 0.91 0.88
## techo5_Caña 0.51 0.44 0.39
## techo6_Triplay 0.93 0.83 0.80
## techo7_Paja 0.01 0.04 0.08
## piso1_Parquet 0.81 0.99 0.96
## piso2_Láminas 0.81 0.99 0.96
## piso3_Losetas 0.85 1.00 0.97
## piso4_Madera 0.47 0.56 0.61
## piso5_Cemento 0.85 0.99 0.96
## piso6_Tierra 0.72 0.68 0.61
## agua1_Red 0.85 1.00 0.96
## agua2_Red_fueraVivienda 0.82 0.99 0.96
## agua3_Pilón 0.79 0.91 0.86
## agua4_Camión 0.89 0.99 0.95
## agua5_Pozo 0.29 0.37 0.36
## agua6_Manantial -0.08 -0.05 -0.05
## agua7_Río 0.22 -0.02 0.00
## agua9_Vecino 0.88 0.93 0.90
## techo3_Tejas techo4_Planchas techo5_Caña techo6_Triplay
## pared1_Ladrillo 0.13 0.92 0.44 0.84
## pared2_Piedra 0.04 0.62 0.24 0.49
## pared3_Adobe 0.45 0.46 0.38 0.29
## pared4_Tapia 0.41 -0.02 -0.13 -0.10
## pared5_Quincha -0.05 0.43 0.16 0.25
## pared6_Piedra 0.00 0.12 -0.05 0.03
## pared7_Madera 0.03 0.87 0.31 0.73
## pared8_Triplay 0.04 0.85 0.51 0.93
## techo1_Concreto 0.13 0.91 0.44 0.83
## techo2_Madera 0.10 0.88 0.39 0.80
## techo3_Tejas 1.00 0.09 -0.05 0.03
## techo4_Planchas 0.09 1.00 0.37 0.76
## techo5_Caña -0.05 0.37 1.00 0.66
## techo6_Triplay 0.03 0.76 0.66 1.00
## techo7_Paja -0.13 0.13 -0.11 -0.02
## piso1_Parquet 0.13 0.89 0.38 0.80
## piso2_Láminas 0.12 0.89 0.38 0.80
## piso3_Losetas 0.14 0.92 0.44 0.84
## piso4_Madera 0.16 0.63 0.14 0.43
## piso5_Cemento 0.13 0.93 0.47 0.85
## piso6_Tierra 0.32 0.84 0.36 0.62
## agua1_Red 0.16 0.93 0.46 0.84
## agua2_Red_fueraVivienda 0.19 0.92 0.40 0.81
## agua3_Pilón 0.11 0.90 0.38 0.76
## agua4_Camión 0.10 0.91 0.46 0.88
## agua5_Pozo 0.04 0.51 0.15 0.26
## agua6_Manantial 0.19 0.06 -0.13 -0.10
## agua7_Río -0.10 0.27 -0.03 0.04
## agua9_Vecino 0.13 0.96 0.45 0.81
## techo7_Paja piso1_Parquet piso2_Láminas piso3_Losetas
## pared1_Ladrillo 0.04 0.99 0.99 1.00
## pared2_Piedra 0.02 0.59 0.69 0.62
## pared3_Adobe 0.08 0.31 0.30 0.36
## pared4_Tapia -0.12 -0.02 -0.03 -0.03
## pared5_Quincha -0.06 0.17 0.18 0.22
## pared6_Piedra 0.26 0.07 0.07 0.06
## pared7_Madera 0.24 0.89 0.88 0.89
## pared8_Triplay 0.01 0.81 0.81 0.85
## techo1_Concreto 0.04 0.99 0.99 1.00
## techo2_Madera 0.08 0.96 0.96 0.97
## techo3_Tejas -0.13 0.13 0.12 0.14
## techo4_Planchas 0.13 0.89 0.89 0.92
## techo5_Caña -0.11 0.38 0.38 0.44
## techo6_Triplay -0.02 0.80 0.80 0.84
## techo7_Paja 1.00 0.05 0.05 0.04
## piso1_Parquet 0.05 1.00 0.99 0.99
## piso2_Láminas 0.05 0.99 1.00 0.99
## piso3_Losetas 0.04 0.99 0.99 1.00
## piso4_Madera 0.34 0.57 0.56 0.57
## piso5_Cemento 0.04 0.98 0.98 0.99
## piso6_Tierra 0.20 0.63 0.64 0.68
## agua1_Red 0.04 0.98 0.99 1.00
## agua2_Red_fueraVivienda 0.06 0.99 0.98 0.99
## agua3_Pilón 0.08 0.87 0.92 0.90
## agua4_Camión 0.03 0.98 0.98 0.99
## agua5_Pozo 0.51 0.35 0.35 0.35
## agua6_Manantial 0.33 -0.04 -0.05 -0.06
## agua7_Río 0.43 -0.03 -0.03 0.01
## agua9_Vecino 0.06 0.91 0.91 0.94
## piso4_Madera piso5_Cemento piso6_Tierra agua1_Red
## pared1_Ladrillo 0.57 1.00 0.69 1.00
## pared2_Piedra 0.32 0.67 0.45 0.64
## pared3_Adobe 0.12 0.38 0.72 0.39
## pared4_Tapia -0.02 -0.03 0.14 -0.02
## pared5_Quincha 0.04 0.24 0.50 0.24
## pared6_Piedra 0.02 0.07 0.23 0.07
## pared7_Madera 0.76 0.89 0.58 0.89
## pared8_Triplay 0.47 0.85 0.72 0.85
## techo1_Concreto 0.56 0.99 0.68 1.00
## techo2_Madera 0.61 0.96 0.61 0.96
## techo3_Tejas 0.16 0.13 0.32 0.16
## techo4_Planchas 0.63 0.93 0.84 0.93
## techo5_Caña 0.14 0.47 0.36 0.46
## techo6_Triplay 0.43 0.85 0.62 0.84
## techo7_Paja 0.34 0.04 0.20 0.04
## piso1_Parquet 0.57 0.98 0.63 0.98
## piso2_Láminas 0.56 0.98 0.64 0.99
## piso3_Losetas 0.57 0.99 0.68 1.00
## piso4_Madera 1.00 0.58 0.38 0.58
## piso5_Cemento 0.58 1.00 0.71 1.00
## piso6_Tierra 0.38 0.71 1.00 0.72
## agua1_Red 0.58 1.00 0.72 1.00
## agua2_Red_fueraVivienda 0.59 0.98 0.72 0.99
## agua3_Pilón 0.51 0.92 0.73 0.91
## agua4_Camión 0.56 0.98 0.69 0.99
## agua5_Pozo 0.43 0.40 0.59 0.38
## agua6_Manantial -0.01 -0.05 0.30 -0.05
## agua7_Río 0.35 0.02 0.37 0.02
## agua9_Vecino 0.59 0.94 0.79 0.95
## agua2_Red_fueraVivienda agua3_Pilón agua4_Camión
## pared1_Ladrillo 0.99 0.91 0.99
## pared2_Piedra 0.59 0.84 0.61
## pared3_Adobe 0.40 0.38 0.33
## pared4_Tapia 0.01 -0.02 -0.06
## pared5_Quincha 0.21 0.28 0.27
## pared6_Piedra 0.10 0.11 0.06
## pared7_Madera 0.90 0.79 0.88
## pared8_Triplay 0.82 0.79 0.89
## techo1_Concreto 0.99 0.91 0.99
## techo2_Madera 0.96 0.86 0.95
## techo3_Tejas 0.19 0.11 0.10
## techo4_Planchas 0.92 0.90 0.91
## techo5_Caña 0.40 0.38 0.46
## techo6_Triplay 0.81 0.76 0.88
## techo7_Paja 0.06 0.08 0.03
## piso1_Parquet 0.99 0.87 0.98
## piso2_Láminas 0.98 0.92 0.98
## piso3_Losetas 0.99 0.90 0.99
## piso4_Madera 0.59 0.51 0.56
## piso5_Cemento 0.98 0.92 0.98
## piso6_Tierra 0.72 0.73 0.69
## agua1_Red 0.99 0.91 0.99
## agua2_Red_fueraVivienda 1.00 0.88 0.97
## agua3_Pilón 0.88 1.00 0.89
## agua4_Camión 0.97 0.89 1.00
## agua5_Pozo 0.39 0.40 0.34
## agua6_Manantial 0.03 0.01 -0.07
## agua7_Río 0.01 0.10 0.03
## agua9_Vecino 0.93 0.86 0.94
## agua5_Pozo agua6_Manantial agua7_Río agua9_Vecino
## pared1_Ladrillo 0.37 -0.05 0.01 0.94
## pared2_Piedra 0.25 -0.03 0.00 0.55
## pared3_Adobe 0.45 0.27 0.06 0.41
## pared4_Tapia 0.02 0.24 -0.06 -0.03
## pared5_Quincha 0.07 -0.04 0.47 0.45
## pared6_Piedra 0.24 0.39 0.10 0.06
## pared7_Madera 0.45 0.00 0.19 0.86
## pared8_Triplay 0.29 -0.08 0.22 0.88
## techo1_Concreto 0.37 -0.05 -0.02 0.93
## techo2_Madera 0.36 -0.05 0.00 0.90
## techo3_Tejas 0.04 0.19 -0.10 0.13
## techo4_Planchas 0.51 0.06 0.27 0.96
## techo5_Caña 0.15 -0.13 -0.03 0.45
## techo6_Triplay 0.26 -0.10 0.04 0.81
## techo7_Paja 0.51 0.33 0.43 0.06
## piso1_Parquet 0.35 -0.04 -0.03 0.91
## piso2_Láminas 0.35 -0.05 -0.03 0.91
## piso3_Losetas 0.35 -0.06 0.01 0.94
## piso4_Madera 0.43 -0.01 0.35 0.59
## piso5_Cemento 0.40 -0.05 0.02 0.94
## piso6_Tierra 0.59 0.30 0.37 0.79
## agua1_Red 0.38 -0.05 0.02 0.95
## agua2_Red_fueraVivienda 0.39 0.03 0.01 0.93
## agua3_Pilón 0.40 0.01 0.10 0.86
## agua4_Camión 0.34 -0.07 0.03 0.94
## agua5_Pozo 1.00 0.29 0.27 0.42
## agua6_Manantial 0.29 1.00 0.31 -0.06
## agua7_Río 0.27 0.31 1.00 0.16
## agua9_Vecino 0.42 -0.06 0.16 1.00
library(ggcorrplot)
## Warning: package 'ggcorrplot' was built under R version 4.3.3
## Loading required package: ggplot2
ggcorrplot(corMatrix)
#matriz
library(psych)
##
## Attaching package: 'psych'
## The following objects are masked from 'package:ggplot2':
##
## %+%, alpha
## The following object is masked from 'package:polycor':
##
## polyserial
psych::KMO(corMatrix)
## Kaiser-Meyer-Olkin factor adequacy
## Call: psych::KMO(r = corMatrix)
## Overall MSA = 0.43
## MSA for each item =
## pared1_Ladrillo pared2_Piedra pared3_Adobe
## 0.49 0.29 0.16
## pared4_Tapia pared5_Quincha pared6_Piedra
## 0.02 0.10 0.03
## pared7_Madera pared8_Triplay techo1_Concreto
## 0.44 0.43 0.49
## techo2_Madera techo3_Tejas techo4_Planchas
## 0.47 0.05 0.47
## techo5_Caña techo6_Triplay techo7_Paja
## 0.18 0.42 0.06
## piso1_Parquet piso2_Láminas piso3_Losetas
## 0.74 0.74 0.75
## piso4_Madera piso5_Cemento piso6_Tierra
## 0.54 0.75 0.65
## agua1_Red agua2_Red_fueraVivienda agua3_Pilón
## 0.59 0.59 0.54
## agua4_Camión agua5_Pozo agua6_Manantial
## 0.59 0.25 0.07
## agua7_Río agua9_Vecino
## 0.10 0.60
cortest.bartlett(corMatrix,n=nrow(theData))$p.value>0.05
## [1] FALSE
library(matrixcalc)
is.singular.matrix(corMatrix)
## [1] TRUE
fa.parallel(theData, fa = 'fa',correct = T,plot = F)
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully
## Parallel analysis suggests that the number of factors = 4 and the number of components = NA
VARIMAX
library(GPArotation)
## Warning: package 'GPArotation' was built under R version 4.3.3
##
## Attaching package: 'GPArotation'
## The following objects are masked from 'package:psych':
##
## equamax, varimin
resfa <- fa(theData,
nfactors = 4,
cor = 'mixed',
rotate = "varimax", #oblimin?
fm="minres")
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully
print(resfa$loadings)
##
## Loadings:
## MR1 MR2 MR4 MR3
## pared1_Ladrillo 0.991
## pared2_Piedra 0.631
## pared3_Adobe 0.274 0.151 0.299 0.639
## pared4_Tapia -0.116 0.379
## pared5_Quincha 0.165 0.735
## pared6_Piedra 0.321 0.209
## pared7_Madera 0.905 0.317 -0.162
## pared8_Triplay 0.827 0.448
## techo1_Concreto 0.991
## techo2_Madera 0.970
## techo3_Tejas 0.591
## techo4_Planchas 0.882 0.256 0.335
## techo5_Caña 0.429 -0.179 0.280
## techo6_Triplay 0.833 0.286
## techo7_Paja 0.767 -0.115
## piso1_Parquet 0.985
## piso2_Láminas 0.990
## piso3_Losetas 0.989
## piso4_Madera 0.584 0.426 -0.125
## piso5_Cemento 0.987 0.112
## piso6_Tierra 0.592 0.346 0.560 0.502
## agua1_Red 0.985 0.110 0.119
## agua2_Red_fueraVivienda 0.970 0.165
## agua3_Pilón 0.891 0.107 0.176 0.119
## agua4_Camión 0.980 0.149
## agua5_Pozo 0.331 0.588 0.207
## agua6_Manantial -0.115 0.499 0.395
## agua7_Río 0.608 0.515 -0.196
## agua9_Vecino 0.908 0.339
##
## MR1 MR2 MR4 MR3
## SS loadings 15.787 2.237 1.929 1.621
## Proportion Var 0.544 0.077 0.067 0.056
## Cumulative Var 0.544 0.621 0.688 0.744
OBLIMIN
library(GPArotation)
resfa2 <- fa(theData,
nfactors = 4,
cor = 'mixed',
rotate = "oblimin", #oblimin?
fm="minres")
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully
print(resfa2$loadings)
##
## Loadings:
## MR1 MR3 MR2 MR4
## pared1_Ladrillo 0.998
## pared2_Piedra 0.634
## pared3_Adobe 0.732
## pared4_Tapia 0.366 -0.250
## pared5_Quincha 0.738
## pared6_Piedra 0.267 0.268
## pared7_Madera 0.956 -0.191 0.305
## pared8_Triplay 0.777 0.393
## techo1_Concreto 1.003
## techo2_Madera 1.009
## techo3_Tejas 0.580 -0.133 -0.283
## techo4_Planchas 0.814 0.151 0.142 0.215
## techo5_Caña 0.388 -0.245 0.224
## techo6_Triplay 0.815 -0.166 0.218
## techo7_Paja 0.779
## piso1_Parquet 1.014 -0.110
## piso2_Láminas 1.019
## piso3_Losetas 0.996
## piso4_Madera 0.615 -0.114 0.423
## piso5_Cemento 0.985
## piso6_Tierra 0.383 0.664 0.124 0.303
## agua1_Red 0.980
## agua2_Red_fueraVivienda 0.963 0.116
## agua3_Pilón 0.863 0.108
## agua4_Camión 0.984
## agua5_Pozo 0.250 0.311 0.500
## agua6_Manantial -0.229 0.509 0.402 -0.122
## agua7_Río -0.161 0.564 0.563
## agua9_Vecino 0.856 0.232
##
## MR1 MR3 MR2 MR4
## SS loadings 15.464 2.009 1.852 1.523
## Proportion Var 0.533 0.069 0.064 0.053
## Cumulative Var 0.533 0.603 0.666 0.719
print(resfa$loadings,cutoff = 0.5)
##
## Loadings:
## MR1 MR2 MR4 MR3
## pared1_Ladrillo 0.991
## pared2_Piedra 0.631
## pared3_Adobe 0.639
## pared4_Tapia
## pared5_Quincha 0.735
## pared6_Piedra
## pared7_Madera 0.905
## pared8_Triplay 0.827
## techo1_Concreto 0.991
## techo2_Madera 0.970
## techo3_Tejas 0.591
## techo4_Planchas 0.882
## techo5_Caña
## techo6_Triplay 0.833
## techo7_Paja 0.767
## piso1_Parquet 0.985
## piso2_Láminas 0.990
## piso3_Losetas 0.989
## piso4_Madera 0.584
## piso5_Cemento 0.987
## piso6_Tierra 0.592 0.560 0.502
## agua1_Red 0.985
## agua2_Red_fueraVivienda 0.970
## agua3_Pilón 0.891
## agua4_Camión 0.980
## agua5_Pozo 0.588
## agua6_Manantial
## agua7_Río 0.608 0.515
## agua9_Vecino 0.908
##
## MR1 MR2 MR4 MR3
## SS loadings 15.787 2.237 1.929 1.621
## Proportion Var 0.544 0.077 0.067 0.056
## Cumulative Var 0.544 0.621 0.688 0.744
fa.diagram(resfa,main = "Resultados del EFA")
#valores que aportan más
sort(resfa$communality)
## pared6_Piedra pared4_Tapia techo5_Caña
## 0.1479411 0.1599348 0.2971420
## techo3_Tejas pared2_Piedra agua6_Manantial
## 0.3611027 0.4059884 0.4187500
## agua5_Pozo piso4_Madera pared5_Quincha
## 0.5072346 0.5401829 0.5768864
## pared3_Adobe techo7_Paja agua7_Río
## 0.5958685 0.6045122 0.6748916
## techo6_Triplay agua3_Pilón pared8_Triplay
## 0.7840876 0.8502469 0.8888532
## pared7_Madera techo2_Madera agua9_Vecino
## 0.9457654 0.9479949 0.9521136
## techo4_Planchas piso1_Parquet agua2_Red_fueraVivienda
## 0.9654449 0.9766272 0.9802470
## agua4_Camión piso2_Láminas piso3_Losetas
## 0.9847153 0.9860292 0.9929105
## techo1_Concreto pared1_Ladrillo agua1_Red
## 0.9958066 0.9977988 0.9992224
## piso5_Cemento piso6_Tierra
## 0.9994736 1.0358692
sort(resfa$complexity)
## piso2_Láminas piso1_Parquet techo2_Madera
## 1.011784 1.014342 1.016012
## techo1_Concreto piso3_Losetas pared1_Ladrillo
## 1.027309 1.031529 1.032962
## pared2_Piedra agua4_Camión piso5_Cemento
## 1.039372 1.048692 1.050759
## techo7_Paja agua1_Red techo3_Tejas
## 1.056476 1.058431 1.069872
## agua2_Red_fueraVivienda pared5_Quincha agua3_Pilón
## 1.085726 1.139839 1.145980
## pared4_Tapia techo6_Triplay agua9_Vecino
## 1.233110 1.259537 1.310512
## pared7_Madera techo4_Planchas pared8_Triplay
## 1.311682 1.495958 1.552028
## pared6_Piedra agua5_Pozo piso4_Madera
## 1.742245 1.931349 1.949594
## pared3_Adobe agua6_Manantial techo5_Caña
## 1.958637 2.029351 2.156064
## agua7_Río piso6_Tierra
## 2.188219 3.587191
2. Utilizando el porcentaje de viviendas que tiene electricidad, la
razón de votacion de castillo entre keiko, y la tasa fallecidos por cada
1000 contagiados, Ud se propone agrupar a las provincias del Peru (sin
la provincia de Lima) siguiendo una estrategia aglomerativa (no corrija
correlacion negativa si la hubiera); y en ese proceso Ud.
encuentra…
names(data)
## [1] "...1" "key"
## [3] "Código" "pared1_Ladrillo"
## [5] "pared2_Piedra" "pared3_Adobe"
## [7] "pared4_Tapia" "pared5_Quincha"
## [9] "pared6_Piedra" "pared7_Madera"
## [11] "pared8_Triplay" "pared9_Otro"
## [13] "pared10_Total" "techo1_Concreto"
## [15] "techo2_Madera" "techo3_Tejas"
## [17] "techo4_Planchas" "techo5_Caña"
## [19] "techo6_Triplay" "techo7_Paja"
## [21] "techo8_Otro" "techo9_Total"
## [23] "piso1_Parquet" "piso2_Láminas"
## [25] "piso3_Losetas" "piso4_Madera"
## [27] "piso5_Cemento" "piso6_Tierra"
## [29] "piso7_Otro" "piso8_Total"
## [31] "agua1_Red" "agua2_Red_fueraVivienda"
## [33] "agua3_Pilón" "agua4_Camión"
## [35] "agua5_Pozo" "agua6_Manantial"
## [37] "agua7_Río" "agua8_Otro"
## [39] "agua9_Vecino" "agua10_Total"
## [41] "elec1_Sí" "elec2_No"
## [43] "elec3_Total" "departamento"
## [45] "provincia" "Castillo"
## [47] "Keiko" "ganaCastillo"
## [49] "countPositivos" "countFallecidos"
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
preg2<- data%>%
select(provincia,elec1_Sí, elec2_No, Castillo, Keiko, ganaCastillo, countPositivos, countFallecidos)
head(preg2)
## provincia elec1_Sí elec2_No Castillo Keiko ganaCastillo
## 1 BAGUA 13204 6316 25629 10770 1
## 2 BONGARA 6025 1283 8374 5209 1
## 3 CHACHAPOYAS 12248 1751 15671 10473 1
## 4 CONDORCANQUI 1792 7924 13154 1446 1
## 5 LUYA 10886 1871 12606 7840 1
## 6 RODRÍGUEZ DE MENDOZA 6895 2009 7967 5491 1
## countPositivos countFallecidos
## 1 8126 462
## 2 389 72
## 3 2174 281
## 4 3481 111
## 5 456 88
## 6 110 60
datos_sin_lima <- preg2 %>%
filter(provincia != "Lima")
names(preg2)
## [1] "provincia" "elec1_Sí" "elec2_No" "Castillo"
## [5] "Keiko" "ganaCastillo" "countPositivos" "countFallecidos"
dataClus=preg2[,c(2:8)]
row.names(dataClus)=preg2$provincia
library(cluster)
g.dist = daisy(dataClus, metric="gower")
## Warning in daisy(dataClus, metric = "gower"): binary variable(s) 5 treated as
## interval scaled
## para PAM
library(factoextra)
## Warning: package 'factoextra' was built under R version 4.3.3
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
fviz_nbclust(dataClus, pam,diss=g.dist,method = "gap_stat",k.max = 10,verbose = F)
library(kableExtra)
## Warning: package 'kableExtra' was built under R version 4.3.2
##
## Attaching package: 'kableExtra'
## The following object is masked from 'package:dplyr':
##
## group_rows
set.seed(123)
res.pam=pam(g.dist,3,cluster.only = F)
#nueva columna
dataClus$pam=res.pam$cluster
# ver
head(dataClus,15)%>%kbl()%>%kable_styling()
|
|
elec1_Sí
|
elec2_No
|
Castillo
|
Keiko
|
ganaCastillo
|
countPositivos
|
countFallecidos
|
pam
|
|
BAGUA
|
13204
|
6316
|
25629
|
10770
|
1
|
8126
|
462
|
1
|
|
BONGARA
|
6025
|
1283
|
8374
|
5209
|
1
|
389
|
72
|
1
|
|
CHACHAPOYAS
|
12248
|
1751
|
15671
|
10473
|
1
|
2174
|
281
|
1
|
|
CONDORCANQUI
|
1792
|
7924
|
13154
|
1446
|
1
|
3481
|
111
|
1
|
|
LUYA
|
10886
|
1871
|
12606
|
7840
|
1
|
456
|
88
|
1
|
|
RODRÍGUEZ DE MENDOZA
|
6895
|
2009
|
7967
|
5491
|
1
|
110
|
60
|
1
|
|
UTCUBAMBA
|
24395
|
5808
|
36540
|
19222
|
1
|
3749
|
336
|
1
|
|
AIJA
|
1528
|
413
|
2325
|
1413
|
1
|
79
|
26
|
1
|
|
ANTONIO RAYMONDI
|
3089
|
697
|
5056
|
788
|
1
|
54
|
31
|
1
|
|
ASUNCIÓN
|
2032
|
270
|
2860
|
827
|
1
|
59
|
21
|
1
|
|
BOLOGNESI
|
5375
|
1443
|
7690
|
3994
|
1
|
242
|
96
|
1
|
|
CARHUAZ
|
10348
|
2655
|
18781
|
8590
|
1
|
552
|
163
|
1
|
|
CARLOS FERMÍN FITZCARRALD
|
3398
|
1790
|
6462
|
1697
|
1
|
56
|
34
|
1
|
|
CASMA
|
11637
|
2924
|
11328
|
15546
|
0
|
963
|
362
|
2
|
|
CORONGO
|
1816
|
209
|
2174
|
1460
|
1
|
37
|
19
|
1
|
fviz_silhouette(res.pam,print.summary = F)
AGLOMERATIVA
## PARA JERARQUICO
fviz_nbclust(dataClus, hcut,diss=g.dist,method = "gap_stat",k.max = 10,verbose = F,hc_func = "agnes")
set.seed(123)
library(factoextra)
res.agnes<- hcut(g.dist, k = 3,hc_func='agnes',hc_method = "ward.D")
dataClus$agnes=res.agnes$cluster
# ver
head(dataClus,15)%>%kbl()%>%kable_styling()
|
|
elec1_Sí
|
elec2_No
|
Castillo
|
Keiko
|
ganaCastillo
|
countPositivos
|
countFallecidos
|
pam
|
agnes
|
|
BAGUA
|
13204
|
6316
|
25629
|
10770
|
1
|
8126
|
462
|
1
|
1
|
|
BONGARA
|
6025
|
1283
|
8374
|
5209
|
1
|
389
|
72
|
1
|
1
|
|
CHACHAPOYAS
|
12248
|
1751
|
15671
|
10473
|
1
|
2174
|
281
|
1
|
1
|
|
CONDORCANQUI
|
1792
|
7924
|
13154
|
1446
|
1
|
3481
|
111
|
1
|
1
|
|
LUYA
|
10886
|
1871
|
12606
|
7840
|
1
|
456
|
88
|
1
|
1
|
|
RODRÍGUEZ DE MENDOZA
|
6895
|
2009
|
7967
|
5491
|
1
|
110
|
60
|
1
|
1
|
|
UTCUBAMBA
|
24395
|
5808
|
36540
|
19222
|
1
|
3749
|
336
|
1
|
1
|
|
AIJA
|
1528
|
413
|
2325
|
1413
|
1
|
79
|
26
|
1
|
1
|
|
ANTONIO RAYMONDI
|
3089
|
697
|
5056
|
788
|
1
|
54
|
31
|
1
|
1
|
|
ASUNCIÓN
|
2032
|
270
|
2860
|
827
|
1
|
59
|
21
|
1
|
1
|
|
BOLOGNESI
|
5375
|
1443
|
7690
|
3994
|
1
|
242
|
96
|
1
|
1
|
|
CARHUAZ
|
10348
|
2655
|
18781
|
8590
|
1
|
552
|
163
|
1
|
1
|
|
CARLOS FERMÍN FITZCARRALD
|
3398
|
1790
|
6462
|
1697
|
1
|
56
|
34
|
1
|
1
|
|
CASMA
|
11637
|
2924
|
11328
|
15546
|
0
|
963
|
362
|
2
|
2
|
|
CORONGO
|
1816
|
209
|
2174
|
1460
|
1
|
37
|
19
|
1
|
1
|
# Visualize
fviz_dend(res.agnes, cex = 0.7, horiz = T,main = "")
## Warning: The `<scale>` argument of `guides()` cannot be `FALSE`. Use "none" instead as
## of ggplot2 3.3.4.
## ℹ The deprecated feature was likely used in the factoextra package.
## Please report the issue at <https://github.com/kassambara/factoextra/issues>.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
