IMPORTAR DATA
library(rio)
datita = import("dataOK_all.xlsx")
## New names:
## • `` -> `...1`
str(datita)
## 'data.frame': 196 obs. of 50 variables:
## $ ...1 : num 1 2 3 4 5 6 7 8 9 10 ...
## $ key : chr "AMAZONAS+BAGUA" "AMAZONAS+BONGARA" "AMAZONAS+CHACHAPOYAS" "AMAZONAS+CONDORCANQUI" ...
## $ Código : num 102 103 101 104 105 106 107 202 203 204 ...
## $ pared1_Ladrillo : num 4633 1602 3782 291 430 ...
## $ pared2_Piedra : num 46 9 22 7 7 7 35 1 0 3 ...
## $ pared3_Adobe : num 6639 2729 5881 672 5217 ...
## $ pared4_Tapia : num 222 240 2476 8 6052 ...
## $ pared5_Quincha : num 2518 157 309 386 346 ...
## $ pared6_Piedra : num 127 36 168 7 54 28 518 65 7 6 ...
## $ pared7_Madera : num 4484 2505 1270 8145 606 ...
## $ pared8_Triplay : num 851 30 91 200 45 24 210 18 0 1 ...
## $ pared9_Otro : num 0 0 0 0 0 0 0 0 0 0 ...
## $ pared10_Total : num 19520 7308 13999 9716 12757 ...
## $ techo1_Concreto : num 2187 692 2262 56 187 ...
## $ techo2_Madera : num 294 75 160 188 43 48 340 57 12 8 ...
## $ techo3_Tejas : num 179 382 3393 177 3071 ...
## $ techo4_Planchas : num 13186 6084 8005 2036 9343 ...
## $ techo5_Caña : num 160 38 50 15 26 15 196 10 8 5 ...
## $ techo6_Triplay : num 106 5 14 10 12 5 62 17 4 3 ...
## $ techo7_Paja : num 3408 32 115 7234 75 ...
## $ techo8_Otro : num 0 0 0 0 0 0 0 0 0 0 ...
## $ techo9_Total : num 19520 7308 13999 9716 12757 ...
## $ piso1_Parquet : num 6 5 23 2 4 3 20 0 0 5 ...
## $ piso2_Láminas : num 19 2 36 0 0 4 32 0 0 1 ...
## $ piso3_Losetas : num 647 165 1077 20 46 ...
## $ piso4_Madera : num 157 132 240 1523 295 ...
## $ piso5_Cemento : num 7121 2917 6189 943 1911 ...
## $ piso6_Tierra : num 11569 4087 6434 7228 10501 ...
## $ piso7_Otro : num 1 0 0 0 0 0 0 0 0 0 ...
## $ piso8_Total : num 19520 7308 13999 9716 12757 ...
## $ agua1_Red : num 9429 4569 10647 1307 7172 ...
## $ agua2_Red_fueraVivienda: num 4392 1497 1619 867 3097 ...
## $ agua3_Pilón : num 793 215 184 1003 1112 ...
## $ agua4_Camión : num 59 0 49 2 0 0 117 0 0 0 ...
## $ agua5_Pozo : num 1792 474 876 2564 819 ...
## $ agua6_Manantial : num 270 67 92 431 132 211 471 121 61 27 ...
## $ agua7_Río : num 2648 388 488 3428 369 ...
## $ agua8_Otro : num 56 61 24 80 9 29 104 2 1 6 ...
## $ agua9_Vecino : num 81 37 20 34 47 8 177 9 4 6 ...
## $ agua10_Total : num 19520 7308 13999 9716 12757 ...
## $ elec1_Sí : num 13204 6025 12248 1792 10886 ...
## $ elec2_No : num 6316 1283 1751 7924 1871 ...
## $ elec3_Total : num 19520 7308 13999 9716 12757 ...
## $ departamento : chr "AMAZONAS" "AMAZONAS" "AMAZONAS" "AMAZONAS" ...
## $ provincia : chr "BAGUA" "BONGARA" "CHACHAPOYAS" "CONDORCANQUI" ...
## $ Castillo : num 25629 8374 15671 13154 12606 ...
## $ Keiko : num 10770 5209 10473 1446 7840 ...
## $ ganaCastillo : num 1 1 1 1 1 1 1 1 1 1 ...
## $ countPositivos : num 8126 389 2174 3481 456 ...
## $ countFallecidos : num 462 72 281 111 88 60 336 26 31 21 ...
datita <- datita[complete.cases(datita), ]
names(datita)
## [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", "agua10_Total", "elec1_Sí", "elec2_No", "elec3_Total", "departamento", "provincia", "Castillo", "Keiko", "ganaCastillo", "countPositivos", "countFallecidos", "pared10_Total", "techo9_Total", "piso8_Total")
select=setdiff(names(datita),dontselect)
latentes=datita[,select]
# usaremos:
library(magrittr)
head(latentes,10)%>%
rmarkdown::paged_table()
latentes <- latentes[complete.cases(latentes), ]
library(polycor)
corMatrix=polycor::hetcor(latentes)$correlations
any(is.na(corMatrix))
## [1] FALSE
any(is.na(latentes))
## [1] FALSE
corMatrix <- cor(latentes, use = "complete.obs")
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
## pared9_Otro 0.24 0.26 0.33 -0.07
## 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
## techo8_Otro 0.24 0.26 0.32 -0.07
## 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
## piso7_Otro 0.87 0.53 0.34 -0.05
## 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
## agua8_Otro 0.57 0.34 0.35 -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
## pared9_Otro 0.02 0.02 0.15
## 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
## techo8_Otro 0.02 0.01 0.17
## 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
## piso7_Otro 0.17 0.03 0.78
## 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
## agua8_Otro 0.63 0.09 0.57
## agua9_Vecino 0.45 0.06 0.86
## pared8_Triplay pared9_Otro techo1_Concreto
## pared1_Ladrillo 0.85 0.24 1.00
## pared2_Piedra 0.50 0.26 0.65
## pared3_Adobe 0.27 0.33 0.35
## pared4_Tapia -0.09 -0.07 -0.02
## pared5_Quincha 0.45 0.02 0.20
## pared6_Piedra 0.04 0.02 0.07
## pared7_Madera 0.74 0.15 0.88
## pared8_Triplay 1.00 0.16 0.84
## pared9_Otro 0.16 1.00 0.25
## techo1_Concreto 0.84 0.25 1.00
## techo2_Madera 0.79 0.20 0.96
## techo3_Tejas 0.04 -0.04 0.13
## techo4_Planchas 0.85 0.24 0.91
## techo5_Caña 0.51 0.35 0.44
## techo6_Triplay 0.93 0.23 0.83
## techo7_Paja 0.01 -0.03 0.04
## techo8_Otro 0.17 0.99 0.25
## piso1_Parquet 0.81 0.21 0.99
## piso2_Láminas 0.81 0.22 0.99
## piso3_Losetas 0.85 0.24 1.00
## piso4_Madera 0.47 0.06 0.56
## piso5_Cemento 0.85 0.26 0.99
## piso6_Tierra 0.72 0.23 0.68
## piso7_Otro 0.72 0.23 0.87
## agua1_Red 0.85 0.25 1.00
## agua2_Red_fueraVivienda 0.82 0.21 0.99
## agua3_Pilón 0.79 0.28 0.91
## agua4_Camión 0.89 0.23 0.99
## agua5_Pozo 0.29 0.12 0.37
## agua6_Manantial -0.08 -0.02 -0.05
## agua7_Río 0.22 -0.05 -0.02
## agua8_Otro 0.69 0.19 0.54
## agua9_Vecino 0.88 0.24 0.93
## techo2_Madera techo3_Tejas techo4_Planchas techo5_Caña
## pared1_Ladrillo 0.96 0.13 0.92 0.44
## pared2_Piedra 0.55 0.04 0.62 0.24
## pared3_Adobe 0.26 0.45 0.46 0.38
## pared4_Tapia -0.04 0.41 -0.02 -0.13
## pared5_Quincha 0.18 -0.05 0.43 0.16
## pared6_Piedra 0.05 0.00 0.12 -0.05
## pared7_Madera 0.94 0.03 0.87 0.31
## pared8_Triplay 0.79 0.04 0.85 0.51
## pared9_Otro 0.20 -0.04 0.24 0.35
## techo1_Concreto 0.96 0.13 0.91 0.44
## techo2_Madera 1.00 0.10 0.88 0.39
## techo3_Tejas 0.10 1.00 0.09 -0.05
## techo4_Planchas 0.88 0.09 1.00 0.37
## techo5_Caña 0.39 -0.05 0.37 1.00
## techo6_Triplay 0.80 0.03 0.76 0.66
## techo7_Paja 0.08 -0.13 0.13 -0.11
## techo8_Otro 0.20 -0.05 0.25 0.35
## piso1_Parquet 0.96 0.13 0.89 0.38
## piso2_Láminas 0.96 0.12 0.89 0.38
## piso3_Losetas 0.97 0.14 0.92 0.44
## piso4_Madera 0.61 0.16 0.63 0.14
## piso5_Cemento 0.96 0.13 0.93 0.47
## piso6_Tierra 0.61 0.32 0.84 0.36
## piso7_Otro 0.83 0.06 0.79 0.54
## agua1_Red 0.96 0.16 0.93 0.46
## agua2_Red_fueraVivienda 0.96 0.19 0.92 0.40
## agua3_Pilón 0.86 0.11 0.90 0.38
## agua4_Camión 0.95 0.10 0.91 0.46
## agua5_Pozo 0.36 0.04 0.51 0.15
## agua6_Manantial -0.05 0.19 0.06 -0.13
## agua7_Río 0.00 -0.10 0.27 -0.03
## agua8_Otro 0.52 0.02 0.76 0.36
## agua9_Vecino 0.90 0.13 0.96 0.45
## techo6_Triplay techo7_Paja techo8_Otro piso1_Parquet
## pared1_Ladrillo 0.84 0.04 0.24 0.99
## pared2_Piedra 0.49 0.02 0.26 0.59
## pared3_Adobe 0.29 0.08 0.32 0.31
## pared4_Tapia -0.10 -0.12 -0.07 -0.02
## pared5_Quincha 0.25 -0.06 0.02 0.17
## pared6_Piedra 0.03 0.26 0.01 0.07
## pared7_Madera 0.73 0.24 0.17 0.89
## pared8_Triplay 0.93 0.01 0.17 0.81
## pared9_Otro 0.23 -0.03 0.99 0.21
## techo1_Concreto 0.83 0.04 0.25 0.99
## techo2_Madera 0.80 0.08 0.20 0.96
## techo3_Tejas 0.03 -0.13 -0.05 0.13
## techo4_Planchas 0.76 0.13 0.25 0.89
## techo5_Caña 0.66 -0.11 0.35 0.38
## techo6_Triplay 1.00 -0.02 0.23 0.80
## techo7_Paja -0.02 1.00 -0.02 0.05
## techo8_Otro 0.23 -0.02 1.00 0.21
## piso1_Parquet 0.80 0.05 0.21 1.00
## piso2_Láminas 0.80 0.05 0.22 0.99
## piso3_Losetas 0.84 0.04 0.24 0.99
## piso4_Madera 0.43 0.34 0.10 0.57
## piso5_Cemento 0.85 0.04 0.27 0.98
## piso6_Tierra 0.62 0.20 0.24 0.63
## piso7_Otro 0.74 0.02 0.24 0.85
## agua1_Red 0.84 0.04 0.26 0.98
## agua2_Red_fueraVivienda 0.81 0.06 0.22 0.99
## agua3_Pilón 0.76 0.08 0.29 0.87
## agua4_Camión 0.88 0.03 0.23 0.98
## agua5_Pozo 0.26 0.51 0.15 0.35
## agua6_Manantial -0.10 0.33 -0.03 -0.04
## agua7_Río 0.04 0.43 -0.05 -0.03
## agua8_Otro 0.53 0.15 0.19 0.50
## agua9_Vecino 0.81 0.06 0.25 0.91
## piso2_Láminas piso3_Losetas piso4_Madera piso5_Cemento
## pared1_Ladrillo 0.99 1.00 0.57 1.00
## pared2_Piedra 0.69 0.62 0.32 0.67
## pared3_Adobe 0.30 0.36 0.12 0.38
## pared4_Tapia -0.03 -0.03 -0.02 -0.03
## pared5_Quincha 0.18 0.22 0.04 0.24
## pared6_Piedra 0.07 0.06 0.02 0.07
## pared7_Madera 0.88 0.89 0.76 0.89
## pared8_Triplay 0.81 0.85 0.47 0.85
## pared9_Otro 0.22 0.24 0.06 0.26
## techo1_Concreto 0.99 1.00 0.56 0.99
## techo2_Madera 0.96 0.97 0.61 0.96
## techo3_Tejas 0.12 0.14 0.16 0.13
## techo4_Planchas 0.89 0.92 0.63 0.93
## techo5_Caña 0.38 0.44 0.14 0.47
## techo6_Triplay 0.80 0.84 0.43 0.85
## techo7_Paja 0.05 0.04 0.34 0.04
## techo8_Otro 0.22 0.24 0.10 0.27
## piso1_Parquet 0.99 0.99 0.57 0.98
## piso2_Láminas 1.00 0.99 0.56 0.98
## piso3_Losetas 0.99 1.00 0.57 0.99
## piso4_Madera 0.56 0.57 1.00 0.58
## piso5_Cemento 0.98 0.99 0.58 1.00
## piso6_Tierra 0.64 0.68 0.38 0.71
## piso7_Otro 0.85 0.87 0.47 0.87
## agua1_Red 0.99 1.00 0.58 1.00
## agua2_Red_fueraVivienda 0.98 0.99 0.59 0.98
## agua3_Pilón 0.92 0.90 0.51 0.92
## agua4_Camión 0.98 0.99 0.56 0.98
## agua5_Pozo 0.35 0.35 0.43 0.40
## agua6_Manantial -0.05 -0.06 -0.01 -0.05
## agua7_Río -0.03 0.01 0.35 0.02
## agua8_Otro 0.51 0.57 0.59 0.59
## agua9_Vecino 0.91 0.94 0.59 0.94
## piso6_Tierra piso7_Otro agua1_Red
## pared1_Ladrillo 0.69 0.87 1.00
## pared2_Piedra 0.45 0.53 0.64
## pared3_Adobe 0.72 0.34 0.39
## pared4_Tapia 0.14 -0.05 -0.02
## pared5_Quincha 0.50 0.17 0.24
## pared6_Piedra 0.23 0.03 0.07
## pared7_Madera 0.58 0.78 0.89
## pared8_Triplay 0.72 0.72 0.85
## pared9_Otro 0.23 0.23 0.25
## techo1_Concreto 0.68 0.87 1.00
## techo2_Madera 0.61 0.83 0.96
## techo3_Tejas 0.32 0.06 0.16
## techo4_Planchas 0.84 0.79 0.93
## techo5_Caña 0.36 0.54 0.46
## techo6_Triplay 0.62 0.74 0.84
## techo7_Paja 0.20 0.02 0.04
## techo8_Otro 0.24 0.24 0.26
## piso1_Parquet 0.63 0.85 0.98
## piso2_Láminas 0.64 0.85 0.99
## piso3_Losetas 0.68 0.87 1.00
## piso4_Madera 0.38 0.47 0.58
## piso5_Cemento 0.71 0.87 1.00
## piso6_Tierra 1.00 0.59 0.72
## piso7_Otro 0.59 1.00 0.87
## agua1_Red 0.72 0.87 1.00
## agua2_Red_fueraVivienda 0.72 0.85 0.99
## agua3_Pilón 0.73 0.77 0.91
## agua4_Camión 0.69 0.86 0.99
## agua5_Pozo 0.59 0.32 0.38
## agua6_Manantial 0.30 -0.10 -0.05
## agua7_Río 0.37 -0.02 0.02
## agua8_Otro 0.70 0.47 0.59
## agua9_Vecino 0.79 0.81 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
## pared9_Otro 0.21 0.28 0.23
## 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
## techo8_Otro 0.22 0.29 0.23
## 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
## piso7_Otro 0.85 0.77 0.86
## 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
## agua8_Otro 0.55 0.58 0.59
## agua9_Vecino 0.93 0.86 0.94
## agua5_Pozo agua6_Manantial agua7_Río agua8_Otro
## pared1_Ladrillo 0.37 -0.05 0.01 0.57
## pared2_Piedra 0.25 -0.03 0.00 0.34
## pared3_Adobe 0.45 0.27 0.06 0.35
## pared4_Tapia 0.02 0.24 -0.06 -0.06
## pared5_Quincha 0.07 -0.04 0.47 0.63
## pared6_Piedra 0.24 0.39 0.10 0.09
## pared7_Madera 0.45 0.00 0.19 0.57
## pared8_Triplay 0.29 -0.08 0.22 0.69
## pared9_Otro 0.12 -0.02 -0.05 0.19
## techo1_Concreto 0.37 -0.05 -0.02 0.54
## techo2_Madera 0.36 -0.05 0.00 0.52
## techo3_Tejas 0.04 0.19 -0.10 0.02
## techo4_Planchas 0.51 0.06 0.27 0.76
## techo5_Caña 0.15 -0.13 -0.03 0.36
## techo6_Triplay 0.26 -0.10 0.04 0.53
## techo7_Paja 0.51 0.33 0.43 0.15
## techo8_Otro 0.15 -0.03 -0.05 0.19
## piso1_Parquet 0.35 -0.04 -0.03 0.50
## piso2_Láminas 0.35 -0.05 -0.03 0.51
## piso3_Losetas 0.35 -0.06 0.01 0.57
## piso4_Madera 0.43 -0.01 0.35 0.59
## piso5_Cemento 0.40 -0.05 0.02 0.59
## piso6_Tierra 0.59 0.30 0.37 0.70
## piso7_Otro 0.32 -0.10 -0.02 0.47
## agua1_Red 0.38 -0.05 0.02 0.59
## agua2_Red_fueraVivienda 0.39 0.03 0.01 0.55
## agua3_Pilón 0.40 0.01 0.10 0.58
## agua4_Camión 0.34 -0.07 0.03 0.59
## agua5_Pozo 1.00 0.29 0.27 0.36
## agua6_Manantial 0.29 1.00 0.31 -0.04
## agua7_Río 0.27 0.31 1.00 0.56
## agua8_Otro 0.36 -0.04 0.56 1.00
## agua9_Vecino 0.42 -0.06 0.16 0.75
## agua9_Vecino
## pared1_Ladrillo 0.94
## pared2_Piedra 0.55
## pared3_Adobe 0.41
## pared4_Tapia -0.03
## pared5_Quincha 0.45
## pared6_Piedra 0.06
## pared7_Madera 0.86
## pared8_Triplay 0.88
## pared9_Otro 0.24
## techo1_Concreto 0.93
## techo2_Madera 0.90
## techo3_Tejas 0.13
## techo4_Planchas 0.96
## techo5_Caña 0.45
## techo6_Triplay 0.81
## techo7_Paja 0.06
## techo8_Otro 0.25
## piso1_Parquet 0.91
## piso2_Láminas 0.91
## piso3_Losetas 0.94
## piso4_Madera 0.59
## piso5_Cemento 0.94
## piso6_Tierra 0.79
## piso7_Otro 0.81
## agua1_Red 0.95
## agua2_Red_fueraVivienda 0.93
## agua3_Pilón 0.86
## agua4_Camión 0.94
## agua5_Pozo 0.42
## agua6_Manantial -0.06
## agua7_Río 0.16
## agua8_Otro 0.75
## agua9_Vecino 1.00
library(ggcorrplot)
## Loading required package: ggplot2
ggcorrplot(corMatrix)
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)
## Error in solve.default(r) :
## sistema es computacionalmente singular: número de condición recíproco = 1.75716e-18
## matrix is not invertible, image not found
## Kaiser-Meyer-Olkin factor adequacy
## Call: psych::KMO(r = corMatrix)
## Overall MSA = 0.5
## MSA for each item =
## pared1_Ladrillo pared2_Piedra pared3_Adobe
## 0.5 0.5 0.5
## pared4_Tapia pared5_Quincha pared6_Piedra
## 0.5 0.5 0.5
## pared7_Madera pared8_Triplay pared9_Otro
## 0.5 0.5 0.5
## techo1_Concreto techo2_Madera techo3_Tejas
## 0.5 0.5 0.5
## techo4_Planchas techo5_Caña techo6_Triplay
## 0.5 0.5 0.5
## techo7_Paja techo8_Otro piso1_Parquet
## 0.5 0.5 0.5
## piso2_Láminas piso3_Losetas piso4_Madera
## 0.5 0.5 0.5
## piso5_Cemento piso6_Tierra piso7_Otro
## 0.5 0.5 0.5
## agua1_Red agua2_Red_fueraVivienda agua3_Pilón
## 0.5 0.5 0.5
## agua4_Camión agua5_Pozo agua6_Manantial
## 0.5 0.5 0.5
## agua7_Río agua8_Otro agua9_Vecino
## 0.5 0.5 0.5
cortest.bartlett(corMatrix,n=nrow(latentes))$p.value>0.05
## Warning in log(detR): Se han producido NaNs
## [1] NA
library(matrixcalc)
is.singular.matrix(corMatrix)
## [1] TRUE
library(GPArotation)
##
## Attaching package: 'GPArotation'
## The following objects are masked from 'package:psych':
##
## equamax, varimin
resfa <- fa(latentes,
nfactors = 4,
cor = 'mixed',
rotate = "varimax", #oblimin?
fm="minres")
## In smc, smcs > 1 were set to 1.0
## In smc, smcs > 1 were set to 1.0
## In smc, smcs > 1 were set to 1.0
## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done
## 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
## In factor.scores, the correlation matrix is singular, the pseudo inverse is used
print(resfa$loadings)
##
## Loadings:
## MR1 MR3 MR2 MR4
## pared1_Ladrillo 0.977 0.191
## pared2_Piedra 0.593 0.276
## pared3_Adobe 0.201 0.637 0.484
## pared4_Tapia -0.163 0.290
## pared5_Quincha 0.178 0.632 -0.115
## pared6_Piedra 0.387
## pared7_Madera 0.902 0.198 0.109
## pared8_Triplay 0.823 0.156 0.374
## pared9_Otro 0.264 0.938
## techo1_Concreto 0.977 0.195
## techo2_Madera 0.966
## techo3_Tejas 0.120 -0.169 0.371
## techo4_Planchas 0.865 0.225 0.365 0.197
## techo5_Caña 0.355 0.572 0.107 -0.204
## techo6_Triplay 0.807 0.268 0.167 -0.122
## techo7_Paja -0.115 0.284 0.424
## techo8_Otro 0.272 0.889
## piso1_Parquet 0.983 0.109
## piso2_Láminas 0.982 0.136
## piso3_Losetas 0.976 0.188
## piso4_Madera 0.584 0.276 0.197
## piso5_Cemento 0.967 0.235
## piso6_Tierra 0.574 0.377 0.423 0.497
## piso7_Otro 0.837 0.236
## agua1_Red 0.969 0.219
## agua2_Red_fueraVivienda 0.967 0.150 0.165
## agua3_Pilón 0.859 0.294 0.138 0.122
## agua4_Camión 0.970 0.179 0.109
## agua5_Pozo 0.305 0.164 0.250 0.529
## agua6_Manantial -0.102 0.664
## agua7_Río -0.119 0.817 0.253
## agua8_Otro 0.493 0.223 0.735
## agua9_Vecino 0.892 0.229 0.315
##
## MR1 MR3 MR2 MR4
## SS loadings 16.326 3.398 2.581 2.072
## Proportion Var 0.495 0.103 0.078 0.063
## Cumulative Var 0.495 0.598 0.676 0.739
library(GPArotation)
resfa <- fa(latentes,
nfactors = 4,
cor = 'mixed',
rotate = "oblimin", #oblimin?
fm="minres")
## In smc, smcs > 1 were set to 1.0
## In smc, smcs > 1 were set to 1.0
## In smc, smcs > 1 were set to 1.0
## Warning in cor.smooth(r): Matrix was not positive definite, smoothing was done
## 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
## In factor.scores, the correlation matrix is singular, the pseudo inverse is used
print(resfa$loadings)
##
## Loadings:
## MR1 MR3 MR2 MR4
## pared1_Ladrillo 0.997
## pared2_Piedra 0.561 0.192
## pared3_Adobe 0.613 0.502
## pared4_Tapia -0.130 -0.212 0.301
## pared5_Quincha 0.672 -0.162
## pared6_Piedra 0.391
## pared7_Madera 0.950 -0.197 0.112
## pared8_Triplay 0.758 0.335 -0.169
## pared9_Otro 0.981
## techo1_Concreto 1.005
## techo2_Madera 1.024
## techo3_Tejas 0.183 -0.243 0.379
## techo4_Planchas 0.794 0.281 0.129
## techo5_Caña 0.175 0.581 0.113 -0.214
## techo6_Triplay 0.754 0.160 0.122 -0.180
## techo7_Paja -0.172 0.239 0.409
## techo8_Otro 0.926
## piso1_Parquet 1.047 -0.110
## piso2_Láminas 1.036 -0.104
## piso3_Losetas 0.998
## piso4_Madera 0.607 -0.223 0.211 0.139
## piso5_Cemento 0.967
## piso6_Tierra 0.423 0.260 0.328 0.459
## piso7_Otro 0.831 0.110
## agua1_Red 0.977
## agua2_Red_fueraVivienda 1.006 0.103
## agua3_Pilón 0.818 0.157
## agua4_Camión 0.979
## agua5_Pozo 0.239 0.164 0.511
## agua6_Manantial -0.107 0.679
## agua7_Río -0.190 -0.153 0.835 0.210
## agua8_Otro 0.291 0.149 0.731
## agua9_Vecino 0.829 0.246
##
## MR1 MR3 MR2 MR4
## SS loadings 15.921 2.934 2.362 1.979
## Proportion Var 0.482 0.089 0.072 0.060
## Cumulative Var 0.482 0.571 0.643 0.703
EJERCICIO 2
datita$elec_porcentaje <- (datita$elec1_Sí / datita$elec3_Total) * 100
str(datita$elec_porcentaje)
## num [1:196] 67.6 82.4 87.5 18.4 85.3 ...
datita$tasa_covid <- (datita$countFallecidos / datita$countPositivos) * 1000
datita$razon_presi <- datita$Castillo / datita$Keiko
DATITA SIN LIMA
chaolima <- subset(datita, provincia != "LIMA")
dataClus=chaolima[,c(51:53)]
row.names(dataClus)=chaolima$provincia
library(cluster)
g.dist = daisy(dataClus, metric="gower")
library(factoextra)
## Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa
fviz_nbclust(dataClus, hcut,diss=g.dist,method = "gap_stat",k.max = 10,verbose = F,hc_func = "agnes")
set.seed(123)
library(factoextra)
library(kableExtra)
res.agnes6<- hcut(g.dist, k = 6,hc_func='agnes',hc_method = "ward.D")
dataClus$agnes=res.agnes6$cluster
# ver
head(dataClus,15)%>%kbl()%>%kable_styling()
|
|
elec_porcentaje
|
tasa_covid
|
razon_presi
|
agnes
|
|
BAGUA
|
67.64344
|
56.85454
|
2.3796657
|
1
|
|
BONGARA
|
82.44390
|
185.08997
|
1.6076022
|
2
|
|
CHACHAPOYAS
|
87.49196
|
129.25483
|
1.4963239
|
2
|
|
CONDORCANQUI
|
18.44380
|
31.88739
|
9.0968188
|
3
|
|
LUYA
|
85.33354
|
192.98246
|
1.6079082
|
2
|
|
RODRÍGUEZ DE MENDOZA
|
77.43711
|
545.45455
|
1.4509197
|
2
|
|
UTCUBAMBA
|
80.77012
|
89.62390
|
1.9009468
|
2
|
|
AIJA
|
78.72231
|
329.11392
|
1.6454352
|
2
|
|
ANTONIO RAYMONDI
|
81.59007
|
574.07407
|
6.4162437
|
4
|
|
ASUNCIÓN
|
88.27107
|
355.93220
|
3.4582830
|
2
|
|
BOLOGNESI
|
78.83544
|
396.69421
|
1.9253881
|
2
|
|
CARHUAZ
|
79.58164
|
295.28986
|
2.1863795
|
2
|
|
CARLOS FERMÍN FITZCARRALD
|
65.49730
|
607.14286
|
3.8078963
|
4
|
|
CASMA
|
79.91896
|
375.90862
|
0.7286762
|
2
|
|
CORONGO
|
89.67901
|
513.51351
|
1.4890411
|
2
|
fviz_silhouette(res.agnes6,print.summary = F)
set.seed(123)
library(factoextra)
library(kableExtra)
res.agnes5<- hcut(g.dist, k = 5,hc_func='agnes',hc_method = "ward.D")
dataClus$agnes=res.agnes5$cluster
# ver
head(dataClus,15)%>%kbl()%>%kable_styling()
|
|
elec_porcentaje
|
tasa_covid
|
razon_presi
|
agnes
|
|
BAGUA
|
67.64344
|
56.85454
|
2.3796657
|
1
|
|
BONGARA
|
82.44390
|
185.08997
|
1.6076022
|
2
|
|
CHACHAPOYAS
|
87.49196
|
129.25483
|
1.4963239
|
2
|
|
CONDORCANQUI
|
18.44380
|
31.88739
|
9.0968188
|
1
|
|
LUYA
|
85.33354
|
192.98246
|
1.6079082
|
2
|
|
RODRÍGUEZ DE MENDOZA
|
77.43711
|
545.45455
|
1.4509197
|
2
|
|
UTCUBAMBA
|
80.77012
|
89.62390
|
1.9009468
|
2
|
|
AIJA
|
78.72231
|
329.11392
|
1.6454352
|
2
|
|
ANTONIO RAYMONDI
|
81.59007
|
574.07407
|
6.4162437
|
3
|
|
ASUNCIÓN
|
88.27107
|
355.93220
|
3.4582830
|
2
|
|
BOLOGNESI
|
78.83544
|
396.69421
|
1.9253881
|
2
|
|
CARHUAZ
|
79.58164
|
295.28986
|
2.1863795
|
2
|
|
CARLOS FERMÍN FITZCARRALD
|
65.49730
|
607.14286
|
3.8078963
|
3
|
|
CASMA
|
79.91896
|
375.90862
|
0.7286762
|
2
|
|
CORONGO
|
89.67901
|
513.51351
|
1.4890411
|
2
|
fviz_silhouette(res.agnes5,print.summary = F)
set.seed(123)
library(factoextra)
library(kableExtra)
res.agnes7<- hcut(g.dist, k = 7,hc_func='agnes',hc_method = "ward.D")
dataClus$agnes=res.agnes7$cluster
# ver
head(dataClus,15)%>%kbl()%>%kable_styling()
|
|
elec_porcentaje
|
tasa_covid
|
razon_presi
|
agnes
|
|
BAGUA
|
67.64344
|
56.85454
|
2.3796657
|
1
|
|
BONGARA
|
82.44390
|
185.08997
|
1.6076022
|
2
|
|
CHACHAPOYAS
|
87.49196
|
129.25483
|
1.4963239
|
2
|
|
CONDORCANQUI
|
18.44380
|
31.88739
|
9.0968188
|
3
|
|
LUYA
|
85.33354
|
192.98246
|
1.6079082
|
2
|
|
RODRÍGUEZ DE MENDOZA
|
77.43711
|
545.45455
|
1.4509197
|
2
|
|
UTCUBAMBA
|
80.77012
|
89.62390
|
1.9009468
|
2
|
|
AIJA
|
78.72231
|
329.11392
|
1.6454352
|
2
|
|
ANTONIO RAYMONDI
|
81.59007
|
574.07407
|
6.4162437
|
4
|
|
ASUNCIÓN
|
88.27107
|
355.93220
|
3.4582830
|
2
|
|
BOLOGNESI
|
78.83544
|
396.69421
|
1.9253881
|
2
|
|
CARHUAZ
|
79.58164
|
295.28986
|
2.1863795
|
2
|
|
CARLOS FERMÍN FITZCARRALD
|
65.49730
|
607.14286
|
3.8078963
|
4
|
|
CASMA
|
79.91896
|
375.90862
|
0.7286762
|
2
|
|
CORONGO
|
89.67901
|
513.51351
|
1.4890411
|
2
|
fviz_silhouette(res.agnes7,print.summary = F)
# k es la cantidad de dimensiones
proyeccion = cmdscale(g.dist, k=7,add = T)
head(proyeccion$points,20)
## [,1] [,2] [,3] [,4]
## BAGUA 0.04448855 -0.20652501 -0.035389292 -4.036798e-02
## BONGARA -0.11722784 -0.04094571 0.040813995 -2.995733e-02
## CHACHAPOYAS -0.17643509 -0.04877868 0.077363900 -4.896040e-03
## CONDORCANQUI 0.38188965 -0.35157469 0.085823875 -4.121818e-02
## LUYA -0.14728804 -0.02528587 0.055311455 -8.100901e-03
## RODRÍGUEZ DE MENDOZA -0.02896989 0.10352565 -0.177936906 -8.692899e-03
## UTCUBAMBA -0.09576217 -0.08367622 0.044949540 -7.034791e-02
## AIJA -0.05369621 0.02382508 -0.050771694 9.046708e-03
## ANTONIO RAYMONDI 0.09159046 0.22023335 -0.041034861 -1.265541e-01
## ASUNCIÓN -0.08716196 0.11179574 0.031399827 -1.330032e-02
## BOLOGNESI -0.04003726 0.06334762 -0.082365208 -9.350437e-03
## CARHUAZ -0.05121346 0.01455622 -0.016578624 -2.007227e-02
## CARLOS FERMÍN FITZCARRALD 0.15814410 0.03457577 -0.239379356 -5.494417e-02
## CASMA -0.08406760 0.05406885 -0.079814680 4.003301e-02
## CORONGO -0.15390341 0.15838208 -0.094541626 5.233849e-02
## HUARAZ -0.17926940 -0.02485220 0.083261148 7.925800e-03
## HUARI 0.02275277 0.16995571 -0.099543159 -1.137150e-01
## HUARMEY -0.15715526 -0.05504148 0.050791649 7.641503e-06
## HUAYLAS -0.14885432 -0.02963135 0.037337765 1.351051e-02
## MARISCAL LUZURIAGA 0.14703244 -0.04373031 -0.009527567 -5.979777e-02
## [,5] [,6] [,7]
## BAGUA -0.069067662 0.066222267 0.0610878838
## BONGARA -0.038962067 0.059816289 -0.0362169293
## CHACHAPOYAS 0.031576062 0.080544589 0.0157451569
## CONDORCANQUI 0.295951954 0.012385997 -0.2178514028
## LUYA -0.003982055 0.045767620 -0.0044569280
## RODRÍGUEZ DE MENDOZA -0.065075161 0.034499945 -0.0809369216
## UTCUBAMBA -0.047393972 0.105226027 -0.0625143837
## AIJA -0.099791032 -0.030404772 -0.0876560442
## ANTONIO RAYMONDI 0.079098632 -0.010343827 -0.0498369237
## ASUNCIÓN 0.040887009 -0.085274018 0.0176317994
## BOLOGNESI -0.087531392 -0.020164744 -0.1021441038
## CARHUAZ -0.088350567 -0.038773586 -0.0656456086
## CARLOS FERMÍN FITZCARRALD 0.017255252 -0.026668851 0.0857459362
## CASMA -0.076173791 -0.017997098 -0.1128235780
## CORONGO 0.067796505 -0.003233012 0.0006306538
## HUARAZ 0.042530084 0.035251909 0.0503998796
## HUARI 0.013659473 -0.004439805 -0.0386960869
## HUARMEY -0.008734729 0.086360249 -0.0309169101
## HUAYLAS -0.020046849 0.043287332 -0.0284082210
## MARISCAL LUZURIAGA -0.057849156 -0.115279891 0.0816366741
EJERCICIO 3
datita$ganaCastillo <- as.factor(datita$ganaCastillo)
h1=formula(ganaCastillo ~ elec_porcentaje + tasa_covid)
library(modelsummary)
## `modelsummary` 2.0.0 now uses `tinytable` as its default table-drawing
## backend. Learn more at: https://vincentarelbundock.github.io/tinytable/
##
## Revert to `kableExtra` for one session:
##
## options(modelsummary_factory_default = 'kableExtra')
##
## Change the default backend persistently:
##
## config_modelsummary(factory_default = 'gt')
##
## Silence this message forever:
##
## config_modelsummary(startup_message = FALSE)
##
## Attaching package: 'modelsummary'
## The following object is masked from 'package:psych':
##
## SD
rcast=glm(h1, data=datita,family = binomial)
modelrl=list('GanaCastillo'=rcast)
#f <- function(x) format(x, digits = 4, scientific = FALSE)
modelsummary(modelrl,
title = "Regresión Logística",
stars = TRUE,
output = "kableExtra")
Regresión Logística
|
|
GanaCastillo
|
|
(Intercept)
|
6.232***
|
|
|
(1.657)
|
|
elec_porcentaje
|
-0.063**
|
|
|
(0.020)
|
|
tasa_covid
|
0.000
|
|
|
(0.001)
|
|
Num.Obs.
|
196
|
|
AIC
|
199.5
|
|
BIC
|
209.4
|
|
Log.Lik.
|
-96.760
|
|
F
|
5.026
|
|
RMSE
|
0.39
|
|
+ p < 0.1, * p < 0.05, ** p < 0.01, *** p <
0.001
|
modelrl=list('Gana Castillo (I)'=rcast)
# formato creado para modelsummary
formatoNumero = function(x) format(x, digits = 4, scientific = FALSE)
modelsummary(modelrl,
fmt=formatoNumero, # usa función que creé antes
exponentiate = T, # coeficientes sin logaritmo
statistic = 'conf.int', # mostrar ICs
title = "Regresión Logística (Coeficientes Exponenciados)",
stars = TRUE,
output = "kableExtra")
Regresión Logística (Coeficientes Exponenciados)
|
|
Gana Castillo (I)
|
|
(Intercept)
|
508.5939***
|
|
|
[25.3315, 16952.582]
|
|
elec_porcentaje
|
0.9393**
|
|
|
[ 0.9011, 0.974]
|
|
tasa_covid
|
1.0002
|
|
|
[ 0.9986, 1.002]
|
|
Num.Obs.
|
196
|
|
AIC
|
199.5
|
|
BIC
|
209.4
|
|
Log.Lik.
|
-96.760
|
|
F
|
5.026
|
|
RMSE
|
0.39
|
|
+ p < 0.1, * p < 0.05, ** p < 0.01, *** p <
0.001
|
datita$aguared_porcentaje <- (datita$agua1_Red / datita$agua10_Total) * 100
h2=formula(ganaCastillo ~ elec_porcentaje + tasa_covid + aguared_porcentaje)
library(modelsummary)
rlog2=glm(h2, data=datita,family = binomial)
modelrl=list('GanaCastillo'=rlog2)
#f <- function(x) format(x, digits = 4, scientific = FALSE)
modelsummary(modelrl,
title = "Regresión Logística",
stars = TRUE,
output = "kableExtra")
Regresión Logística
|
|
GanaCastillo
|
|
(Intercept)
|
7.226***
|
|
|
(1.888)
|
|
elec_porcentaje
|
-0.088**
|
|
|
(0.029)
|
|
tasa_covid
|
0.000
|
|
|
(0.001)
|
|
aguared_porcentaje
|
0.019
|
|
|
(0.015)
|
|
Num.Obs.
|
196
|
|
AIC
|
200.0
|
|
BIC
|
213.1
|
|
Log.Lik.
|
-95.994
|
|
F
|
3.681
|
|
RMSE
|
0.39
|
|
+ p < 0.1, * p < 0.05, ** p < 0.01, *** p <
0.001
|
modelrl=list('Gana Castillo (II)'=rlog2)
# formato creado para modelsummary
formatoNumero = function(x) format(x, digits = 4, scientific = FALSE)
modelsummary(modelrl,
fmt=formatoNumero, # usa función que creé antes
exponentiate = T, # coeficientes sin logaritmo
statistic = 'conf.int', # mostrar ICs
title = "Regresión Logística (Coeficientes Exponenciados)",
stars = TRUE,
output = "kableExtra")
Regresión Logística (Coeficientes Exponenciados)
|
|
Gana Castillo (II)
|
|
(Intercept)
|
1375.2427***
|
|
|
[44.2982, 74042.8220]
|
|
elec_porcentaje
|
0.9153**
|
|
|
[ 0.8612, 0.9672]
|
|
tasa_covid
|
1.0002
|
|
|
[ 0.9985, 1.0021]
|
|
aguared_porcentaje
|
1.0192
|
|
|
[ 0.9888, 1.0507]
|
|
Num.Obs.
|
196
|
|
AIC
|
200.0
|
|
BIC
|
213.1
|
|
Log.Lik.
|
-95.994
|
|
F
|
3.681
|
|
RMSE
|
0.39
|
|
+ p < 0.1, * p < 0.05, ** p < 0.01, *** p <
0.001
|
library(lmtest)
## Loading required package: zoo
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
lrtest(rcast,rlog2) %>%
kable(caption = "Tabla LRT para comparar modelos")%>%kableExtra::kable_styling(full_width = FALSE)
Tabla LRT para comparar modelos
|
#Df
|
LogLik
|
Df
|
Chisq
|
Pr(>Chisq)
|
|
3
|
-96.75961
|
NA
|
NA
|
NA
|
|
4
|
-95.99378
|
1
|
1.531652
|
0.2158647
|
library(ggplot2)
dotwhisker::dwplot(list(Logit_I=rcast,Logit_II=rlog2),
exp=T) + #exponenciados!
scale_y_discrete(labels=c("VI1",
"VI2",
"VI3")) + #si es categórica evaluar el añadir referencia
scale_color_discrete(name="Modelos para: VD") +
geom_vline(xintercept = 1,
colour = "grey60",
linetype = 2)
```