Uso de factores de expansión, Encuestas INEGI
Claudia Guerrero
26 de mayo de 2018
Introducción
Del muestreo a la estimación, muestreos complejos
Survey Package
Basado en http://javier-marquez.org/2015/10/12/como-analizar-la-envipe-en-r/
Datos actualizados de la:
Encuesta Nacional de Victimización y Percepción sobre Seguridad Pública (ENVIPE) 2017 http://www.beta.inegi.org.mx/proyectos/enchogares/regulares/envipe/2017/
Conglomerado por estados
x <- c("dplyr", "tidyr","survey","arm")
# instalación de paquetes, con lapply se aplica una función sobre una lista de vectores.
lapply(x, library, character.only = TRUE) # carga los paquetes requeridos
#Basado en http://javier-marquez.org/2015/10/12/como-analizar-la-envipe-en-r/
# y en http://www.beta.inegi.org.mx/contenidos/proyectos/enchogares/regulares/envipe/2016/doc/calculo_indicadores_r_envipe2016.pdf
#http://www.andrew.cmu.edu/user/jsmurray/teaching/303/files/lab.html
#https://www.jstatsoft.org/index.php/jss/article/view/v009i08/paper-5.pdf##
## Seguro inseguro no sabe
## 28.1 69.8 2.1## mean SE
## AP4_3_3Seguro 0.239770 0.0020
## AP4_3_3inseguro 0.742934 0.0021
## AP4_3_3no sabe 0.017296 0.0006## total SE
## AP4_3_3Seguro 20113943 180989
## AP4_3_3inseguro 62323530 299494
## AP4_3_3no sabe 1450930 46419## by AP4_3_3Seguro AP4_3_3inseguro AP4_3_3no sabe se.AP4_3_3Seguro
## 1 1 468662 377632 18030 15080.562
## 2 2 971878 1416731 52091 32321.458
## 3 3 206536 341751 12838 7995.478
## 4 4 238715 366973 31768 9362.047
## 5 5 818960 1150527 69726 26479.719
## 6 6 129341 386839 3383 5763.000
## 7 7 1234092 1993983 37172 48687.025
## 8 8 579113 1888983 77767 22461.152
## 9 9 922432 5914760 66638 40478.338
## 10 10 438395 677032 63255 14548.997
## 11 11 898520 2901536 58078 44454.244
## 12 12 323356 1897952 63985 24467.530
## 13 13 849681 1079349 31275 31999.986
## 14 14 1826281 3626770 66522 67352.836
## 15 15 1029729 10832055 77792 75164.649
## 16 16 593905 2397006 96161 34283.614
## 17 17 174312 1174948 11717 11681.638
## 18 18 337520 499746 14948 13409.428
## 19 19 1024923 2576106 24331 53109.405
## 20 20 612160 1983011 80503 34564.919
## 21 21 1193570 2826477 130786 43974.092
## 22 22 603514 756676 29845 18923.639
## 23 23 328610 770230 26363 13581.388
## 24 24 414984 1368603 74299 23861.193
## 25 25 509917 1559350 22527 18855.216
## 26 26 850911 1166369 16060 30735.955
## 27 27 168195 1444878 13403 10474.832
## 28 28 327557 2101865 36617 17084.640
## 29 29 336871 511669 17547 12955.667
## 30 30 486444 5041676 79037 33124.943
## 31 31 1062525 410434 36183 21017.047
## 32 32 152334 881613 10283 11300.863
## se.AP4_3_3inseguro se.AP4_3_3no sabe
## 1 13179.411 2657.0334
## 2 39411.170 7106.1236
## 3 8935.191 2043.6565
## 4 12452.423 3904.8659
## 5 33070.543 8866.0259
## 6 7395.435 805.8451
## 7 52870.112 6261.9146
## 8 38833.846 11419.1708
## 9 65221.693 11085.2370
## 10 17333.892 6556.9893
## 11 66210.649 11704.7287
## 12 43018.385 9048.1210
## 13 31215.701 4703.3443
## 14 89841.451 12577.9489
## 15 182728.900 19662.4272
## 16 51714.654 10358.1075
## 17 24089.199 2543.3672
## 18 14515.282 2824.2885
## 19 67331.529 6604.1017
## 20 54983.222 10379.7201
## 21 58429.616 13061.5870
## 22 22068.737 4610.1127
## 23 18018.464 4408.2191
## 24 50887.292 10259.1887
## 25 24438.482 4287.7377
## 26 38671.136 4962.3177
## 27 27989.715 2635.2377
## 28 34709.848 6590.3835
## 29 13421.876 3069.1911
## 30 79833.324 12192.4978
## 31 14538.624 5465.4888
## 32 19383.228 2502.3419## by AP4_3_3Seguro AP4_3_3inseguro AP4_3_3no sabe se.AP4_3_3Seguro
## 1 1 0.54222953 0.4369102 0.020860233 0.014114091
## 2 2 0.39819642 0.5804609 0.021342648 0.011850035
## 3 3 0.36807485 0.6090461 0.022879038 0.012995585
## 4 4 0.37448075 0.5756837 0.049835596 0.014330079
## 5 5 0.40160591 0.5642015 0.034192603 0.011808263
## 6 6 0.24894190 0.7445469 0.006511241 0.010180645
## 7 7 0.37794752 0.6106684 0.011384131 0.013592689
## 8 8 0.22747218 0.7419814 0.030546420 0.008522904
## 9 9 0.13361163 0.8567360 0.009652323 0.005731257
## 10 10 0.37193662 0.5743975 0.053665874 0.011098738
## 11 11 0.23288979 0.7520568 0.015053391 0.010273057
## 12 12 0.14149433 0.8305071 0.027998598 0.010538895
## 13 13 0.43344327 0.5506026 0.015954150 0.013267767
## 14 14 0.33087360 0.6570744 0.012052019 0.011400743
## 15 15 0.08624502 0.9072395 0.006515474 0.006203686
## 16 16 0.19238456 0.7764659 0.031149581 0.010942726
## 17 17 0.12807858 0.8633122 0.008609256 0.008349484
## 18 18 0.39605076 0.5864090 0.017540195 0.014647524
## 19 19 0.28270930 0.7105794 0.006711333 0.011168971
## 20 20 0.22878721 0.7411258 0.030086999 0.011915376
## 21 21 0.28754951 0.6809421 0.031508374 0.009426548
## 22 22 0.43417180 0.5443575 0.021470682 0.011542513
## 23 23 0.29204508 0.6845254 0.023429550 0.011092790
## 24 24 0.22336354 0.7366453 0.039991151 0.011506573
## 25 25 0.24377018 0.7454606 0.010769225 0.008027263
## 26 26 0.41847945 0.5736222 0.007898335 0.013364007
## 27 27 0.10341069 0.8883488 0.008240515 0.006402311
## 28 28 0.13282718 0.8523243 0.014848508 0.006887952
## 29 29 0.38895746 0.5907825 0.020260089 0.012958281
## 30 30 0.08675413 0.8991501 0.014095735 0.005828602
## 31 31 0.70405900 0.2719651 0.023975875 0.009458497
## 32 32 0.14588165 0.8442709 0.009847447 0.010365204
## se.AP4_3_3inseguro se.AP4_3_3no sabe
## 1 0.013989555 0.003055923
## 2 0.012071798 0.002921146
## 3 0.012882378 0.003573434
## 4 0.014885387 0.005979947
## 5 0.012349930 0.004363129
## 6 0.010384279 0.001553401
## 7 0.013813538 0.001889949
## 8 0.010166585 0.004423578
## 9 0.005908184 0.001601312
## 10 0.010826987 0.005451350
## 11 0.010386970 0.003026758
## 12 0.011088455 0.003968235
## 13 0.013319385 0.002378002
## 14 0.011523052 0.002267248
## 15 0.006317041 0.001650414
## 16 0.011143819 0.003419725
## 17 0.008511507 0.001869457
## 18 0.014934422 0.003314884
## 19 0.011078150 0.001830415
## 20 0.012787916 0.003970793
## 21 0.009757506 0.003188953
## 22 0.011801734 0.003365824
## 23 0.011246529 0.003850868
## 24 0.013252359 0.005848656
## 25 0.007974060 0.002037740
## 26 0.013638738 0.002428209
## 27 0.006683769 0.001621786
## 28 0.007576883 0.002650911
## 29 0.012963024 0.003582494
## 30 0.006137331 0.002186709
## 31 0.009327233 0.003596514
## 32 0.010278405 0.002410842## [,1] [,2] [,3] [,4] [,5]
## [1,] 864324 468662 54.2 377632 43.7
## [2,] 2440700 971878 39.8 1416731 58.0
## [3,] 561125 206536 36.8 341751 60.9
## [4,] 637456 238715 37.4 366973 57.6
## [5,] 2039213 818960 40.2 1150527 56.4
## [6,] 519563 129341 24.9 386839 74.5
## [7,] 3265247 1234092 37.8 1993983 61.1
## [8,] 2545863 579113 22.7 1888983 74.2
## [9,] 6903830 922432 13.4 5914760 85.7
## [10,] 1178682 438395 37.2 677032 57.4
## [11,] 3858134 898520 23.3 2901536 75.2
## [12,] 2285293 323356 14.1 1897952 83.1
## [13,] 1960305 849681 43.3 1079349 55.1
## [14,] 5519573 1826281 33.1 3626770 65.7
## [15,] 11939576 1029729 8.6 10832055 90.7
## [16,] 3087072 593905 19.2 2397006 77.6
## [17,] 1360977 174312 12.8 1174948 86.3
## [18,] 852214 337520 39.6 499746 58.6
## [19,] 3625360 1024923 28.3 2576106 71.1
## [20,] 2675674 612160 22.9 1983011 74.1
## [21,] 4150833 1193570 28.8 2826477 68.1
## [22,] 1390035 603514 43.4 756676 54.4
## [23,] 1125203 328610 29.2 770230 68.5
## [24,] 1857886 414984 22.3 1368603 73.7
## [25,] 2091794 509917 24.4 1559350 74.5
## [26,] 2033340 850911 41.8 1166369 57.4
## [27,] 1626476 168195 10.3 1444878 88.8
## [28,] 2466039 327557 13.3 2101865 85.2
## [29,] 866087 336871 38.9 511669 59.1
## [30,] 5607157 486444 8.7 5041676 89.9
## [31,] 1509142 1062525 70.4 410434 27.2
## [32,] 1044230 152334 14.6 881613 84.4
Uso de los mismos códigos en Coahuila Entidad 5 y sus municipios De los tabulados básicos a la situación de la entidad y de los municipios http://www.beta.inegi.org.mx/contenidos/proyectos/enchogares/regulares/envipe/2017/doc/envipe2017_coah.pdf>
tpv1 = read.csv(file,stringsAsFactors=FALSE,header = TRUE, fileEncoding = "UTF-8")
tpv1<-tpv1[ tpv1$CVE_ENT %in% c(5),] #Elección de Coahuila
tpv1$ENT <- (tpv1$NOM_MUN) #Agregar por municipio
#Percepción sobre seguridad en su estado AP4_3_3
# 1 " , " s e g u r o ? "
# 2 " , " i n s e g u r o ? "
# 9 , " N o s a b e / n o r e s p o n d e "
tpv1$AP4_3_3 = factor(tpv1$AP4_3_3, levels = c(1,2,9), labels = c("Seguro", "inseguro","no sabe") )
round(prop.table(table(tpv1$AP4_3_3))*100,1)##
## Seguro inseguro no sabe
## 38.9 57.7 3.4design = svydesign(id=~UPM_DIS,strata=~EST_DIS, weights=~tpv1$FAC_ELE, data=tpv1)
svymean(~AP4_3_3, design)## mean SE
## AP4_3_3Seguro 0.401606 0.0118
## AP4_3_3inseguro 0.564201 0.0123
## AP4_3_3no sabe 0.034193 0.0044svytotal(~AP4_3_3, design)## total SE
## AP4_3_3Seguro 818960 26480
## AP4_3_3inseguro 1150527 33071
## AP4_3_3no sabe 69726 8866total.edo = svyby(~AP4_3_3, by=tpv1$ENT, design=design, svytotal)
total.edo## by AP4_3_3Seguro AP4_3_3inseguro
## Acuña\n Acuña\n 53447 39892
## Allende\n Allende\n 5220 6960
## Arteaga\n Arteaga\n 18997 12174
## Cuatro Ciénegas\n Cuatro Ciénegas\n 1098 9882
## Francisco I. Madero\n Francisco I. Madero\n 10440 21652
## Frontera\n Frontera\n 9579 31248
## Múzquiz\n Múzquiz\n 5402 11441
## Matamoros\n Matamoros\n 41547 62545
## Monclova\n Monclova\n 34745 109456
## Nava\n Nava\n 4306 957
## Ocampo\n Ocampo\n 7462 10944
## Parras\n Parras\n 8057 17457
## Piedras Negras\n Piedras Negras\n 62021 32898
## Ramos Arizpe\n Ramos Arizpe\n 46485 44969
## Sabinas\n Sabinas\n 8486 12320
## Saltillo\n Saltillo\n 276319 242698
## San Buenaventura\n San Buenaventura\n 6600 16256
## San Juan de Sabinas\n San Juan de Sabinas\n 6933 20435
## San Pedro\n San Pedro\n 46727 86524
## Torreón\n Torreón\n 153681 339935
## Villa Unión\n Villa Unión\n 5985 10588
## Zaragoza\n Zaragoza\n 5423 9296
## AP4_3_3no sabe se.AP4_3_3Seguro se.AP4_3_3inseguro
## Acuña\n 7591 6608.969 6831.601
## Allende\n 0 5220.000 6960.000
## Arteaga\n 3829 13724.403 8968.831
## Cuatro Ciénegas\n 1098 1098.000 9882.000
## Francisco I. Madero\n 290 8078.465 17241.201
## Frontera\n 3139 2662.307 4129.545
## Múzquiz\n 0 5402.000 11441.000
## Matamoros\n 6102 12288.325 18448.263
## Monclova\n 13277 6252.614 8610.931
## Nava\n 0 4306.000 957.000
## Ocampo\n 0 7462.000 10944.000
## Parras\n 0 8057.000 17457.000
## Piedras Negras\n 17382 7131.445 6150.486
## Ramos Arizpe\n 1771 9678.315 11350.918
## Sabinas\n 0 2269.377 1851.641
## Saltillo\n 2885 15789.362 16681.976
## San Buenaventura\n 606 4955.813 11574.958
## San Juan de Sabinas\n 0 4495.684 13193.090
## San Pedro\n 1490 16571.412 26313.042
## Torreón\n 7262 9528.365 25716.605
## Villa Unión\n 1842 5985.000 10588.000
## Zaragoza\n 1162 5423.000 9296.000
## se.AP4_3_3no sabe
## Acuña\n 3053.489
## Allende\n 0.000
## Arteaga\n 3829.000
## Cuatro Ciénegas\n 1098.000
## Francisco I. Madero\n 290.000
## Frontera\n 2236.308
## Múzquiz\n 0.000
## Matamoros\n 3008.317
## Monclova\n 3927.982
## Nava\n 0.000
## Ocampo\n 0.000
## Parras\n 0.000
## Piedras Negras\n 4513.351
## Ramos Arizpe\n 1504.407
## Sabinas\n 0.000
## Saltillo\n 1241.151
## San Buenaventura\n 606.000
## San Juan de Sabinas\n 0.000
## San Pedro\n 1056.152
## Torreón\n 2296.974
## Villa Unión\n 1842.000
## Zaragoza\n 1162.000prop.edo = svyby(~AP4_3_3, by=tpv1$ENT, design=design, svymean)
prop.edo## by AP4_3_3Seguro AP4_3_3inseguro
## Acuña\n Acuña\n 0.52954523 0.3952442
## Allende\n Allende\n 0.42857143 0.5714286
## Arteaga\n Arteaga\n 0.54277143 0.3478286
## Cuatro Ciénegas\n Cuatro Ciénegas\n 0.09090909 0.8181818
## Francisco I. Madero\n Francisco I. Madero\n 0.32240133 0.6686431
## Frontera\n Frontera\n 0.21787290 0.7107310
## Múzquiz\n Múzquiz\n 0.32072671 0.6792733
## Matamoros\n Matamoros\n 0.37703505 0.5675899
## Monclova\n Monclova\n 0.22063399 0.6950558
## Nava\n Nava\n 0.81816454 0.1818355
## Ocampo\n Ocampo\n 0.40541128 0.5945887
## Parras\n Parras\n 0.31578741 0.6842126
## Piedras Negras\n Piedras Negras\n 0.55227469 0.2929449
## Ramos Arizpe\n Ramos Arizpe\n 0.49863234 0.4823706
## Sabinas\n Sabinas\n 0.40786312 0.5921369
## Saltillo\n Saltillo\n 0.52944614 0.4650260
## San Buenaventura\n San Buenaventura\n 0.28130594 0.6928651
## San Juan de Sabinas\n San Juan de Sabinas\n 0.25332505 0.7466749
## San Pedro\n San Pedro\n 0.34679125 0.6421505
## Torreón\n Torreón\n 0.30682322 0.6786782
## Villa Unión\n Villa Unión\n 0.32500679 0.5749661
## Zaragoza\n Zaragoza\n 0.34147724 0.5853536
## AP4_3_3no sabe se.AP4_3_3Seguro se.AP4_3_3inseguro
## Acuña\n 0.075210542 6.713850e-02 6.012724e-02
## Allende\n 0.000000000 2.775558e-17 5.204170e-17
## Arteaga\n 0.109400000 3.380591e-02 1.017744e-01
## Cuatro Ciénegas\n 0.090909091 6.938894e-18 4.857226e-17
## Francisco I. Madero\n 0.008955593 1.455468e-01 1.531079e-01
## Frontera\n 0.071396079 5.752050e-02 7.140866e-02
## Múzquiz\n 0.000000000 1.301043e-17 1.301043e-17
## Matamoros\n 0.055375066 5.325852e-02 3.924123e-02
## Monclova\n 0.084310189 3.440254e-02 3.460014e-02
## Nava\n 0.000000000 5.551115e-17 0.000000e+00
## Ocampo\n 0.000000000 5.551115e-17 2.081668e-17
## Parras\n 0.000000000 1.387779e-17 1.387779e-17
## Piedras Negras\n 0.154780456 5.262565e-02 4.962623e-02
## Ramos Arizpe\n 0.018997050 6.065270e-02 5.987517e-02
## Sabinas\n 0.000000000 7.859068e-02 7.859068e-02
## Saltillo\n 0.005527858 2.387642e-02 2.412252e-02
## San Buenaventura\n 0.025829000 7.252455e-02 5.439458e-02
## San Juan de Sabinas\n 0.000000000 5.159965e-02 5.159965e-02
## San Pedro\n 0.011058252 4.842344e-02 4.780816e-02
## Torreón\n 0.014498541 1.940284e-02 2.010003e-02
## Villa Unión\n 0.100027152 1.387779e-17 2.775558e-17
## Zaragoza\n 0.073169196 3.469447e-17 3.816392e-17
## se.AP4_3_3no sabe
## Acuña\n 2.906132e-02
## Allende\n 0.000000e+00
## Arteaga\n 6.796849e-02
## Cuatro Ciénegas\n 0.000000e+00
## Francisco I. Madero\n 7.561056e-03
## Frontera\n 5.117051e-02
## Múzquiz\n 0.000000e+00
## Matamoros\n 2.104941e-02
## Monclova\n 2.572870e-02
## Nava\n 0.000000e+00
## Ocampo\n 0.000000e+00
## Parras\n 0.000000e+00
## Piedras Negras\n 3.986650e-02
## Ramos Arizpe\n 1.331587e-02
## Sabinas\n 0.000000e+00
## Saltillo\n 2.396463e-03
## San Buenaventura\n 1.812997e-02
## San Juan de Sabinas\n 0.000000e+00
## San Pedro\n 6.413296e-03
## Torreón\n 4.647246e-03
## Villa Unión\n 1.734723e-18
## Zaragoza\n 1.214306e-17pob.edo = aggregate(tpv1$FAC_ELE, by=list(tpv1$ENT), sum)
cbind(Poblacion.18.y.mas <- pob.edo[,2], Seguro.Absolutos <- total.edo[,2],Seguro.Relativos <- round(prop.edo[,2]*100, 1), Inseguro.Absolutos <- total.edo[,3],Inseguro.Relativos <- round(prop.edo[,3]*100, 1))## [,1] [,2] [,3] [,4] [,5]
## [1,] 100930 53447 53.0 39892 39.5
## [2,] 12180 5220 42.9 6960 57.1
## [3,] 35000 18997 54.3 12174 34.8
## [4,] 12078 1098 9.1 9882 81.8
## [5,] 32382 10440 32.2 21652 66.9
## [6,] 43966 9579 21.8 31248 71.1
## [7,] 16843 5402 32.1 11441 67.9
## [8,] 110194 41547 37.7 62545 56.8
## [9,] 157478 34745 22.1 109456 69.5
## [10,] 5263 4306 81.8 957 18.2
## [11,] 18406 7462 40.5 10944 59.5
## [12,] 25514 8057 31.6 17457 68.4
## [13,] 112301 62021 55.2 32898 29.3
## [14,] 93225 46485 49.9 44969 48.2
## [15,] 20806 8486 40.8 12320 59.2
## [16,] 521902 276319 52.9 242698 46.5
## [17,] 23462 6600 28.1 16256 69.3
## [18,] 27368 6933 25.3 20435 74.7
## [19,] 134741 46727 34.7 86524 64.2
## [20,] 500878 153681 30.7 339935 67.9
## [21,] 18415 5985 32.5 10588 57.5
## [22,] 15881 5423 34.1 9296 58.5abbrev = c('Acuña','Allende','Arteaga','Cuatrociénegas','Fco I Madero','Frontera','Múzquiz','Matamoros','Monclova','Nava','Ocampo','Parras','Piedras Negras','Ramoz Arispe','Sabinas','Saltillo','SanBuenaventura','Sabinas','San Pedro','Torreón','Villa Unión','Zaragoza')
coefplot(rev(prop.edo[,3]*100), rev(prop.edo[,5]*100), varnames=rev(abbrev), cex.var= 0.4, cex.pts=1, col.pts="blue",main='% Inseguro')
abline(v=svymean(~AP4_3_3, design)[2]*100, lty='dashed')