#REGRESION
Abrir la data:
library(foreign)
filename="pract25nov.csv"
perudat=read.csv(filename)
names(perudat)## [1] "SP_ID" "IDPROV" "IDDPTO" "NOMBDEP" "NOMBPROV"
## [6] "SUP_INSULA" "SUP_LACUST" "SUP_INS_D" "IDH" "esperanza"
## [11] "secundaria" "educa" "percapitaf" "IDE" "identidad"
## [16] "salud" "educacion" "saneamient" "electrific" "costa"
## [21] "capital" "tamano" "fecundidad" "desnutrici" "densidadpo"
## [26] "mortalidad" "analfa" "analfa1" "analfa2" "analfa3"
## [31] "analfa4" "pob" "pob_ur" "pob_rural" "pob_h"
## [36] "pob_m" "TOTAL" "INTEL" "AUDIT" "CEGUE"
## [41] "BAJAVISI" "SORDCEGUE" "MOTORA" "AUTIS" "ARPERG"
## [46] "OTRO" "EBR"str(perudat)## 'data.frame': 196 obs. of 47 variables:
## $ SP_ID : int 7 6 5 4 1 3 2 27 26 25 ...
## $ IDPROV : int 107 106 105 104 101 103 102 220 219 218 ...
## $ IDDPTO : int 1 1 1 1 1 1 1 2 2 2 ...
## $ NOMBDEP : Factor w/ 25 levels "AMAZONAS","ANCASH",..: 1 1 1 1 1 1 1 2 2 2 ...
## $ NOMBPROV : Factor w/ 196 levels "ABANCAY","ACOBAMBA",..: 187 157 116 59 46 24 19 194 172 167 ...
## $ SUP_INSULA: num 0 0 0 0 0 0 0 0 0 0 ...
## $ SUP_LACUST: int 0 0 0 0 0 0 0 0 0 0 ...
## $ SUP_INS_D : int 0 0 0 0 0 0 0 0 0 0 ...
## $ IDH : num 0.274 0.27 0.251 0.169 0.334 ...
## $ esperanza : num 72.8 74.6 71.2 70.1 72.5 ...
## $ secundaria: num 33.44 26.69 34.6 8.02 45.69 ...
## $ educa : num 5.77 5.77 5.17 5.25 7.4 ...
## $ percapitaf: num 242 249 211 148 307 ...
## $ IDE : num 0.61 0.631 0.605 0.46 0.774 ...
## $ identidad : num 95.2 97.3 96.2 86.2 98.6 ...
## $ salud : num 10.11 14.88 12.42 8.56 25.45 ...
## $ educacion : num 77.2 79.4 74.7 52.2 91.5 ...
## $ saneamient: num 52.5 46.5 43.3 37.7 70.3 ...
## $ electrific: num 63.1 67.5 67.4 39.5 84 ...
## $ costa : Factor w/ 2 levels "NO","SI": 1 1 1 1 1 1 1 1 1 2 ...
## $ capital : Factor w/ 2 levels "NO","SI": 1 1 1 1 2 1 1 1 1 1 ...
## $ tamano : int 3 1 2 2 2 1 2 2 1 4 ...
## $ fecundidad: num 2.74 2.39 3.07 4.81 2.32 2.47 2.81 2.63 3.72 2.09 ...
## $ desnutrici: num 32.5 23.5 30.6 56.8 20.7 ...
## $ densidadpo: num 28.25 11.18 14.93 2.42 15 ...
## $ mortalidad: num 19.4 14.3 24.5 28.5 20.4 21.4 16.9 37.4 25.6 12.9 ...
## $ analfa : num 12.85 7.85 14.27 18.97 7.97 ...
## $ analfa1 : num 7.82 4.27 11.71 7.09 5.2 ...
## $ analfa2 : Factor w/ 186 levels "#N/A","0.15",..: 60 185 53 84 45 35 59 140 123 31 ...
## $ analfa3 : num 7.11 4.96 8.27 8.57 4.28 ...
## $ analfa4 : num 19.3 11.1 20.8 29.6 11.4 ...
## $ pob : int 109043 26389 48328 43311 49700 27465 71757 54963 30700 396434 ...
## $ pob_ur : int 47064 8593 19526 6458 34343 16460 33559 13268 7977 370476 ...
## $ pob_rural : int 61979 17796 28802 36853 15357 11005 38198 41695 22723 25958 ...
## $ pob_h : int 56969 13903 24968 21806 24433 14148 36713 27043 15106 197865 ...
## $ pob_m : int 52074 12486 23360 21505 25267 13317 35044 27920 15594 198569 ...
## $ TOTAL : int 113 82 1 8 25 1 96 187 164 481 ...
## $ INTEL : int 75 78 1 8 18 1 65 187 160 417 ...
## $ AUDIT : int 14 4 0 0 2 0 11 0 0 19 ...
## $ CEGUE : int 8 0 0 0 0 0 4 0 0 12 ...
## $ BAJAVISI : int 0 0 0 0 2 0 6 0 0 5 ...
## $ SORDCEGUE : int 0 0 0 0 0 0 0 0 0 0 ...
## $ MOTORA : int 16 0 0 0 1 0 6 0 4 10 ...
## $ AUTIS : int 0 0 0 0 0 0 4 0 0 14 ...
## $ ARPERG : int 0 0 0 0 0 0 0 0 0 1 ...
## $ OTRO : int 0 0 0 0 2 0 0 0 0 3 ...
## $ EBR : int 5 7 9 2 5 7 9 2 7 3 ...names(perudat)## [1] "SP_ID" "IDPROV" "IDDPTO" "NOMBDEP" "NOMBPROV"
## [6] "SUP_INSULA" "SUP_LACUST" "SUP_INS_D" "IDH" "esperanza"
## [11] "secundaria" "educa" "percapitaf" "IDE" "identidad"
## [16] "salud" "educacion" "saneamient" "electrific" "costa"
## [21] "capital" "tamano" "fecundidad" "desnutrici" "densidadpo"
## [26] "mortalidad" "analfa" "analfa1" "analfa2" "analfa3"
## [31] "analfa4" "pob" "pob_ur" "pob_rural" "pob_h"
## [36] "pob_m" "TOTAL" "INTEL" "AUDIT" "CEGUE"
## [41] "BAJAVISI" "SORDCEGUE" "MOTORA" "AUTIS" "ARPERG"
## [46] "OTRO" "EBR"#VD:ebr
#VIs:intel, audit, cegue, bajavisi,sordcegue,motora,autis,arperg,
#VCs: total
regreData1=perudat[,c(37,41,45)]
names(regreData1)## [1] "TOTAL" "BAJAVISI" "ARPERG"modelo1=glm(TOTAL~.,
data=regreData1,
family ="gaussian")
summary(modelo1)##
## Call:
## glm(formula = TOTAL ~ ., family = "gaussian", data = regreData1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -805.14 -30.37 -13.19 20.63 674.31
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 31.369 10.940 2.867 0.0046 **
## BAJAVISI 13.662 2.600 5.254 3.91e-07 ***
## ARPERG 52.938 2.598 20.374 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 19817.96)
##
## Null deviance: 47671527 on 195 degrees of freedom
## Residual deviance: 3824865 on 193 degrees of freedom
## AIC: 2500.5
##
## Number of Fisher Scoring iterations: 2Tiene mayor influencia el asperger y la baja visión siendo la tipología de asperger el que tiene mayor influencia Donde hay más niños con baja visión hay mayor población de niños con discapacidad.