UBICACION DE PERROS EN ASA
#LIBRERIAS
library(plyr)
library(readxl)
library(data.table)
library(tidyverse)
library(ggplot2)
library(httr)
library(dplyr)
library(cowplot)
#BASE DE DATOS
PERROS_TOTAL<- read_excel("F:/BUSQUEDA PERROS/BUSQUEDA-DE-PERROS/DATOS PERROS.xlsx",
sheet = "DATOS_GENERAL")
poligonos<- read_excel("F:/BUSQUEDA PERROS/BUSQUEDA-DE-PERROS/ASA.xlsx")
##COMPARACION DE PERROS ENCONTRADOS ENTRE BUSCADORES
#URB. APURIMAC
PERROS.34<-filter(PERROS_TOTAL, ZONA=="URB. APURIMAC")
PERROS.34<-select( PERROS.34,CODIGO_PERRO, BUSCADOR, ZONA)
PERROS.34<-na.omit( PERROS.34)
userA <- PERROS.34[PERROS.34$BUSCADOR=="3",]
userB <- PERROS.34[PERROS.34$BUSCADOR=="9",]
userC <- PERROS.34[PERROS.34$BUSCADOR=="2",]
userD <- PERROS.34[PERROS.34$BUSCADOR=="1",]
userGS <- PERROS.34[PERROS.34$BUSCADOR=="GS",]
#Merge entre busquedas
resultAxB <- merge(userA, userB, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxC <- merge(userA, userC,by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxD <- merge(userA, userC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultBxC <- merge(userB, userC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultBxD <- merge(userB, userD, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultCxD <- merge(userA, userC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxBxC <- merge(userC,resultAxB, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultBxCxD <- merge(userD, resultBxC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxBxD <- merge(userA, resultBxD, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxCxD <- merge(userA, resultCxD, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxBxCxD <- merge(userD,resultAxBxC ,by=c("CODIGO_PERRO","ZONA"), all=TRUE)
#colocar combinaciones en un data frame para graficar
resultAxB=cbind(resultAxB,Busqueda=rep("3x4",80))
resultAxB<- select(resultAxB,CODIGO_PERRO,Busqueda,ZONA)
resultAxC=cbind(resultAxC,Busqueda=rep("3x2",68))
resultAxC<- select(resultAxC,CODIGO_PERRO,Busqueda,ZONA)
resultAxD=cbind(resultAxD,Busqueda=rep("3x1",68))
resultAxD<- select(resultAxD,CODIGO_PERRO,Busqueda,ZONA)
resultBxC=cbind(resultBxC,Busqueda=rep("4x2",81))
resultBxC<- select(resultBxC,CODIGO_PERRO,Busqueda,ZONA)
resultBxD=cbind(resultBxD,Busqueda=rep("4x1",80))
resultBxD<- select(resultBxD,CODIGO_PERRO,Busqueda,ZONA)
resultCxD=cbind(resultCxD,Busqueda=rep("2x1",68))
resultCxD<- select(resultCxD,CODIGO_PERRO,Busqueda,ZONA)
resultAxBxC=cbind(resultAxBxC,Busqueda=rep("3x4x2",82))
resultAxBxC<- select(resultAxBxC,CODIGO_PERRO,Busqueda,ZONA)
resultAxBxD=cbind(resultAxBxD,Busqueda=rep("3x4x1",80))
resultAxBxD<- select(resultAxBxD,CODIGO_PERRO,Busqueda,ZONA)
resultBxCxD=cbind(resultBxCxD,Busqueda=rep("4x2x1",82))
resultBxCxD<- select(resultBxCxD,CODIGO_PERRO,Busqueda,ZONA)
resultAxCxD=cbind(resultAxCxD,Busqueda=rep("3x2x1",68))
resultAxCxD<- select(resultAxCxD,CODIGO_PERRO,Busqueda,ZONA)
resultAxBxCxD=cbind(resultAxBxCxD,Busqueda=rep("3x4x2x1",82))
resultAxBxCxD<- select(resultAxBxCxD,CODIGO_PERRO,Busqueda,ZONA)
##Cambiar nombre a columna para unir
names(userA)[2]="Busqueda"
names(userB)[2]="Busqueda"
names(userC)[2]="Busqueda"
names(userD)[2]="Busqueda"
names(userGS)[2]="Busqueda"
grafica.34<-rbind(resultAxB,resultAxC,resultAxD,resultBxC,resultBxD,resultCxD,
resultAxBxC,resultAxBxD,resultBxCxD,resultAxCxD,resultAxBxCxD,
userA,userB,userC,userD,userGS)
grafica.34count<-grafica.34%>%count(Busqueda)
grafica.34count<-grafica.34count%>%arrange(desc(n))%>%
mutate(Busqueda=factor(Busqueda,level=Busqueda))
#grafica de buscadores en combinacion
ggplot(grafica.34count,aes(x=Busqueda,y=n))+
geom_bar(aes(),stat = "identity",position="dodge") + labs(x="BUSCADOR",y="PERROS",
title="PERROS ENCONTRADOS EN URB. APURIMAC") + coord_flip()
## VILLA CONFRATERNIDAD ZONA B III MARGEN DERECHO
PERROS.95<-filter(PERROS_TOTAL, ZONA=="VILLA CONFRATERNIDAD ZONA B III MARGEN DERECHO")
PERROS.95<-select( PERROS.95,CODIGO_PERRO, BUSCADOR, ZONA)
PERROS.95<-na.omit(PERROS.95)
userA <- PERROS.95[PERROS.95$BUSCADOR=="1",]
userB <- PERROS.95[PERROS.95$BUSCADOR=="2",]
userC <- PERROS.95[PERROS.95$BUSCADOR=="5",]
userD <- PERROS.95[PERROS.95$BUSCADOR=="3",]
userGS <- PERROS.95[PERROS.95$BUSCADOR=="GS",]
#Merge entre busquedas
resultAxB <- merge(userA, userB, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxC <- merge(userA, userC,by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxD <- merge(userA, userC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultBxC <- merge(userB, userC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultBxD <- merge(userB, userD, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultCxD <- merge(userA, userC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxBxC <- merge(userC,resultAxB, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultBxCxD <- merge(userD, resultBxC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxBxD <- merge(userA, resultBxD, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxCxD <- merge(userA, resultCxD, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxBxCxD <- merge(userD,resultAxBxC ,by=c("CODIGO_PERRO","ZONA"), all=TRUE)
#colocar combinaciones en un data frame para graficar
resultAxB=cbind(resultAxB,Busqueda=rep("1x2",33))
resultAxB<- select(resultAxB,CODIGO_PERRO,Busqueda,ZONA)
resultAxC=cbind(resultAxC,Busqueda=rep("1x5",29))
resultAxC<- select(resultAxC,CODIGO_PERRO,Busqueda,ZONA)
resultAxD=cbind(resultAxD,Busqueda=rep("1x3",29))
resultAxD<- select(resultAxD,CODIGO_PERRO,Busqueda,ZONA)
resultBxC=cbind(resultBxC,Busqueda=rep("2x5",34))
resultBxC<- select(resultBxC,CODIGO_PERRO,Busqueda,ZONA)
resultBxD=cbind(resultBxD,Busqueda=rep("2x3",33))
resultBxD<- select(resultBxD,CODIGO_PERRO,Busqueda,ZONA)
resultCxD=cbind(resultCxD,Busqueda=rep("5x3",29))
resultCxD<- select(resultCxD,CODIGO_PERRO,Busqueda,ZONA)
resultAxBxC=cbind(resultAxBxC,Busqueda=rep("1x2x5",34))
resultAxBxC<- select(resultAxBxC,CODIGO_PERRO,Busqueda,ZONA)
resultAxBxD=cbind(resultAxBxD,Busqueda=rep("1x2x3",35))
resultAxBxD<- select(resultAxBxD,CODIGO_PERRO,Busqueda,ZONA)
resultBxCxD=cbind(resultBxCxD,Busqueda=rep("2x5x3",36))
resultBxCxD<- select(resultBxCxD,CODIGO_PERRO,Busqueda,ZONA)
resultAxCxD=cbind(resultAxCxD,Busqueda=rep("1x5x3",29))
resultAxCxD<- select(resultAxCxD,CODIGO_PERRO,Busqueda,ZONA)
resultAxBxCxD=cbind(resultAxBxCxD,Busqueda=rep("1x2x5x3",36))
resultAxBxCxD<- select(resultAxBxCxD,CODIGO_PERRO,Busqueda,ZONA)
##Cambiar nombre a columna para unir
names(userA)[2]="Busqueda"
names(userB)[2]="Busqueda"
names(userC)[2]="Busqueda"
names(userD)[2]="Busqueda"
names(userGS)[2]="Busqueda"
grafica.95<-rbind(resultAxB,resultAxC,resultAxD,resultBxC,resultBxD,resultCxD,
resultAxBxC,resultAxBxD,resultBxCxD,resultAxCxD,resultAxBxCxD,
userA,userB,userC,userD,userGS)
grafica.95count<-grafica.95%>%count(Busqueda)
grafica.95count<-grafica.95count%>%arrange(desc(n))%>%
mutate(Busqueda=factor(Busqueda,level=Busqueda))
#grafica de buscadores en combinacion
ggplot(grafica.95count,aes(x=Busqueda,y=n))+
geom_bar(aes(),stat = "identity",position="dodge") +
labs(x="BUSCADOR",y="PERROS", title="PERROS ENCONTRADOS EN VILLA CONFRATERNIDAD
ZONA B III MARGEN DERECHO") +
coord_flip()
## ALTO SELVA ALEGRE ZONA A
PERROS.1<-filter(PERROS_TOTAL, ZONA=="ALTO SELVA ALEGRE ZONA A")
PERROS.1<-select( PERROS.1,CODIGO_PERRO, BUSCADOR, ZONA)
PERROS.1<-na.omit(PERROS.1)
userA <- PERROS.1[PERROS.1$BUSCADOR=="19",]
userB <- PERROS.1[PERROS.1$BUSCADOR=="26",]
userC <- PERROS.1[PERROS.1$BUSCADOR=="3",]
userD <- PERROS.1[PERROS.1$BUSCADOR=="2",]
userGS <- PERROS.1[PERROS.1$BUSCADOR=="GS",]
#Merge entre busquedas
resultAxB <- merge(userA, userB, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxC <- merge(userA, userC,by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxD <- merge(userA, userC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultBxC <- merge(userB, userC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultBxD <- merge(userB, userD, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultCxD <- merge(userA, userC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxBxC <- merge(userC,resultAxB, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultBxCxD <- merge(userD, resultBxC, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxBxD <- merge(userA, resultBxD, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxCxD <- merge(userA, resultCxD, by=c("CODIGO_PERRO","ZONA"), all=TRUE)
resultAxBxCxD <- merge(userD,resultAxBxC ,by=c("CODIGO_PERRO","ZONA"), all=TRUE)
#colocar combinaciones en un data frame para graficar
resultAxB=cbind(resultAxB,Busqueda=rep("19x26",44))
resultAxB<- select(resultAxB,CODIGO_PERRO,Busqueda,ZONA)
resultAxC=cbind(resultAxC,Busqueda=rep("19x3",52))
resultAxC<- select(resultAxC,CODIGO_PERRO,Busqueda,ZONA)
resultAxD=cbind(resultAxD,Busqueda=rep("19x2",52))
resultAxD<- select(resultAxD,CODIGO_PERRO,Busqueda,ZONA)
resultBxC=cbind(resultBxC,Busqueda=rep("26x3",45))
resultBxC<- select(resultBxC,CODIGO_PERRO,Busqueda,ZONA)
resultBxD=cbind(resultBxD,Busqueda=rep("26x2",58))
resultBxD<- select(resultBxD,CODIGO_PERRO,Busqueda,ZONA)
resultCxD=cbind(resultCxD,Busqueda=rep("3x2",52))
resultCxD<- select(resultCxD,CODIGO_PERRO,Busqueda,ZONA)
resultAxBxC=cbind(resultAxBxC,Busqueda=rep("19x26x3",56))
resultAxBxC<- select(resultAxBxC,CODIGO_PERRO,Busqueda,ZONA)
resultAxBxD=cbind(resultAxBxD,Busqueda=rep("19x26x2",63))
resultAxBxD<- select(resultAxBxD,CODIGO_PERRO,Busqueda,ZONA)
resultBxCxD=cbind(resultBxCxD,Busqueda=rep("26x3x2",65))
resultBxCxD<- select(resultBxCxD,CODIGO_PERRO,Busqueda,ZONA)
resultAxCxD=cbind(resultAxCxD,Busqueda=rep("19x3x2",52))
resultAxCxD<- select(resultAxCxD,CODIGO_PERRO,Busqueda,ZONA)
resultAxBxCxD=cbind(resultAxBxCxD,Busqueda=rep("19x26x3x2",69))
resultAxBxCxD<- select(resultAxBxCxD,CODIGO_PERRO,Busqueda,ZONA)
##Cambiar nombre a columna para unir
names(userA)[2]="Busqueda"
names(userB)[2]="Busqueda"
names(userC)[2]="Busqueda"
names(userD)[2]="Busqueda"
names(userGS)[2]="Busqueda"
grafica.1<-rbind(resultAxB,resultAxC,resultAxD,resultBxC,resultBxD,resultCxD,
resultAxBxC,resultAxBxD,resultBxCxD,resultAxCxD,resultAxBxCxD,
userA,userB,userC,userD,userGS)
grafica.1count<-grafica.1%>%count(Busqueda)
grafica.1count<-grafica.1count%>%arrange(desc(n))%>%
mutate(Busqueda=factor(Busqueda,level=Busqueda))
#grafica de buscadores en combinacion
ggplot(grafica.1count,aes(x=Busqueda,y=n))+
geom_bar(aes(),stat = "identity",position="dodge") +
labs(x="BUSCADOR",y="PERROS",
title="PERROS ENCONTRADOS EN URB. ALTO SELVA ALEGRE ZONA A") +
coord_flip()
CORRELACION ENTRE PERROS ENCUESTAS Y PERROS STREET VIEW
PERROS CON ACCESO A LA CALLE ENCUESTAS
#CARGANDO BASES DE DATOS
ENCUESTA.PERROS<- read_excel("F:/BUSQUEDA PERROS/BUSQUEDA-DE-PERROS/ENCUESTA PERROS.xlsx")
PERROS_GOOGLE<- read_excel("F:/BUSQUEDA PERROS/BUSQUEDA-DE-PERROS/DATOS PERROS.xlsx",
sheet = "GOLD_STANDARD")
PRUEBA_PERROS<- read_excel("F:/BUSQUEDA PERROS/BUSQUEDA-DE-PERROS/DATOS PERROS.xlsx",
sheet = "KM")
#filtrar perros deambulantes encuestas
ENC_PERROS_LIB.ACCE<-filter(ENCUESTA.PERROS,ACCESO_CALLE=="SI")
#filtrar perros GSV
PERROS_GSV<-filter(PERROS_GOOGLE,BUSQUEDA=="GS")
PERROS_GSV<-filter(PERROS_GSV, ZONA=="CONQUISTADOR II"|
ZONA=="A.A.H.H. JAVIER HERAUD PAMPAS POLANCO" |
ZONA=="VILLA FLORIDA"|ZONA=="VILLA SALVADOR"|
ZONA=="INDEPENDENCIA ZONA A I"|ZONA=="URB. APURIMAC"|
ZONA=="EL MIRADOR P. POLANCO"|ZONA=="AA. HH. PRIMERO DE ENERO"|
ZONA=="ANTONIO JOSE DE SUCRE"|ZONA=="AMPLIACION VILLA UNION"|
ZONA=="ASOC. ARTESANAL EL MISTI"|
ZONA=="ASOCIACION VILLA VITARTE Y SAN HILARION"|
ZONA=="AVIS JUAN VELASCO ALVARADO A"|ZONA=="COOP. CRUCE CHILINA"|
ZONA=="CONQUISTADOR II"|ZONA=="COOP. DE VIV. ENATRU"|
ZONA=="COOP. DE VIV. LOS EUCALIPTOS"|
ZONA=="HABITACION URBANA PROGRESIVA SE搼㸱OR DE LOS PIEDADES"|
ZONA=="PAMPA CHICA"|ZONA=="UPIS SAN LUIS"|
ZONA=="VILLA CONFRATERNIDAD B-II"|
ZONA=="VILLA CONFRATERNIDAD ZONA B III MARGEN DERECHO"|
ZONA=="VILLA ECOLOGICA ZONA C I MARGEN DERECHO"|
ZONA=="VILLA ECOLOGICA ZONA C II MARGEN IZQUIERDO"|
ZONA=="VILLA ECOLOGICA ZONA D-1"|ZONA=="VILLA ECOLOGICA ZONA D-2 MARGEN DERECHO"|
ZONA=="VILLAS CHACHAS")
#filtrar zonas por km y area
PERROS_KM<-filter(PRUEBA_PERROS, ZONA=="CONQUISTADOR II"|
ZONA=="A.A.H.H. JAVIER HERAUD PAMPAS POLANCO" |
ZONA=="VILLA FLORIDA"|ZONA=="VILLA SALVADOR"|
ZONA=="INDEPENDENCIA ZONA A I"|ZONA=="URB. APURIMAC"|
ZONA=="EL MIRADOR P. POLANCO"|ZONA=="AA. HH. PRIMERO DE ENERO"|
ZONA=="ANTONIO JOSE DE SUCRE"|ZONA=="AMPLIACION VILLA UNION"|
ZONA=="ASOC. ARTESANAL EL MISTI"|
ZONA=="ASOCIACION VILLA VITARTE Y SAN HILARION"|
ZONA=="AVIS JUAN VELASCO ALVARADO A"|ZONA=="COOP. CRUCE CHILINA"|
ZONA=="CONQUISTADOR II"|ZONA=="COOP. DE VIV. ENATRU"|
ZONA=="COOP. DE VIV. LOS EUCALIPTOS"|
ZONA=="HABITACION URBANA PROGRESIVA SE搼㸱OR DE LOS PIEDADES"|
ZONA=="PAMPA CHICA"|ZONA=="UPIS SAN LUIS"|
ZONA=="VILLA CONFRATERNIDAD B-II"|
ZONA=="VILLA CONFRATERNIDAD ZONA B III MARGEN DERECHO"|
ZONA=="VILLA ECOLOGICA ZONA C I MARGEN DERECHO"|
ZONA=="VILLA ECOLOGICA ZONA C II MARGEN IZQUIERDO"|
ZONA=="VILLA ECOLOGICA ZONA D-1"|ZONA=="VILLA ECOLOGICA ZONA D-2 MARGEN DERECHO"|
ZONA=="VILLAS CHACHAS")
#creando data.frame de KM Y AREA
PERROS_KM<-select(PERROS_KM,ZONA,AREA, KILOMETROS)
#creando data.frame de perros encuesta zona /perro
ENC_PERROS_LIB.ACCE<-select(ENC_PERROS_LIB.ACCE,ZONA)
ENC_PERROS_LIB.ACCE$ZONA<-as.factor(ENC_PERROS_LIB.ACCE$ZONA)
ENC_PERROS_LIB.ACCE<-as.data.frame(table(ENC_PERROS_LIB.ACCE))
colnames(ENC_PERROS_LIB.ACCE)[1] <- "ZONA"
colnames(ENC_PERROS_LIB.ACCE)[2] <- "PERROS.ENC"
ENC_PERROS_LIB.ACCE$ZONA<-as.factor(ENC_PERROS_LIB.ACCE$ZONA)
# CREANDO DATA FRAME PERROS GSV
PERROS_GSV<-select(PERROS_GSV,ZONA)
PERROS_GSV<-as.data.frame(table(PERROS_GSV))
colnames(PERROS_GSV)[1] <- "ZONA"
colnames(PERROS_GSV)[2] <- "PERROS.GSV"
PERROS_GSV$ZONA<-as.factor(PERROS_GSV$ZONA)
#merge
PERROS_LIB.ACCE.1<-merge(ENC_PERROS_LIB.ACCE,PERROS_GSV,by="ZONA")
PERROS_LIB.ACCE.1<-merge(PERROS_LIB.ACCE.1,PERROS_KM,by="ZONA")
#distribucion normal
par(mfrow=c(1,2))
hist(PERROS_LIB.ACCE.1$PERROS.GSV, xlab = "PERROS.GSV", ylab = "ZONAS")
hist(PERROS_LIB.ACCE.1$PERROS.ENC, xlab = "PERROS.ENC", ylab = "ZONAS")
#correlaci昼㸳n de Spearman
cor(x=PERROS_LIB.ACCE.1$PERROS.GSV,y=PERROS_LIB.ACCE.1$PERROS.ENC
, method = "spearman")
## [1] 0.5892893
#GRAFICAS
PERROS_FREE<-ggplot(data=PERROS_LIB.ACCE.1,aes(PERROS.GSV,PERROS.ENC )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "lm", colour="Red")+
labs(x="GSV",y="ENCUESTAS",
title="PERROS LIBRE ACCESO ENCUESTAS Y PERROS STREET VIEW")+
geom_text(data=PERROS_LIB.ACCE.1,x=75,y=20,label="??=0.6202706")
PERROS_FREE
PERROS CON ACCESO A LA CALLE O PASEAN SIN CORREA ENCUESTAS
ENC_PERROS_SIN.CORREA<-filter(ENCUESTA.PERROS,ACCESO_CALLE=="SI"|PASEAN=="SI"& CORREA=="NO")
#crenado data.frame de perros encuesta sin correa y libre acceso zona /perro
ENC_PERROS_SIN.CORREA<-select(ENC_PERROS_SIN.CORREA,ZONA)
ENC_PERROS_SIN.CORREA$ZONA<-as.factor( ENC_PERROS_SIN.CORREA$ZONA)
ENC_PERROS_SIN.CORREA<-as.data.frame(table(ENC_PERROS_SIN.CORREA))
colnames(ENC_PERROS_SIN.CORREA)[1] <- "ZONA"
colnames(ENC_PERROS_SIN.CORREA)[2] <- "PERROS.ENC.SIN.COR"
ENC_PERROS_SIN.CORREA$ZONA<-as.factor(ENC_PERROS_SIN.CORREA$ZONA)
#merge
PERROS_SIN.CORREA.1<-merge(ENC_PERROS_SIN.CORREA,PERROS_GSV,by="ZONA")
PERROS_SIN.CORREA.1<-merge(PERROS_SIN.CORREA.1,PERROS_KM,by="ZONA")
#distribucion normal
hist(PERROS_SIN.CORREA.1$PERROS.ENC , xlab = "PERROS.ENC.SIN.COR", ylab = "ZONAS")
#correlaci昼㸳n de spearman
cor(x=PERROS_SIN.CORREA.1$PERROS.GSV,y=PERROS_SIN.CORREA.1$PERROS.ENC.SIN.COR
, method = "spearman")
## [1] 0.6164806
#GRAFICAS
PERROS.SIN.CORR<-ggplot(data=PERROS_SIN.CORREA.1,aes(PERROS.GSV,PERROS.ENC.SIN.COR )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "lm", colour="Red")+
labs(x="GSV",y="ENCUESTAS",
title="PERROS ENCUESTAS CON LIBRE ACCESO
Y/O PASEAN SIN CORREA")+
geom_text(data=PERROS_SIN.CORREA.1,x=75,y=20,label="??=0.6542872")
PERROS.SIN.CORR
PERROS POBLACION TOTAL ENCUESTAS
#creando data.frame de perros totales encuesta zona /perro
ENC_PERROS_TOTAL<-select(ENCUESTA.PERROS,ZONA)
ENC_PERROS_TOTAL$ZONA<-as.factor( ENC_PERROS_TOTAL$ZONA)
ENC_PERROS_TOTAL<-as.data.frame(table(ENC_PERROS_TOTAL))
colnames(ENC_PERROS_TOTAL)[1] <- "ZONA"
colnames(ENC_PERROS_TOTAL)[2] <- "PERROS.ENC.TOT"
ENC_PERROS_TOTAL$ZONA<-as.factor(ENC_PERROS_TOTAL$ZONA)
#merge
PERROS_TOTAL.1<-merge(ENC_PERROS_TOTAL,PERROS_GSV,by="ZONA")
PERROS_TOTAL.1<-merge(PERROS_TOTAL.1,PERROS_KM,by="ZONA")
#distribuci昼㸳n normal
hist(PERROS_TOTAL.1$PERROS.ENC, xlab = "PERROS.ENC.TOT", ylab = "ZONAS")
#correlaci昼㸳n de spearman
cor(x=PERROS_TOTAL.1$PERROS.GSV,y=PERROS_TOTAL.1$PERROS.ENC.TOT
, method = "spearman")
## [1] 0.4938415
#GRAFICAS
PERROS_TOTAL<-ggplot(data=PERROS_TOTAL.1,aes(PERROS.GSV,PERROS.ENC.TOT )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "lm", colour="Red")+
labs(x="GSV",y="ENCUESTAS",
title="POBLACION TOTAL PERROS ENCUESTAS")+
geom_text(data=PERROS_TOTAL.1,x=75,y=20,label="??=0.5412248")
PERROS_TOTAL
MODELOS PARA PERROS LIBRE ACCESO ENCUESTAS Y PERROS STREET VIEW
#MODELO 0
modelo_0<- glm(PERROS.ENC ~ PERROS.GSV,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_0)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.1921 -2.9152 -0.0138 1.7337 6.4860
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.761322 0.067566 40.87 <2e-16 ***
## PERROS.GSV 0.021240 0.001308 16.24 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 232.65 on 23 degrees of freedom
## AIC: 364.66
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_0)
#MODELO 1
modelo_1<- glm(PERROS.ENC ~ PERROS.GSV + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_1)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + KILOMETROS, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.8402 -2.2566 -0.3532 1.4037 6.0709
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.824754 0.065876 42.880 < 2e-16 ***
## PERROS.GSV 0.002635 0.003976 0.663 0.507
## KILOMETROS 0.235276 0.047552 4.948 7.51e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 207.26 on 22 degrees of freedom
## AIC: 341.27
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_1)
#MODELO 2
modelo_2<- glm(PERROS.ENC ~ PERROS.GSV + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_2)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.0854 -1.4080 -0.9239 1.5056 6.3277
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.804525 0.067540 41.524 <2e-16 ***
## PERROS.GSV -0.001728 0.001307 -1.322 0.186
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 211.34 on 24 degrees of freedom
## Residual deviance: 209.58 on 23 degrees of freedom
## AIC: 341.59
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_2)
#MODELO 3
modelo_3<- glm(PERROS.ENC ~ PERROS.GSV + AREA ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_3)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + AREA, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.3401 -2.6395 -0.2109 2.0613 6.4704
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.7968242 0.0650194 43.015 < 2e-16 ***
## PERROS.GSV 0.0089184 0.0023785 3.750 0.000177 ***
## AREA 0.0041657 0.0006988 5.962 2.5e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 198.38 on 22 degrees of freedom
## AIC: 332.4
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_3)
#MODELO 4
modelo_4<- glm(PERROS.ENC ~ PERROS.GSV + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_4)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + offset(log(AREA)), family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.0006 -2.0774 0.6914 1.4910 6.4030
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.8721020 0.0648326 -13.452 <2e-16 ***
## PERROS.GSV -0.0004912 0.0012371 -0.397 0.691
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 218.96 on 24 degrees of freedom
## Residual deviance: 218.80 on 23 degrees of freedom
## AIC: 350.82
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_4)
#MODELO 5
modelo_5<- glm(PERROS.ENC ~ PERROS.GSV + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_5)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + KILOMETROS + AREA, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.4600 -2.7512 -0.2285 1.9215 6.3067
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.8159234 0.0657169 42.849 < 2e-16 ***
## PERROS.GSV 0.0042694 0.0039603 1.078 0.281013
## KILOMETROS 0.0923866 0.0626312 1.475 0.140189
## AREA 0.0032516 0.0009468 3.434 0.000594 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 196.17 on 21 degrees of freedom
## AIC: 332.18
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_5)
MODELO PARA PERROS LIBRE ACCESO ENCUESTAS Y/O PERROS QUE PASEAN SIN CORREA Y PERROS STREET VIEW
#MODELO 6
modelo_6<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_6)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV, family = poisson(link = "log"),
## data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -7.825 -2.350 -0.517 2.541 6.420
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.3064792 0.0485794 68.06 <2e-16 ***
## PERROS.GSV 0.0248533 0.0008999 27.62 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 317.18 on 23 degrees of freedom
## AIC: 468.05
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_6)
#MODELO 7
modelo_7<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_7)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS, family = poisson(link = "log"),
## data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.912 -2.589 -1.125 1.902 5.656
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.407132 0.047009 72.479 <2e-16 ***
## PERROS.GSV -0.000477 0.002865 -0.167 0.868
## KILOMETROS 0.314236 0.033900 9.269 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 226.39 on 22 degrees of freedom
## AIC: 379.26
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_7)
#MODELO 8
modelo_8<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_8)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.499 -1.765 -1.025 2.335 8.184
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.3500735 0.0485129 69.055 <2e-16 ***
## PERROS.GSV 0.0018767 0.0008983 2.089 0.0367 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 250.08 on 24 degrees of freedom
## Residual deviance: 245.74 on 23 degrees of freedom
## AIC: 396.61
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_8)
#MODELO 9
modelo_9<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + AREA ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_9)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + AREA, family = poisson(link = "log"),
## data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.7607 -2.0110 -0.4342 2.5436 6.3321
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.3394538 0.0480914 69.440 < 2e-16 ***
## PERROS.GSV 0.0185178 0.0017858 10.369 < 2e-16 ***
## AREA 0.0020628 0.0005111 4.036 5.43e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 301.18 on 22 degrees of freedom
## AIC: 454.05
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_9)
#MODELO 10
modelo_10<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_10)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -10.7118 -1.7649 0.8781 2.4608 7.6263
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.3099802 0.0466976 -6.638 3.18e-11 ***
## PERROS.GSV 0.0027542 0.0008542 3.224 0.00126 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 530.10 on 24 degrees of freedom
## Residual deviance: 519.78 on 23 degrees of freedom
## AIC: 670.65
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_10)
#MODELO 11
modelo_11<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_11)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS +
## AREA, family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.896 -2.432 -1.096 2.520 5.476
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.3929650 0.0477016 71.129 < 2e-16 ***
## PERROS.GSV -0.0020253 0.0029303 -0.691 0.489
## KILOMETROS 0.4583500 0.0505545 9.066 < 2e-16 ***
## AREA -0.0032181 0.0008245 -3.903 9.49e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 210.19 on 21 degrees of freedom
## AIC: 365.06
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_11)
MODELO PARA POBLACION TOTAL PERROS ENCUESTAS Y PERROS STREET VIEW
#MODELO 12
modelo_12<- glm(PERROS.ENC.TOT ~ PERROS.GSV,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_12)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV, family = poisson(link = "log"),
## data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -16.8206 -2.6335 0.3078 2.7452 9.5974
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2155751 0.0305126 138.16 <2e-16 ***
## PERROS.GSV 0.0255119 0.0005608 45.49 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.7 on 24 degrees of freedom
## Residual deviance: 1051.6 on 23 degrees of freedom
## AIC: 1225.3
##
## Number of Fisher Scoring iterations: 4
#plots residuos
par(mfrow=c(2,2))
plot(modelo_12)
#MODELO 13
modelo_13<- glm(PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_13)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS, family = poisson(link = "log"),
## data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -10.3720 -3.4789 -0.1846 2.6044 8.3884
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.346790 0.028958 150.106 < 2e-16 ***
## PERROS.GSV -0.009272 0.001844 -5.029 4.94e-07 ***
## KILOMETROS 0.430017 0.021876 19.657 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 633.17 on 22 degrees of freedom
## AIC: 808.91
##
## Number of Fisher Scoring iterations: 4
#plots residuos
par(mfrow=c(2,2))
plot(modelo_13)
#MODELO 14
modelo_14<- glm(PERROS.ENC.TOT ~ PERROS.GSV + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_14)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -14.7109 -2.4116 0.7496 4.1812 6.9966
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2592876 0.0304659 139.805 < 2e-16 ***
## PERROS.GSV 0.0025329 0.0005597 4.526 6.02e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 783.99 on 24 degrees of freedom
## Residual deviance: 763.66 on 23 degrees of freedom
## AIC: 937.4
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_14)
#MODELO 15
modelo_15<- glm(PERROS.ENC.TOT ~ PERROS.GSV + AREA ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_15)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + AREA, family = poisson(link = "log"),
## data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -16.112 -2.888 0.450 3.064 9.648
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2324703 0.0307662 137.569 < 2e-16 ***
## PERROS.GSV 0.0227001 0.0011479 19.776 < 2e-16 ***
## AREA 0.0009063 0.0003252 2.787 0.00532 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.7 on 24 degrees of freedom
## Residual deviance: 1043.9 on 22 degrees of freedom
## AIC: 1219.6
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_15)
#MODELO 16
modelo_16<- glm(PERROS.ENC.TOT ~ PERROS.GSV + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_16)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -20.170 -6.702 3.267 7.011 11.554
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.6021944 0.0293403 20.524 < 2e-16 ***
## PERROS.GSV 0.0033482 0.0005327 6.285 3.27e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2106.2 on 24 degrees of freedom
## Residual deviance: 2067.0 on 23 degrees of freedom
## AIC: 2240.7
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_16)
#MODELO 17
modelo_17<- glm(PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_17)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS + AREA,
## family = poisson(link = "log"), data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.2081 -2.8775 -0.5077 2.2540 7.0929
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2430590 0.0313793 135.218 < 2e-16 ***
## PERROS.GSV -0.0150318 0.0019652 -7.649 2.02e-14 ***
## KILOMETROS 0.9239788 0.0375018 24.638 < 2e-16 ***
## AREA -0.0106802 0.0006315 -16.911 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 287.71 on 21 degrees of freedom
## AIC: 465.45
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_17)
COMPARANDO MODELOS PARA PERROS LIBRE ACCESO ENCUESTAS Y PERROS STREET VIEW
#comparando modelo 0 y modelo 1
anova(modelo_0, modelo_1, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC ~ PERROS.GSV
## Model 2: PERROS.ENC ~ PERROS.GSV + KILOMETROS
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 232.65
## 2 22 207.26 1 25.392 4.677e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 0 y modelo 3
anova(modelo_0, modelo_3, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC ~ PERROS.GSV
## Model 2: PERROS.ENC ~ PERROS.GSV + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 232.65
## 2 22 198.38 1 34.265 4.809e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 0 y modelo 5
anova(modelo_0, modelo_5, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC ~ PERROS.GSV
## Model 2: PERROS.ENC ~ PERROS.GSV + KILOMETROS + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 232.65
## 2 21 196.17 2 36.478 1.199e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
COMPARANDO MODELOS PARA PERROS LIBRE ACCESO ENCUESTAS Y/O PERROS QUE PASEAN SIN CORREA Y PERROS STREET VIEW
#comparando modelo 6 y modelo 7
anova(modelo_6, modelo_7, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.SIN.COR ~ PERROS.GSV
## Model 2: PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 317.18
## 2 22 226.39 1 90.794 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 6 y modelo 9
anova(modelo_6, modelo_9, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.SIN.COR ~ PERROS.GSV
## Model 2: PERROS.ENC.SIN.COR ~ PERROS.GSV + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 317.18
## 2 22 301.18 1 16.002 6.329e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 6 y modelo 11
anova(modelo_6, modelo_11, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.SIN.COR ~ PERROS.GSV
## Model 2: PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 317.18
## 2 21 210.19 2 106.99 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
COMPARANDO MODELOS PARA POBLACION TOTAL PERROS ENCUESTAS Y PERROS STREET VIEW
#comparando modelo 12 y modelo 13
anova(modelo_12, modelo_13, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.TOT ~ PERROS.GSV
## Model 2: PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 1051.58
## 2 22 633.17 1 418.41 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 12 y modelo 15
anova(modelo_12, modelo_15, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.TOT ~ PERROS.GSV
## Model 2: PERROS.ENC.TOT ~ PERROS.GSV + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 1051.6
## 2 22 1043.9 1 7.7072 0.0055 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 12 y modelo 17
anova(modelo_12, modelo_17, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.TOT ~ PERROS.GSV
## Model 2: PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 1051.58
## 2 21 287.71 2 763.87 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
PERROS SIN REPETICIONES
#merge
PERROS_TOTAL.3<-merge(ENC_PERROS_TOTAL,PERROS.SIN.REP,by="ZONA")
PERROS_TOTAL.3<-merge(PERROS_TOTAL.3,PERROS_KM,by="ZONA")
#distribuci昼㸳n normal
hist(PERROS_TOTAL.3$PERROS.GSV.SIN.REP, xlab ="PERROS.GSV", ylab = "ZONA")
#correlaci昼㸳n de spearman
cor(x=PERROS_TOTAL.3$PERROS.GSV.SIN.REP,y=PERROS_TOTAL.3$PERROS.ENC.TOT
, method = "spearman")
## [1] 0.6253856
#GRAFICAS
PERROS.TOTAL.SIN.REP<-ggplot(data=PERROS_TOTAL.3,aes(PERROS.GSV.SIN.REP,PERROS.ENC.TOT )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "lm", colour="Red")+
labs(x="GSV",y="ENCUESTAS",
title="POBLACION TOTAL PERROS ENCUESTAS - SIN REPETICIONES")+
geom_text(data=PERROS_TOTAL.3,x=65,y=20,label="??=0.6687768")
PERROS.TOTAL.SIN.REP
COMPARACION DE GRAFICAS
#PLOTS
cowplot::plot_grid(PERROS_TOTAL,PERROS.TOTAL.UNI,PERROS.TOTAL.SIN.REP, labels="AUTO")
GRAFICAS GLM POISSON Y LM EN PERROS GSV VS PERROS ENCUESTAS
#GRAFICAS GLM POISSON
PERROS_FREE.POISSON<-ggplot(data=PERROS_LIB.ACCE.1,aes(PERROS.GSV,PERROS.ENC )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "glm",
method.args = list(family = 'poisson'), colour="Red")+
geom_smooth(method = "lm", colour="blue")+
labs(x="GSV",y="ENCUESTAS",
title="PERROS LIBRE ACCESO ENCUESTAS Y PERROS STREET VIEW")+
geom_text(data=PERROS_LIB.ACCE.1,x=75,y=20,label="??=0.6202706")
PERROS.SIN.CORR.POISSON<-ggplot(data=PERROS_SIN.CORREA.1,aes(PERROS.GSV,PERROS.ENC.SIN.COR )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "glm",
method.args = list(family = 'poisson'), colour="Red")+
geom_smooth(method = "lm", colour="blue")+
labs(x="GSV",y="ENCUESTAS",
title="PERROS ENCUESTAS CON LIBRE ACCESO
Y/O PASEAN SIN CORREA")+
geom_text(data=PERROS_SIN.CORREA.1,x=75,y=20,label="??=0.6542872")
PERROS_TOTAL.POISSON<-ggplot(data=PERROS_TOTAL.1,aes(PERROS.GSV,PERROS.ENC.TOT )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "glm",
method.args = list(family = 'poisson'), colour="Red")+
geom_smooth(method = "lm", colour="blue")+
labs(x="GSV",y="ENCUESTAS",
title="POBLACION TOTAL PERROS ENCUESTAS")+
geom_text(data=PERROS_TOTAL.1,x=75,y=20,label="??=0.5412248")
#PLOTS
plot_grid(PERROS_FREE.POISSON,PERROS.SIN.CORR.POISSON,PERROS_TOTAL.POISSON, labels="AUTO")
MODELOS POISSON PERROS LIBRE ACCESO ENCUESTAS Y PERROS STREET VIEW UNICOS
modelo_0<- glm(PERROS.ENC ~ PERROS_GSV.UNIQUE,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.2)
summary(modelo_0)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS_GSV.UNIQUE, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.9739 -2.5482 0.0722 1.9246 6.0559
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.831113 0.063732 44.42 <2e-16 ***
## PERROS_GSV.UNIQUE 0.021204 0.001301 16.30 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 231.88 on 23 degrees of freedom
## AIC: 363.9
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_0)
#MODELO 1
modelo_1<- glm(PERROS.ENC ~ PERROS_GSV.UNIQUE + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.2)
summary(modelo_1)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS_GSV.UNIQUE + KILOMETROS, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.8628 -2.4096 -0.4601 1.3980 6.0000
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.8413372 0.0611666 46.452 < 2e-16 ***
## PERROS_GSV.UNIQUE 0.0004493 0.0044459 0.101 0.919
## KILOMETROS 0.2600525 0.0536242 4.850 1.24e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 207.68 on 22 degrees of freedom
## AIC: 341.7
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_1)
#MODELO 2
modelo_2<- glm(PERROS.ENC ~ PERROS_GSV.UNIQUE + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.2)
summary(modelo_2)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS_GSV.UNIQUE + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_LIB.ACCE.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.0960 -1.4267 -0.8255 1.3783 6.2251
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.811283 0.063939 43.968 <2e-16 ***
## PERROS_GSV.UNIQUE -0.002014 0.001307 -1.541 0.123
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 211.34 on 24 degrees of freedom
## Residual deviance: 208.94 on 23 degrees of freedom
## AIC: 340.96
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_2)
#MODELO 3
modelo_3<- glm(PERROS.ENC ~ PERROS_GSV.UNIQUE + AREA ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.2)
summary(modelo_3)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS_GSV.UNIQUE + AREA, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.4230 -2.7857 -0.2824 1.8770 6.2925
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.8228666 0.0614953 45.904 < 2e-16 ***
## PERROS_GSV.UNIQUE 0.0091084 0.0022788 3.997 6.41e-05 ***
## AREA 0.0041330 0.0006746 6.127 8.98e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 196.11 on 22 degrees of freedom
## AIC: 330.12
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_3)
#MODELO 4
modelo_4<- glm(PERROS.ENC ~ PERROS_GSV.UNIQUE + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.2)
summary(modelo_4)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS_GSV.UNIQUE + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_LIB.ACCE.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.8705 -2.1403 0.7838 1.5518 6.4822
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.9015394 0.0605831 -14.881 <2e-16 ***
## PERROS_GSV.UNIQUE 0.0001744 0.0012116 0.144 0.886
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 218.96 on 24 degrees of freedom
## Residual deviance: 218.94 on 23 degrees of freedom
## AIC: 350.96
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_4)
#MODELO 5
modelo_5<- glm(PERROS.ENC ~ PERROS_GSV.UNIQUE + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.2)
summary(modelo_5)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS_GSV.UNIQUE + KILOMETROS + AREA,
## family = poisson(link = "log"), data = PERROS_LIB.ACCE.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.4683 -2.8141 -0.3344 1.8538 6.2492
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.826864 0.061482 45.979 < 2e-16 ***
## PERROS_GSV.UNIQUE 0.006206 0.004745 1.308 0.190940
## KILOMETROS 0.055321 0.079243 0.698 0.485101
## AREA 0.003609 0.001013 3.561 0.000369 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 195.62 on 21 degrees of freedom
## AIC: 331.64
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_5)
MODELOS POISSON PERROS LIBRE ACCESO ENCUESTAS Y/O PERROS QUE PASEAN SIN CORREA
Y PERROS STREET VIEW UNICOS
#MODELO 6
modelo_6<- glm(PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
summary(modelo_6)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE, family = poisson(link = "log"),
## data = PERROS_SIN.CORREA.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.4860 -2.4901 -0.7828 3.1374 5.8246
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.3695279 0.0460381 73.19 <2e-16 ***
## PERROS_GSV.UNIQUE 0.0252292 0.0008926 28.27 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 287.81 on 23 degrees of freedom
## AIC: 438.68
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_6)
#MODELO 7
modelo_7<- glm(PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
summary(modelo_7)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + KILOMETROS,
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.880 -2.457 -1.204 2.050 5.687
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.399411 0.044031 77.205 < 2e-16 ***
## PERROS_GSV.UNIQUE 0.001331 0.003196 0.416 0.677
## KILOMETROS 0.293537 0.038058 7.713 1.23e-14 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 226.24 on 22 degrees of freedom
## AIC: 379.11
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_7)
#MODELO 8
modelo_8<- glm(PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
summary(modelo_8)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.3979 -1.7360 -0.8797 2.3457 8.3094
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.348470 0.046130 72.587 <2e-16 ***
## PERROS_GSV.UNIQUE 0.002040 0.000895 2.279 0.0227 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 250.08 on 24 degrees of freedom
## Residual deviance: 244.92 on 23 degrees of freedom
## AIC: 395.79
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_8)
#MODELO 9
modelo_9<- glm(PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + AREA ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
summary(modelo_9)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + AREA,
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.9136 -1.9455 -0.8735 2.3884 5.8789
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.3823031 0.0452745 74.707 < 2e-16 ***
## PERROS_GSV.UNIQUE 0.0198086 0.0017672 11.209 < 2e-16 ***
## AREA 0.0017596 0.0005048 3.486 0.00049 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.5 on 24 degrees of freedom
## Residual deviance: 275.9 on 22 degrees of freedom
## AIC: 428.77
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_9)
#MODELO 10
modelo_10<- glm(PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
summary(modelo_10)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -10.1504 -2.2284 0.8606 2.4174 7.9401
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.3408717 0.0438668 -7.771 7.81e-15 ***
## PERROS_GSV.UNIQUE 0.0036827 0.0008354 4.408 1.04e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 530.10 on 24 degrees of freedom
## Residual deviance: 510.86 on 23 degrees of freedom
## AIC: 661.73
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_10)
#MODELO 11
modelo_11<- glm(PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
summary(modelo_11)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + KILOMETROS +
## AREA, family = poisson(link = "log"), data = PERROS_SIN.CORREA.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.896 -2.366 -1.097 2.438 5.513
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.3880997 0.0445071 76.125 < 2e-16 ***
## PERROS_GSV.UNIQUE -0.0031774 0.0033860 -0.938 0.348
## KILOMETROS 0.4790208 0.0600836 7.973 1.55e-15 ***
## AREA -0.0033971 0.0008605 -3.948 7.88e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 209.79 on 21 degrees of freedom
## AIC: 364.65
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_11)
MODELOS POISSON POBLACION TOTAL PERROS ENCUESTAS Y PERROS STREET VIEW UNICOS
#MODELO 12
modelo_12<- glm(PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE,
family = poisson(link = "log"), data = PERROS_TOTAL.2)
summary(modelo_12)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE, family = poisson(link = "log"),
## data = PERROS_TOTAL.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -14.7906 -2.7768 0.0531 2.5262 9.4613
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2538610 0.0290700 146.33 <2e-16 ***
## PERROS_GSV.UNIQUE 0.0264789 0.0005549 47.72 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 872.74 on 23 degrees of freedom
## AIC: 1046.5
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_12)
#MODELO 13
modelo_13<- glm(PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_TOTAL.2)
summary(modelo_13)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + KILOMETROS,
## family = poisson(link = "log"), data = PERROS_TOTAL.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -11.4617 -3.1356 0.4129 2.8543 8.0954
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.291884 0.027616 155.414 <2e-16 ***
## PERROS_GSV.UNIQUE -0.001810 0.002026 -0.893 0.372
## KILOMETROS 0.345742 0.024104 14.344 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 658.04 on 22 degrees of freedom
## AIC: 833.77
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_13)
#MODELO 14
modelo_14<- glm(PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_TOTAL.2)
summary(modelo_14)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_TOTAL.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -14.5244 -2.4610 0.8018 3.8143 7.3195
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2325280 0.0291183 145.356 < 2e-16 ***
## PERROS_GSV.UNIQUE 0.0032956 0.0005561 5.926 3.1e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 783.99 on 24 degrees of freedom
## Residual deviance: 749.22 on 23 degrees of freedom
## AIC: 922.95
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_14)
#MODELO 15
modelo_15<- glm(PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + AREA ,
family = poisson(link = "log"), data = PERROS_TOTAL.2)
summary(modelo_15)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + AREA, family = poisson(link = "log"),
## data = PERROS_TOTAL.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -14.8016 -2.7613 0.0469 2.5331 9.4596
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.254e+00 2.935e-02 144.93 <2e-16 ***
## PERROS_GSV.UNIQUE 2.655e-02 1.172e-03 22.65 <2e-16 ***
## AREA -2.296e-05 3.278e-04 -0.07 0.944
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 872.74 on 22 degrees of freedom
## AIC: 1048.5
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_15)
#MODELO 16
modelo_16<- glm(PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_TOTAL.2)
summary(modelo_16)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_TOTAL.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -18.973 -6.682 3.842 7.028 12.019
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.5503427 0.0277193 19.854 <2e-16 ***
## PERROS_GSV.UNIQUE 0.0047792 0.0005201 9.189 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2106.2 on 24 degrees of freedom
## Residual deviance: 2022.7 on 23 degrees of freedom
## AIC: 2196.5
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_16)
#MODELO 17
modelo_17<- glm(PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_TOTAL.2)
summary(modelo_17)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + KILOMETROS +
## AREA, family = poisson(link = "log"), data = PERROS_TOTAL.2)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.7941 -2.6699 0.0672 2.3363 7.6761
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.1862211 0.0299747 139.658 < 2e-16 ***
## PERROS_GSV.UNIQUE -0.0147085 0.0021422 -6.866 6.6e-12 ***
## KILOMETROS 0.9446547 0.0416472 22.682 < 2e-16 ***
## AREA -0.0112326 0.0006508 -17.258 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 300.57 on 21 degrees of freedom
## AIC: 478.3
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_17)
COMPARANDO MODELOS PARA PERROS LIBRE ACCESO ENCUESTAS Y PERROS STREET VIEW
UNICOS
#comparando modelo 0 y modelo 1
anova(modelo_0, modelo_4, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC ~ PERROS_GSV.UNIQUE
## Model 2: PERROS.ENC ~ PERROS_GSV.UNIQUE + offset(log(AREA))
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 231.88
## 2 23 218.94 0 12.94
#comparando modelo 0 y modelo 3
anova(modelo_0, modelo_3, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC ~ PERROS_GSV.UNIQUE
## Model 2: PERROS.ENC ~ PERROS_GSV.UNIQUE + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 231.88
## 2 22 196.11 1 35.772 2.218e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 0 y modelo 5
anova(modelo_0, modelo_5, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC ~ PERROS_GSV.UNIQUE
## Model 2: PERROS.ENC ~ PERROS_GSV.UNIQUE + KILOMETROS + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 231.88
## 2 21 195.62 2 36.261 1.337e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
COMPARANDO MODELOS PARA PERROS LIBRE ACCESO ENCUESTAS Y/O PERROS QUE PASEAN SIN CORREA Y PERROS STREET VIEW UNICOS
#comparando modelo 6 y modelo 7
anova(modelo_6, modelo_7, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE
## Model 2: PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + KILOMETROS
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 287.81
## 2 22 226.24 1 61.574 4.264e-15 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 6 y modelo 9
anova(modelo_6, modelo_9, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE
## Model 2: PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 287.81
## 2 22 275.90 1 11.911 0.0005581 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 6 y modelo 11
anova(modelo_6, modelo_11, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE
## Model 2: PERROS.ENC.SIN.COR ~ PERROS_GSV.UNIQUE + KILOMETROS + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 287.81
## 2 21 209.78 2 78.03 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
COMPARANDO MODELOS PARA POBLACION TOTAL PERROS ENCUESTAS Y PERROS STREET VIEW UNICOS
#comparando modelo 12 y modelo 13
anova(modelo_12, modelo_13, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE
## Model 2: PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + KILOMETROS
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 872.74
## 2 22 658.04 1 214.7 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#comparando modelo 12 y modelo 15
anova(modelo_12, modelo_15, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE
## Model 2: PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 872.74
## 2 22 872.74 1 0.0049062 0.9442
#comparando modelo 12 y modelo 17
anova(modelo_12, modelo_17, test="Chisq")
## Analysis of Deviance Table
##
## Model 1: PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE
## Model 2: PERROS.ENC.TOT ~ PERROS_GSV.UNIQUE + KILOMETROS + AREA
## Resid. Df Resid. Dev Df Deviance Pr(>Chi)
## 1 23 872.74
## 2 21 300.57 2 572.17 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
MODELOS POISSON POBLACION TOTAL PERROS ENCUESTAS Y PERROS STREET VIEW SIN REPETICIONES
modelo_0<- glm(PERROS.ENC ~ PERROS.GSV.SIN.REP,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.3)
summary(modelo_0)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV.SIN.REP, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.6435 -2.0049 0.0271 2.0723 6.1272
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.871002 0.063651 45.10 <2e-16 ***
## PERROS.GSV.SIN.REP 0.022804 0.001483 15.38 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 252.84 on 23 degrees of freedom
## AIC: 384.86
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_0)
#MODELO 1
modelo_1<- glm(PERROS.ENC ~ PERROS.GSV.SIN.REP + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.3)
summary(modelo_1)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV.SIN.REP + KILOMETROS, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.8394 -2.6390 -0.1552 1.6105 5.9441
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.854460 0.060450 47.220 < 2e-16 ***
## PERROS.GSV.SIN.REP -0.004316 0.004296 -1.005 0.315
## KILOMETROS 0.309083 0.046119 6.702 2.06e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 206.68 on 22 degrees of freedom
## AIC: 340.7
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_1)
#MODELO 2
modelo_2<- glm(PERROS.ENC ~ PERROS.GSV.SIN.REP + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.3)
summary(modelo_2)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV.SIN.REP + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_LIB.ACCE.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.9875 -1.5061 -0.8869 1.2779 6.1422
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.840871 0.063129 45.001 <2e-16 ***
## PERROS.GSV.SIN.REP -0.003078 0.001466 -2.099 0.0358 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 211.34 on 24 degrees of freedom
## Residual deviance: 206.90 on 23 degrees of freedom
## AIC: 338.91
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_2)
#MODELO 3
modelo_3<- glm(PERROS.ENC ~ PERROS.GSV.SIN.REP + AREA ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.3)
summary(modelo_3)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV.SIN.REP + AREA, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.4003 -2.9229 -0.1884 1.7816 6.3521
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.8342276 0.0613124 46.226 < 2e-16 ***
## PERROS.GSV.SIN.REP 0.0083308 0.0023511 3.543 0.000395 ***
## AREA 0.0046151 0.0006223 7.416 1.2e-13 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 199.97 on 22 degrees of freedom
## AIC: 333.98
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_3)
#MODELO 4
modelo_4<- glm(PERROS.ENC ~ PERROS.GSV.SIN.REP + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.3)
summary(modelo_4)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV.SIN.REP + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_LIB.ACCE.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.8936 -2.1325 0.7701 1.5466 6.4734
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -8.977e-01 5.963e-02 -15.05 <2e-16 ***
## PERROS.GSV.SIN.REP 9.531e-05 1.352e-03 0.07 0.944
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 218.96 on 24 degrees of freedom
## Residual deviance: 218.96 on 23 degrees of freedom
## AIC: 350.97
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_4)
#MODELO 5
modelo_5<- glm(PERROS.ENC ~ PERROS.GSV.SIN.REP + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.3)
summary(modelo_5)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV.SIN.REP + KILOMETROS +
## AREA, family = poisson(link = "log"), data = PERROS_LIB.ACCE.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.4993 -2.9687 -0.1515 1.8564 6.2093
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.840483 0.060821 46.703 < 2e-16 ***
## PERROS.GSV.SIN.REP 0.001629 0.004688 0.348 0.72818
## KILOMETROS 0.123605 0.074837 1.652 0.09861 .
## AREA 0.003273 0.001036 3.160 0.00158 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 471.14 on 24 degrees of freedom
## Residual deviance: 197.20 on 21 degrees of freedom
## AIC: 333.22
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_5)
MODELOS POISSON PERROS LIBRE ACCESO ENCUESTAS Y/O PERROS QUE PASEAN SIN CORREA
Y PERROS STREET VIEW UNICOS SIN REPETICIONES
#MODELO 6
modelo_6<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
summary(modelo_6)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP, family = poisson(link = "log"),
## data = PERROS_SIN.CORREA.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.4780 -2.2761 -0.4352 2.2108 6.0939
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.372454 0.046541 72.46 <2e-16 ***
## PERROS.GSV.SIN.REP 0.028344 0.001021 27.75 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 293.06 on 23 degrees of freedom
## AIC: 443.93
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_6)
#MODELO 7
modelo_7<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
summary(modelo_7)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + KILOMETROS,
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.835 -2.220 -1.113 2.522 5.768
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.387267 0.044332 76.407 < 2e-16 ***
## PERROS.GSV.SIN.REP 0.004671 0.003043 1.535 0.125
## KILOMETROS 0.262147 0.031962 8.202 2.37e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 224.06 on 22 degrees of freedom
## AIC: 376.93
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_7)
#MODELO 8
modelo_8<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
summary(modelo_8)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.5197 -1.7561 -0.8868 2.2512 8.3011
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.347366 0.046099 72.61 <2e-16 ***
## PERROS.GSV.SIN.REP 0.002330 0.001008 2.31 0.0209 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 250.08 on 24 degrees of freedom
## Residual deviance: 244.77 on 23 degrees of freedom
## AIC: 395.64
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_8)
#MODELO 9
modelo_9<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + AREA ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
summary(modelo_9)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + AREA,
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.780 -2.634 -0.581 3.110 6.114
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.3792487 0.0453513 74.513 < 2e-16 ***
## PERROS.GSV.SIN.REP 0.0209264 0.0018058 11.588 < 2e-16 ***
## AREA 0.0022191 0.0004577 4.848 1.25e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 269.94 on 22 degrees of freedom
## AIC: 422.81
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_9)
#MODELO 10
modelo_10<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
summary(modelo_10)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -10.0328 -1.9559 0.9089 2.4369 8.0047
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.3618320 0.0436805 -8.284 < 2e-16 ***
## PERROS.GSV.SIN.REP 0.0047274 0.0009366 5.047 4.48e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 530.10 on 24 degrees of freedom
## Residual deviance: 504.78 on 23 degrees of freedom
## AIC: 655.65
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_10)
#MODELO 11
modelo_11<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
summary(modelo_11)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV.SIN.REP + KILOMETROS +
## AREA, family = poisson(link = "log"), data = PERROS_SIN.CORREA.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.853 -2.379 -1.123 2.511 5.545
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.3804394 0.0446393 75.728 < 2e-16 ***
## PERROS.GSV.SIN.REP -0.0003635 0.0033537 -0.108 0.913700
## KILOMETROS 0.4377261 0.0585748 7.473 7.84e-14 ***
## AREA -0.0031834 0.0008931 -3.564 0.000365 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1005.51 on 24 degrees of freedom
## Residual deviance: 210.66 on 21 degrees of freedom
## AIC: 365.52
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_11)
MODELOS POISSON POBLACION TOTAL PERROS ENCUESTAS Y PERROS STREET VIEW SIN REPETICIONES
#MODELO 12
modelo_12<- glm(PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP,
family = poisson(link = "log"), data = PERROS_TOTAL.3)
summary(modelo_12)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP, family = poisson(link = "log"),
## data = PERROS_TOTAL.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -14.7648 -3.4612 0.5218 2.3002 9.5801
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2538488 0.0294470 144.46 <2e-16 ***
## PERROS.GSV.SIN.REP 0.0298270 0.0006364 46.87 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 882.61 on 23 degrees of freedom
## AIC: 1056.3
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_12)
#MODELO 13
modelo_13<- glm(PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_TOTAL.3)
summary(modelo_13)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + KILOMETROS,
## family = poisson(link = "log"), data = PERROS_TOTAL.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -11.8613 -3.0170 0.1139 3.1112 8.0789
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.276031 0.027884 153.348 <2e-16 ***
## PERROS.GSV.SIN.REP 0.002768 0.001921 1.441 0.15
## KILOMETROS 0.297351 0.020097 14.796 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 656.76 on 22 degrees of freedom
## AIC: 832.5
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_13)
#MODELO 14
modelo_14<- glm(PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_TOTAL.3)
summary(modelo_14)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_TOTAL.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -14.8236 -2.4371 0.5057 3.8417 7.2696
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2302673 0.0291589 145.08 < 2e-16 ***
## PERROS.GSV.SIN.REP 0.0037748 0.0006281 6.01 1.86e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 783.99 on 24 degrees of freedom
## Residual deviance: 748.08 on 23 degrees of freedom
## AIC: 921.82
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_14)
#MODELO 15
modelo_15<- glm(PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + AREA ,
family = poisson(link = "log"), data = PERROS_TOTAL.3)
summary(modelo_15)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + AREA, family = poisson(link = "log"),
## data = PERROS_TOTAL.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -14.9444 -2.9117 0.4283 2.4717 9.6455
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2599433 0.0292211 145.783 < 2e-16 ***
## PERROS.GSV.SIN.REP 0.0270932 0.0011748 23.062 < 2e-16 ***
## AREA 0.0008013 0.0002920 2.744 0.00608 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 875.12 on 22 degrees of freedom
## AIC: 1050.9
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_15)
#MODELO 16
modelo_16<- glm(PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_TOTAL.3)
summary(modelo_16)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_TOTAL.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -18.980 -6.440 3.910 6.587 12.044
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.5288891 0.0276509 19.13 <2e-16 ***
## PERROS.GSV.SIN.REP 0.0059761 0.0005844 10.23 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2106.2 on 24 degrees of freedom
## Residual deviance: 2002.3 on 23 degrees of freedom
## AIC: 2176
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_16)
#MODELO 17
modelo_17<- glm(PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_TOTAL.3)
summary(modelo_17)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV.SIN.REP + KILOMETROS +
## AREA, family = poisson(link = "log"), data = PERROS_TOTAL.3)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.0502 -2.5781 -0.3486 2.3127 7.4460
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.1806227 0.0299969 139.368 < 2e-16 ***
## PERROS.GSV.SIN.REP -0.0141768 0.0021551 -6.578 4.76e-11 ***
## KILOMETROS 0.9398706 0.0424360 22.148 < 2e-16 ***
## AREA -0.0117992 0.0006925 -17.039 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 2919.66 on 24 degrees of freedom
## Residual deviance: 304.22 on 21 degrees of freedom
## AIC: 481.95
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_17)
CORRELACION ENTRE PERROS ENCUESTAS Y PERROS STREET VIEW
PERROS CON ACCESO A LA CALLE ENCUESTAS
#CARGANDO BASES DE DATOS
ENCUESTA.PERROS<- read_excel("F:/BUSQUEDA PERROS/BUSQUEDA-DE-PERROS/ENCUESTA PERROS.xlsx")
PERROS_GOOGLE<- read_excel("F:/BUSQUEDA PERROS/BUSQUEDA-DE-PERROS/DATOS PERROS.xlsx",
sheet = "GOLD_STANDARD")
PRUEBA_PERROS<- read_excel("F:/BUSQUEDA PERROS/BUSQUEDA-DE-PERROS/DATOS PERROS.xlsx",
sheet = "KM")
#filtrar perros deambulantes encuestas
ENC_PERROS_LIB.ACCE<-filter(ENCUESTA.PERROS,ACCESO_CALLE=="SI")
#filtrar perros GSV
PERROS_GSV<-filter(PERROS_GOOGLE,BUSQUEDA=="GS")
PERROS_GSV<-filter(PERROS_GSV, ZONA=="CONQUISTADOR II"|
ZONA=="A.A.H.H. JAVIER HERAUD PAMPAS POLANCO" |
ZONA=="VILLA FLORIDA"|ZONA=="VILLA SALVADOR"|
ZONA=="EL MIRADOR P. POLANCO"|ZONA=="AA. HH. PRIMERO DE ENERO"|
ZONA=="ANTONIO JOSE DE SUCRE"|ZONA=="AMPLIACION VILLA UNION"|
ZONA=="ASOC. ARTESANAL EL MISTI"|
ZONA=="ASOCIACION VILLA VITARTE Y SAN HILARION"|
ZONA=="AVIS JUAN VELASCO ALVARADO A"|ZONA=="COOP. CRUCE CHILINA"|
ZONA=="CONQUISTADOR II"|ZONA=="COOP. DE VIV. ENATRU"|
ZONA=="COOP. DE VIV. LOS EUCALIPTOS"|
ZONA=="HABITACION URBANA PROGRESIVA SE搼㸱OR DE LOS PIEDADES"|
ZONA=="PAMPA CHICA"|ZONA=="UPIS SAN LUIS"|
ZONA=="VILLA CONFRATERNIDAD B-II"|
ZONA=="VILLA CONFRATERNIDAD ZONA B III MARGEN DERECHO"|
ZONA=="VILLA ECOLOGICA ZONA D-1"|ZONA=="VILLA ECOLOGICA ZONA D-2 MARGEN DERECHO"|
ZONA=="VILLAS CHACHAS")
#filtrar zonas por km y area
PERROS_KM<-filter(PRUEBA_PERROS, ZONA=="CONQUISTADOR II"|
ZONA=="A.A.H.H. JAVIER HERAUD PAMPAS POLANCO" |
ZONA=="VILLA FLORIDA"|ZONA=="VILLA SALVADOR"|
ZONA=="EL MIRADOR P. POLANCO"|ZONA=="AA. HH. PRIMERO DE ENERO"|
ZONA=="ANTONIO JOSE DE SUCRE"|ZONA=="AMPLIACION VILLA UNION"|
ZONA=="ASOC. ARTESANAL EL MISTI"|
ZONA=="ASOCIACION VILLA VITARTE Y SAN HILARION"|
ZONA=="AVIS JUAN VELASCO ALVARADO A"|ZONA=="COOP. CRUCE CHILINA"|
ZONA=="CONQUISTADOR II"|ZONA=="COOP. DE VIV. ENATRU"|
ZONA=="COOP. DE VIV. LOS EUCALIPTOS"|
ZONA=="HABITACION URBANA PROGRESIVA SE搼㸱OR DE LOS PIEDADES"|
ZONA=="PAMPA CHICA"|ZONA=="UPIS SAN LUIS"|
ZONA=="VILLA CONFRATERNIDAD B-II"|
ZONA=="VILLA CONFRATERNIDAD ZONA B III MARGEN DERECHO"|
ZONA=="VILLA ECOLOGICA ZONA D-1"|ZONA=="VILLA ECOLOGICA ZONA D-2 MARGEN DERECHO"|
ZONA=="VILLAS CHACHAS")
#creando data.frame de KM Y AREA
PERROS_KM<-select(PERROS_KM,ZONA,AREA, KILOMETROS)
#creando data.frame de perros encuesta zona /perro
ENC_PERROS_LIB.ACCE<-select(ENC_PERROS_LIB.ACCE,ZONA)
ENC_PERROS_LIB.ACCE$ZONA<-as.factor(ENC_PERROS_LIB.ACCE$ZONA)
ENC_PERROS_LIB.ACCE<-as.data.frame(table(ENC_PERROS_LIB.ACCE))
colnames(ENC_PERROS_LIB.ACCE)[1] <- "ZONA"
colnames(ENC_PERROS_LIB.ACCE)[2] <- "PERROS.ENC"
ENC_PERROS_LIB.ACCE$ZONA<-as.factor(ENC_PERROS_LIB.ACCE$ZONA)
# CREANDO DATA FRAME PERROS GSV
PERROS_GSV<-select(PERROS_GSV,ZONA)
PERROS_GSV<-as.data.frame(table(PERROS_GSV))
colnames(PERROS_GSV)[1] <- "ZONA"
colnames(PERROS_GSV)[2] <- "PERROS.GSV"
PERROS_GSV$ZONA<-as.factor(PERROS_GSV$ZONA)
#merge
PERROS_LIB.ACCE.1<-merge(ENC_PERROS_LIB.ACCE,PERROS_GSV,by="ZONA")
PERROS_LIB.ACCE.1<-merge(PERROS_LIB.ACCE.1,PERROS_KM,by="ZONA")
#distribucion normal
par(mfrow=c(1,2))
hist(PERROS_LIB.ACCE.1$PERROS.GSV, xlab = "PERROS.GSV", ylab = "ZONAS")
hist(PERROS_LIB.ACCE.1$PERROS.ENC, xlab = "PERROS.ENC", ylab = "ZONAS")
#correlaci昼㸳n de Spearman
cor(x=PERROS_LIB.ACCE.1$PERROS.GSV,y=PERROS_LIB.ACCE.1$PERROS.ENC
, method = "spearman")
## [1] 0.4789973
#GRAFICAS
PERROS_FREE<-ggplot(data=PERROS_LIB.ACCE.1,aes(PERROS.GSV,PERROS.ENC )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "lm", colour="Red")+
labs(x="GSV",y="ENCUESTAS",
title="PERROS LIBRE ACCESO ENCUESTAS Y PERROS STREET VIEW")+
geom_text(data=PERROS_LIB.ACCE.1,x=75,y=20,label="??=0.6202706")
PERROS_FREE
PERROS CON ACCESO A LA CALLE O PASEAN SIN CORREA ENCUESTAS
ENC_PERROS_SIN.CORREA<-filter(ENCUESTA.PERROS,ACCESO_CALLE=="SI"|PASEAN=="SI"& CORREA=="NO")
#crenado data.frame de perros encuesta sin correa y libre acceso zona /perro
ENC_PERROS_SIN.CORREA<-select(ENC_PERROS_SIN.CORREA,ZONA)
ENC_PERROS_SIN.CORREA$ZONA<-as.factor( ENC_PERROS_SIN.CORREA$ZONA)
ENC_PERROS_SIN.CORREA<-as.data.frame(table(ENC_PERROS_SIN.CORREA))
colnames(ENC_PERROS_SIN.CORREA)[1] <- "ZONA"
colnames(ENC_PERROS_SIN.CORREA)[2] <- "PERROS.ENC.SIN.COR"
ENC_PERROS_SIN.CORREA$ZONA<-as.factor(ENC_PERROS_SIN.CORREA$ZONA)
#merge
PERROS_SIN.CORREA.1<-merge(ENC_PERROS_SIN.CORREA,PERROS_GSV,by="ZONA")
PERROS_SIN.CORREA.1<-merge(PERROS_SIN.CORREA.1,PERROS_KM,by="ZONA")
#distribucion normal
hist(PERROS_SIN.CORREA.1$PERROS.ENC , xlab = "PERROS.ENC.SIN.COR", ylab = "ZONAS")
#correlaci昼㸳n de spearman
cor(x=PERROS_SIN.CORREA.1$PERROS.GSV,y=PERROS_SIN.CORREA.1$PERROS.ENC.SIN.COR
, method = "spearman")
## [1] 0.562134
#GRAFICAS
PERROS.SIN.CORR<-ggplot(data=PERROS_SIN.CORREA.1,aes(PERROS.GSV,PERROS.ENC.SIN.COR )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "lm", colour="Red")+
labs(x="GSV",y="ENCUESTAS",
title="PERROS ENCUESTAS CON LIBRE ACCESO
Y/O PASEAN SIN CORREA")+
geom_text(data=PERROS_SIN.CORREA.1,x=75,y=20,label="??=0.6542872")
PERROS.SIN.CORR
PERROS POBLACION TOTAL ENCUESTAS
#creando data.frame de perros totales encuesta zona /perro
ENC_PERROS_TOTAL<-select(ENCUESTA.PERROS,ZONA)
ENC_PERROS_TOTAL$ZONA<-as.factor( ENC_PERROS_TOTAL$ZONA)
ENC_PERROS_TOTAL<-as.data.frame(table(ENC_PERROS_TOTAL))
colnames(ENC_PERROS_TOTAL)[1] <- "ZONA"
colnames(ENC_PERROS_TOTAL)[2] <- "PERROS.ENC.TOT"
ENC_PERROS_TOTAL$ZONA<-as.factor(ENC_PERROS_TOTAL$ZONA)
#merge
PERROS_TOTAL.1<-merge(ENC_PERROS_TOTAL,PERROS_GSV,by="ZONA")
PERROS_TOTAL.1<-merge(PERROS_TOTAL.1,PERROS_KM,by="ZONA")
#distribuci昼㸳n normal
hist(PERROS_TOTAL.1$PERROS.ENC.TOT, xlab = "PERROS.ENC.TOT", ylab = "ZONAS")
#correlaci昼㸳n de spearman
cor(x=PERROS_TOTAL.1$PERROS.GSV,y=PERROS_TOTAL.1$PERROS.ENC
, method = "spearman")
## [1] 0.5273083
#GRAFICAS
PERROS_TOTAL<-ggplot(data=PERROS_TOTAL.1,aes(PERROS.GSV,PERROS.ENC.TOT )) +
geom_point(aes(size=0.1,alpha=0.2)) + geom_smooth(method = "lm", colour="Red")+
labs(x="GSV",y="ENCUESTAS",
title="POBLACION TOTAL PERROS ENCUESTAS")+
geom_text(data=PERROS_TOTAL.1,x=75,y=20,label="??=0.5412248")
PERROS_TOTAL
MODELOS PARA PERROS LIBRE ACCESO ENCUESTAS Y PERROS STREET VIEW
#MODELO 0
modelo_0<- glm(PERROS.ENC ~ PERROS.GSV,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_0)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.6990 -3.0350 -0.4081 1.6791 6.4451
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.854525 0.094148 30.320 < 2e-16 ***
## PERROS.GSV 0.017776 0.002758 6.446 1.15e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 252.84 on 20 degrees of freedom
## Residual deviance: 212.01 on 19 degrees of freedom
## AIC: 320.07
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_0)
#MODELO 1
modelo_1<- glm(PERROS.ENC ~ PERROS.GSV + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_1)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + KILOMETROS, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.6187 -3.0775 -0.8105 1.0515 6.0313
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.562077 0.117230 21.855 < 2e-16 ***
## PERROS.GSV -0.003176 0.005471 -0.580 0.562
## KILOMETROS 0.443440 0.101073 4.387 1.15e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 252.84 on 20 degrees of freedom
## Residual deviance: 191.99 on 18 degrees of freedom
## AIC: 302.05
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_1)
#MODELO 2
modelo_2<- glm(PERROS.ENC ~ PERROS.GSV + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_2)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.8583 -1.6590 -0.9931 1.4215 6.2544
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.907429 0.095833 30.338 <2e-16 ***
## PERROS.GSV -0.005780 0.002818 -2.051 0.0403 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 201.10 on 20 degrees of freedom
## Residual deviance: 196.87 on 19 degrees of freedom
## AIC: 304.94
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_2)
#MODELO 3
modelo_3<- glm(PERROS.ENC ~ PERROS.GSV + AREA ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_3)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + AREA, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.6207 -3.0748 -0.1727 1.8811 6.5866
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.655129 0.100593 26.395 < 2e-16 ***
## PERROS.GSV 0.012137 0.002856 4.249 2.14e-05 ***
## AREA 0.004808 0.000888 5.414 6.16e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 252.84 on 20 degrees of freedom
## Residual deviance: 184.84 on 18 degrees of freedom
## AIC: 294.91
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_3)
#MODELO 4
modelo_4<- glm(PERROS.ENC ~ PERROS.GSV + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_4)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + offset(log(AREA)), family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.8437 -2.6414 0.7448 1.7920 6.4340
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.979555 0.090067 -10.876 <2e-16 ***
## PERROS.GSV 0.003607 0.002610 1.382 0.167
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 206.34 on 20 degrees of freedom
## Residual deviance: 204.44 on 19 degrees of freedom
## AIC: 312.51
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_4)
#MODELO 5
modelo_5<- glm(PERROS.ENC ~ PERROS.GSV + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_LIB.ACCE.1)
summary(modelo_5)
##
## Call:
## glm(formula = PERROS.ENC ~ PERROS.GSV + KILOMETROS + AREA, family = poisson(link = "log"),
## data = PERROS_LIB.ACCE.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -4.1460 -2.8469 -0.1587 1.3450 6.2746
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 2.4897019 0.1169770 21.284 < 2e-16 ***
## PERROS.GSV -0.0016077 0.0054817 -0.293 0.76930
## KILOMETROS 0.3084564 0.1056763 2.919 0.00351 **
## AREA 0.0039834 0.0009616 4.143 3.43e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 252.84 on 20 degrees of freedom
## Residual deviance: 176.10 on 17 degrees of freedom
## AIC: 288.16
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_5)
MODELO PARA PERROS LIBRE ACCESO ENCUESTAS Y/O PERROS QUE PASEAN SIN CORREA Y PERROS STREET VIEW
#MODELO 6
modelo_6<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_6)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV, family = poisson(link = "log"),
## data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.3686 -2.7602 -0.8446 2.2026 5.9767
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.491775 0.067137 52.01 <2e-16 ***
## PERROS.GSV 0.019605 0.001946 10.08 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 335.75 on 20 degrees of freedom
## Residual deviance: 235.99 on 19 degrees of freedom
## AIC: 360.7
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_6)
#MODELO 7
modelo_7<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_7)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS, family = poisson(link = "log"),
## data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.282 -2.128 -1.031 2.801 5.426
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.203747 0.083179 38.516 < 2e-16 ***
## PERROS.GSV -0.001206 0.003874 -0.311 0.756
## KILOMETROS 0.439367 0.071495 6.145 7.98e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 335.75 on 20 degrees of freedom
## Residual deviance: 196.74 on 18 degrees of freedom
## AIC: 323.45
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_7)
#MODELO 8
modelo_8<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_8)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.241 -2.050 -1.242 2.067 7.785
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.542194 0.068317 51.849 <2e-16 ***
## PERROS.GSV -0.003871 0.001987 -1.948 0.0514 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 201.22 on 20 degrees of freedom
## Residual deviance: 197.41 on 19 degrees of freedom
## AIC: 322.13
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_8)
#MODELO 9
modelo_9<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + AREA ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_9)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + AREA, family = poisson(link = "log"),
## data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.3927 -2.7297 -0.8545 2.1744 5.9766
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.4970345 0.0718723 48.656 <2e-16 ***
## PERROS.GSV 0.0197821 0.0021305 9.285 <2e-16 ***
## AREA -0.0001465 0.0007132 -0.205 0.837
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 335.75 on 20 degrees of freedom
## Residual deviance: 235.95 on 18 degrees of freedom
## AIC: 362.66
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_9)
#MODELO 10
modelo_10<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_10)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -10.9614 -0.5849 0.9686 2.8965 7.4785
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.336325 0.064137 -5.244 1.57e-07 ***
## PERROS.GSV 0.005242 0.001839 2.851 0.00436 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 473.20 on 20 degrees of freedom
## Residual deviance: 465.13 on 19 degrees of freedom
## AIC: 589.85
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_10)
#MODELO 11
modelo_11<- glm(PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
summary(modelo_11)
##
## Call:
## glm(formula = PERROS.ENC.SIN.COR ~ PERROS.GSV + KILOMETROS +
## AREA, family = poisson(link = "log"), data = PERROS_SIN.CORREA.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -5.128 -2.350 -1.226 2.732 5.330
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 3.228194 0.084462 38.221 < 2e-16 ***
## PERROS.GSV -0.002116 0.003893 -0.544 0.58670
## KILOMETROS 0.516891 0.077343 6.683 2.34e-11 ***
## AREA -0.002191 0.000824 -2.659 0.00783 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 335.75 on 20 degrees of freedom
## Residual deviance: 189.32 on 17 degrees of freedom
## AIC: 318.03
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_11)
MODELO PARA POBLACION TOTAL PERROS ENCUESTAS Y PERROS STREET VIEW
#MODELO 12
modelo_12<- glm(PERROS.ENC.TOT ~ PERROS.GSV,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_12)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV, family = poisson(link = "log"),
## data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -12.0533 -2.7986 -0.5576 2.7440 8.7241
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.49807 0.04155 108.25 <2e-16 ***
## PERROS.GSV 0.01742 0.00122 14.28 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 803.99 on 20 degrees of freedom
## Residual deviance: 603.58 on 19 degrees of freedom
## AIC: 748.33
##
## Number of Fisher Scoring iterations: 4
#plots residuos
par(mfrow=c(2,2))
plot(modelo_12)
#MODELO 13
modelo_13<- glm(PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_13)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS, family = poisson(link = "log"),
## data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -13.5158 -2.5869 -0.3299 3.2437 7.0984
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.200512 0.051832 81.04 <2e-16 ***
## PERROS.GSV -0.003845 0.002419 -1.59 0.112
## KILOMETROS 0.450237 0.044715 10.07 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 803.99 on 20 degrees of freedom
## Residual deviance: 498.05 on 18 degrees of freedom
## AIC: 644.8
##
## Number of Fisher Scoring iterations: 4
#plots residuos
par(mfrow=c(2,2))
plot(modelo_13)
#MODELO 14
modelo_14<- glm(PERROS.ENC.TOT ~ PERROS.GSV + offset(log(KILOMETROS)) ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_14)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + offset(log(KILOMETROS)),
## family = poisson(link = "log"), data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -11.8924 -3.2150 -0.6327 3.0180 6.4684
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.551463 0.042297 107.607 < 2e-16 ***
## PERROS.GSV -0.006156 0.001247 -4.938 7.87e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 489.89 on 20 degrees of freedom
## Residual deviance: 465.38 on 19 degrees of freedom
## AIC: 610.12
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_14)
#MODELO 15
modelo_15<- glm(PERROS.ENC.TOT ~ PERROS.GSV + AREA ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_15)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + AREA, family = poisson(link = "log"),
## data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -7.416 -3.853 -2.095 3.359 8.402
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.670558 0.045297 103.11 <2e-16 ***
## PERROS.GSV 0.023605 0.001399 16.87 <2e-16 ***
## AREA -0.005226 0.000519 -10.07 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 803.99 on 20 degrees of freedom
## Residual deviance: 490.51 on 18 degrees of freedom
## AIC: 637.25
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_15)
#MODELO 16
modelo_16<- glm(PERROS.ENC.TOT ~ PERROS.GSV + offset(log(AREA)) ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_16)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + offset(log(AREA)),
## family = poisson(link = "log"), data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -21.0423 0.3793 4.8808 6.6599 10.8915
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.662835 0.039761 16.671 < 2e-16 ***
## PERROS.GSV 0.003284 0.001155 2.844 0.00446 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 1788.5 on 20 degrees of freedom
## Residual deviance: 1780.5 on 19 degrees of freedom
## AIC: 1925.2
##
## Number of Fisher Scoring iterations: 5
par(mfrow=c(2,2))
plot(modelo_16)
#MODELO 17
modelo_17<- glm(PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS + AREA ,
family = poisson(link = "log"), data = PERROS_TOTAL.1)
summary(modelo_17)
##
## Call:
## glm(formula = PERROS.ENC.TOT ~ PERROS.GSV + KILOMETROS + AREA,
## family = poisson(link = "log"), data = PERROS_TOTAL.1)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -6.0703 -2.5031 -0.3175 2.1245 6.9463
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 4.2770293 0.0540966 79.063 < 2e-16 ***
## PERROS.GSV -0.0079275 0.0024511 -3.234 0.00122 **
## KILOMETROS 0.7893866 0.0504341 15.652 < 2e-16 ***
## AREA -0.0096618 0.0006601 -14.637 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 803.99 on 20 degrees of freedom
## Residual deviance: 229.45 on 17 degrees of freedom
## AIC: 378.2
##
## Number of Fisher Scoring iterations: 4
par(mfrow=c(2,2))
plot(modelo_17)
