Ejercicios Sábado
Shamanta
2024-06-15
ANÁLISIS FACTORIAL
library(rio)
dataprincipal=import("criminal_eap.xlsx")str(dataprincipal)## 'data.frame': 140 obs. of 10 variables:
## $ Country : chr "Afghanistan" "Albania" "Algeria" "Angola" ...
## $ Year : chr "2022" "2022" "2022" "2022" ...
## $ Factor 8: Criminal Justice : num 0.261 0.4 0.397 0.346 0.519 ...
## $ 8.1 Criminal investigation system is effective : num 0.298 0.424 0.266 0.354 0.456 ...
## $ 8.2 Criminal adjudication system is timely and effective : num 0.412 0.362 0.438 0.353 0.503 ...
## $ 8.3 Correctional system is effective in reducing criminal behavior: num 0.212 0.37 0.466 0.235 0.408 ...
## $ 8.4 Criminal system is impartial : num 0.169 0.493 0.567 0.376 0.457 ...
## $ 8.5 Criminal system is free of corruption : num 0.27 0.334 0.42 0.497 0.692 ...
## $ 8.6 Criminal system is free of improper government influence : num 0.186 0.303 0.153 0.292 0.546 ...
## $ 8.7. Due process of the law and rights of the accused : num 0.278 0.515 0.471 0.316 0.574 ...set.seed(123)names(dataprincipal)## [1] "Country"
## [2] "Year"
## [3] "Factor 8: Criminal Justice"
## [4] "8.1 Criminal investigation system is effective"
## [5] "8.2 Criminal adjudication system is timely and effective"
## [6] "8.3 Correctional system is effective in reducing criminal behavior"
## [7] "8.4 Criminal system is impartial"
## [8] "8.5 Criminal system is free of corruption"
## [9] "8.6 Criminal system is free of improper government influence"
## [10] "8.7. Due process of the law and rights of the accused"library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, uniondontselect=c("Country","Year","Factor 8: Criminal Justice")
select=setdiff(names(dataprincipal),dontselect)
data=dataprincipal[,select]
# usaremos:
library(magrittr)
head(data,10)%>%
rmarkdown::paged_table()library(psych)
library(corpcor)corMatrix=polycor::hetcor(data)$correlationsround(corMatrix,2)## 8.1 Criminal investigation system is effective
## 8.1 Criminal investigation system is effective 1.00
## 8.2 Criminal adjudication system is timely and effective 0.82
## 8.3 Correctional system is effective in reducing criminal behavior 0.79
## 8.4 Criminal system is impartial 0.62
## 8.5 Criminal system is free of corruption 0.80
## 8.6 Criminal system is free of improper government influence 0.65
## 8.7. Due process of the law and rights of the accused 0.78
## 8.2 Criminal adjudication system is timely and effective
## 8.1 Criminal investigation system is effective 0.82
## 8.2 Criminal adjudication system is timely and effective 1.00
## 8.3 Correctional system is effective in reducing criminal behavior 0.84
## 8.4 Criminal system is impartial 0.68
## 8.5 Criminal system is free of corruption 0.78
## 8.6 Criminal system is free of improper government influence 0.66
## 8.7. Due process of the law and rights of the accused 0.79
## 8.3 Correctional system is effective in reducing criminal behavior
## 8.1 Criminal investigation system is effective 0.79
## 8.2 Criminal adjudication system is timely and effective 0.84
## 8.3 Correctional system is effective in reducing criminal behavior 1.00
## 8.4 Criminal system is impartial 0.72
## 8.5 Criminal system is free of corruption 0.79
## 8.6 Criminal system is free of improper government influence 0.64
## 8.7. Due process of the law and rights of the accused 0.85
## 8.4 Criminal system is impartial
## 8.1 Criminal investigation system is effective 0.62
## 8.2 Criminal adjudication system is timely and effective 0.68
## 8.3 Correctional system is effective in reducing criminal behavior 0.72
## 8.4 Criminal system is impartial 1.00
## 8.5 Criminal system is free of corruption 0.71
## 8.6 Criminal system is free of improper government influence 0.69
## 8.7. Due process of the law and rights of the accused 0.80
## 8.5 Criminal system is free of corruption
## 8.1 Criminal investigation system is effective 0.80
## 8.2 Criminal adjudication system is timely and effective 0.78
## 8.3 Correctional system is effective in reducing criminal behavior 0.79
## 8.4 Criminal system is impartial 0.71
## 8.5 Criminal system is free of corruption 1.00
## 8.6 Criminal system is free of improper government influence 0.82
## 8.7. Due process of the law and rights of the accused 0.87
## 8.6 Criminal system is free of improper government influence
## 8.1 Criminal investigation system is effective 0.65
## 8.2 Criminal adjudication system is timely and effective 0.66
## 8.3 Correctional system is effective in reducing criminal behavior 0.64
## 8.4 Criminal system is impartial 0.69
## 8.5 Criminal system is free of corruption 0.82
## 8.6 Criminal system is free of improper government influence 1.00
## 8.7. Due process of the law and rights of the accused 0.81
## 8.7. Due process of the law and rights of the accused
## 8.1 Criminal investigation system is effective 0.78
## 8.2 Criminal adjudication system is timely and effective 0.79
## 8.3 Correctional system is effective in reducing criminal behavior 0.85
## 8.4 Criminal system is impartial 0.80
## 8.5 Criminal system is free of corruption 0.87
## 8.6 Criminal system is free of improper government influence 0.81
## 8.7. Due process of the law and rights of the accused 1.00library(ggcorrplot)## Warning: package 'ggcorrplot' was built under R version 4.3.3## Loading required package: ggplot2##
## Attaching package: 'ggplot2'## The following objects are masked from 'package:psych':
##
## %+%, alphaggcorrplot(corMatrix)
library(psych)
psych::KMO(corMatrix) ## Kaiser-Meyer-Olkin factor adequacy
## Call: psych::KMO(r = corMatrix)
## Overall MSA = 0.91
## MSA for each item =
## 8.1 Criminal investigation system is effective
## 0.92
## 8.2 Criminal adjudication system is timely and effective
## 0.92
## 8.3 Correctional system is effective in reducing criminal behavior
## 0.90
## 8.4 Criminal system is impartial
## 0.95
## 8.5 Criminal system is free of corruption
## 0.91
## 8.6 Criminal system is free of improper government influence
## 0.90
## 8.7. Due process of the law and rights of the accused
## 0.89correlation_matrix <- cor(data, use = "pairwise.complete.obs")
#valor KMO
kmo_resultados <- KMO(correlation_matrix)
kmo_resultados## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = correlation_matrix)
## Overall MSA = 0.91
## MSA for each item =
## 8.1 Criminal investigation system is effective
## 0.92
## 8.2 Criminal adjudication system is timely and effective
## 0.92
## 8.3 Correctional system is effective in reducing criminal behavior
## 0.90
## 8.4 Criminal system is impartial
## 0.95
## 8.5 Criminal system is free of corruption
## 0.91
## 8.6 Criminal system is free of improper government influence
## 0.90
## 8.7. Due process of the law and rights of the accused
## 0.89#BARRET
cortest.bartlett(corMatrix,n=nrow(data))$p.value>0.05## [1] FALSElibrary(matrixcalc)##
## Attaching package: 'matrixcalc'## The following object is masked from 'package:corpcor':
##
## is.positive.definiteis.singular.matrix(corMatrix)## [1] FALSEvariables latentes que puede dar el analisis
fa.parallel(data, fa = 'fa',correct = T,plot = F) #salen muchos errores## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Parallel analysis suggests that the number of factors = 1 and the number of components = NAefa_result <- fa(data, nfactors = 1, rotate = "varimax", fm = "ml")
print(efa_result)## Factor Analysis using method = ml
## Call: fa(r = data, nfactors = 1, rotate = "varimax", fm = "ml")
## Standardized loadings (pattern matrix) based upon correlation matrix
## ML1 h2
## 8.1 Criminal investigation system is effective 0.85 0.73
## 8.2 Criminal adjudication system is timely and effective 0.86 0.75
## 8.3 Correctional system is effective in reducing criminal behavior 0.89 0.80
## 8.4 Criminal system is impartial 0.81 0.65
## 8.5 Criminal system is free of corruption 0.92 0.84
## 8.6 Criminal system is free of improper government influence 0.82 0.67
## 8.7. Due process of the law and rights of the accused 0.95 0.90
## u2 com
## 8.1 Criminal investigation system is effective 0.27 1
## 8.2 Criminal adjudication system is timely and effective 0.25 1
## 8.3 Correctional system is effective in reducing criminal behavior 0.20 1
## 8.4 Criminal system is impartial 0.35 1
## 8.5 Criminal system is free of corruption 0.16 1
## 8.6 Criminal system is free of improper government influence 0.33 1
## 8.7. Due process of the law and rights of the accused 0.10 1
##
## ML1
## SS loadings 5.33
## Proportion Var 0.76
##
## Mean item complexity = 1
## Test of the hypothesis that 1 factor is sufficient.
##
## df null model = 21 with the objective function = 7.87 with Chi Square = 1068.41
## df of the model are 14 and the objective function was 0.65
##
## The root mean square of the residuals (RMSR) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## The harmonic n.obs is 140 with the empirical chi square 11.45 with prob < 0.65
## The total n.obs was 140 with Likelihood Chi Square = 87.5 with prob < 1.1e-12
##
## Tucker Lewis Index of factoring reliability = 0.894
## RMSEA index = 0.194 and the 90 % confidence intervals are 0.156 0.234
## BIC = 18.32
## Fit based upon off diagonal values = 1
## Measures of factor score adequacy
## ML1
## Correlation of (regression) scores with factors 0.98
## Multiple R square of scores with factors 0.97
## Minimum correlation of possible factor scores 0.93library(GPArotation)## Warning: package 'GPArotation' was built under R version 4.3.3##
## Attaching package: 'GPArotation'## The following objects are masked from 'package:psych':
##
## equamax, variminresfa <- fa(data,
nfactors = 1,
cor = 'mixed',
rotate = "varimax", #oblimin?
fm="minres")
print(resfa$loadings)##
## Loadings:
## MR1
## 8.1 Criminal investigation system is effective 0.852
## 8.2 Criminal adjudication system is timely and effective 0.874
## 8.3 Correctional system is effective in reducing criminal behavior 0.892
## 8.4 Criminal system is impartial 0.797
## 8.5 Criminal system is free of corruption 0.922
## 8.6 Criminal system is free of improper government influence 0.807
## 8.7. Due process of the law and rights of the accused 0.952
##
## MR1
## SS loadings 5.328
## Proportion Var 0.761fa.diagram(resfa,main = "Resultados del EFA")
#valores que aportaron más
sort(resfa$communality)## 8.4 Criminal system is impartial
## 0.6350573
## 8.6 Criminal system is free of improper government influence
## 0.6518719
## 8.1 Criminal investigation system is effective
## 0.7266429
## 8.2 Criminal adjudication system is timely and effective
## 0.7638836
## 8.3 Correctional system is effective in reducing criminal behavior
## 0.7953470
## 8.5 Criminal system is free of corruption
## 0.8494171
## 8.7. Due process of the law and rights of the accused
## 0.9056341valores adecuados para el analisis factorial
# matriz de correlación
correlation_matrix1 <- cor(data, use = "pairwise.complete.obs")
# Redondear la matriz de correlación a 2 decimales
rounded_correlation_matrix1 <- round(correlation_matrix1, 2)
#matriz redondeada
print(rounded_correlation_matrix1)## 8.1 Criminal investigation system is effective
## 8.1 Criminal investigation system is effective 1.00
## 8.2 Criminal adjudication system is timely and effective 0.82
## 8.3 Correctional system is effective in reducing criminal behavior 0.79
## 8.4 Criminal system is impartial 0.62
## 8.5 Criminal system is free of corruption 0.80
## 8.6 Criminal system is free of improper government influence 0.65
## 8.7. Due process of the law and rights of the accused 0.78
## 8.2 Criminal adjudication system is timely and effective
## 8.1 Criminal investigation system is effective 0.82
## 8.2 Criminal adjudication system is timely and effective 1.00
## 8.3 Correctional system is effective in reducing criminal behavior 0.84
## 8.4 Criminal system is impartial 0.68
## 8.5 Criminal system is free of corruption 0.78
## 8.6 Criminal system is free of improper government influence 0.66
## 8.7. Due process of the law and rights of the accused 0.79
## 8.3 Correctional system is effective in reducing criminal behavior
## 8.1 Criminal investigation system is effective 0.79
## 8.2 Criminal adjudication system is timely and effective 0.84
## 8.3 Correctional system is effective in reducing criminal behavior 1.00
## 8.4 Criminal system is impartial 0.72
## 8.5 Criminal system is free of corruption 0.79
## 8.6 Criminal system is free of improper government influence 0.64
## 8.7. Due process of the law and rights of the accused 0.85
## 8.4 Criminal system is impartial
## 8.1 Criminal investigation system is effective 0.62
## 8.2 Criminal adjudication system is timely and effective 0.68
## 8.3 Correctional system is effective in reducing criminal behavior 0.72
## 8.4 Criminal system is impartial 1.00
## 8.5 Criminal system is free of corruption 0.71
## 8.6 Criminal system is free of improper government influence 0.69
## 8.7. Due process of the law and rights of the accused 0.80
## 8.5 Criminal system is free of corruption
## 8.1 Criminal investigation system is effective 0.80
## 8.2 Criminal adjudication system is timely and effective 0.78
## 8.3 Correctional system is effective in reducing criminal behavior 0.79
## 8.4 Criminal system is impartial 0.71
## 8.5 Criminal system is free of corruption 1.00
## 8.6 Criminal system is free of improper government influence 0.82
## 8.7. Due process of the law and rights of the accused 0.87
## 8.6 Criminal system is free of improper government influence
## 8.1 Criminal investigation system is effective 0.65
## 8.2 Criminal adjudication system is timely and effective 0.66
## 8.3 Correctional system is effective in reducing criminal behavior 0.64
## 8.4 Criminal system is impartial 0.69
## 8.5 Criminal system is free of corruption 0.82
## 8.6 Criminal system is free of improper government influence 1.00
## 8.7. Due process of the law and rights of the accused 0.81
## 8.7. Due process of the law and rights of the accused
## 8.1 Criminal investigation system is effective 0.78
## 8.2 Criminal adjudication system is timely and effective 0.79
## 8.3 Correctional system is effective in reducing criminal behavior 0.85
## 8.4 Criminal system is impartial 0.80
## 8.5 Criminal system is free of corruption 0.87
## 8.6 Criminal system is free of improper government influence 0.81
## 8.7. Due process of the law and rights of the accused 1.00#valor KMO
kmo_result <- KMO(correlation_matrix1)
print(kmo_result)## Kaiser-Meyer-Olkin factor adequacy
## Call: KMO(r = correlation_matrix1)
## Overall MSA = 0.91
## MSA for each item =
## 8.1 Criminal investigation system is effective
## 0.92
## 8.2 Criminal adjudication system is timely and effective
## 0.92
## 8.3 Correctional system is effective in reducing criminal behavior
## 0.90
## 8.4 Criminal system is impartial
## 0.95
## 8.5 Criminal system is free of corruption
## 0.91
## 8.6 Criminal system is free of improper government influence
## 0.90
## 8.7. Due process of the law and rights of the accused
## 0.89fa_parallel <- fa.parallel(data, fa = 'fa', correct = TRUE, plot = FALSE)## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.
## Warning in fa.stats(r = r, f = f, phi = phi, n.obs = n.obs, np.obs = np.obs, :
## The estimated weights for the factor scores are probably incorrect. Try a
## different factor score estimation method.## Warning in fac(r = r, nfactors = nfactors, n.obs = n.obs, rotate = rotate, : An
## ultra-Heywood case was detected. Examine the results carefully## Parallel analysis suggests that the number of factors = 1 and the number of components = NAn_factors <- fa_parallel$nfact
efa_result <- fa(data, nfactors = n_factors, rotate = "varimax", fm = "ml", scores = "regression")
print(efa_result)## Factor Analysis using method = ml
## Call: fa(r = data, nfactors = n_factors, rotate = "varimax", scores = "regression",
## fm = "ml")
## Standardized loadings (pattern matrix) based upon correlation matrix
## ML1 h2
## 8.1 Criminal investigation system is effective 0.85 0.73
## 8.2 Criminal adjudication system is timely and effective 0.86 0.75
## 8.3 Correctional system is effective in reducing criminal behavior 0.89 0.80
## 8.4 Criminal system is impartial 0.81 0.65
## 8.5 Criminal system is free of corruption 0.92 0.84
## 8.6 Criminal system is free of improper government influence 0.82 0.67
## 8.7. Due process of the law and rights of the accused 0.95 0.90
## u2 com
## 8.1 Criminal investigation system is effective 0.27 1
## 8.2 Criminal adjudication system is timely and effective 0.25 1
## 8.3 Correctional system is effective in reducing criminal behavior 0.20 1
## 8.4 Criminal system is impartial 0.35 1
## 8.5 Criminal system is free of corruption 0.16 1
## 8.6 Criminal system is free of improper government influence 0.33 1
## 8.7. Due process of the law and rights of the accused 0.10 1
##
## ML1
## SS loadings 5.33
## Proportion Var 0.76
##
## Mean item complexity = 1
## Test of the hypothesis that 1 factor is sufficient.
##
## df null model = 21 with the objective function = 7.87 with Chi Square = 1068.41
## df of the model are 14 and the objective function was 0.65
##
## The root mean square of the residuals (RMSR) is 0.04
## The df corrected root mean square of the residuals is 0.05
##
## The harmonic n.obs is 140 with the empirical chi square 11.45 with prob < 0.65
## The total n.obs was 140 with Likelihood Chi Square = 87.5 with prob < 1.1e-12
##
## Tucker Lewis Index of factoring reliability = 0.894
## RMSEA index = 0.194 and the 90 % confidence intervals are 0.156 0.234
## BIC = 18.32
## Fit based upon off diagonal values = 1
## Measures of factor score adequacy
## ML1
## Correlation of (regression) scores with factors 0.98
## Multiple R square of scores with factors 0.97
## Minimum correlation of possible factor scores 0.93CONCLUSIÓN: El unico factor sí explica un 76% de la varianza observada por lo que sale en el proportion var.
REGRESIÓN LOGÍSTICA
baselog=import("Ceplan.xlsx - Hoja 1 (1).csv")Ceplan = read.csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vSV8h6jh5O6qlzs2LADiOCgrNEFqaMbUhjenWitP2iRn89Qt09mOLTKOgZq3DEq5Q/pub?output=csv")
library(dplyr)
Ceplan2 = Ceplan%>%filter(TIPO == "Provincia")%>%dplyr::select(c(4:8))
Ceplan2$IVIA = gsub(",", ".", Ceplan2$IVIA)
Ceplan2$IDE = gsub(",", ".", Ceplan2$IDE)
Ceplan2$ABASTOS = gsub(",", ".", Ceplan2$ABASTOS)
Ceplan2$IDH = gsub(",", ".", Ceplan2$IDH)
Ceplan2$POBREZA = gsub(",", ".", Ceplan2$POBREZA)
Ceplan2 = as.data.frame(lapply(Ceplan2, as.numeric))## Warning in lapply(Ceplan2, as.numeric): NAs introducidos por coerciónCeplan2 = Ceplan2[complete.cases(Ceplan2),]
Ceplan2$IDH_cat = ifelse(Ceplan2$IDH < 0.430, 0, 1)
Ceplan2$IDH_cat = factor(Ceplan2$IDH_cat, levels = c(0,1), labels = c("No desarrollo humano", "Desarrollo humano"))HIPOTESIS: El tener desarrollo humano (IDH_CAT) está determinado por el número de mercados de abastos (ABASTOS), la vulnerabilidad alimentaria (IVIA), el Índice de Densidad del Estado (IDE) y el porcentaje de la población en pobreza total (POBREZA)
library(dplyr)
library(psych)
library(corpcor)
library(car)## Warning: package 'car' was built under R version 4.3.3## Loading required package: carData## Warning: package 'carData' was built under R version 4.3.3##
## Attaching package: 'car'## The following object is masked from 'package:psych':
##
## logit## The following object is masked from 'package:dplyr':
##
## recode# Ajustar el modelo de regresión logística
logistic_model <- glm(IDH_cat ~ IVIA + IDE + ABASTOS + POBREZA, data = Ceplan2, family = binomial)## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurred# Resumen del modelo
summary(logistic_model)##
## Call:
## glm(formula = IDH_cat ~ IVIA + IDE + ABASTOS + POBREZA, family = binomial,
## data = Ceplan2)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 28.55107 7.77533 3.672 0.000241 ***
## IVIA -42.67810 10.24112 -4.167 3.08e-05 ***
## IDE -7.28485 5.63664 -1.292 0.196215
## ABASTOS 0.31870 0.17667 1.804 0.071252 .
## POBREZA -0.06472 0.05893 -1.098 0.272082
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 253.643 on 182 degrees of freedom
## Residual deviance: 46.614 on 178 degrees of freedom
## AIC: 56.614
##
## Number of Fisher Scoring iterations: 9# Calcular pseudo-R² (Nagelkerke R²)
nagelkerke_r2 <- function(logistic_model) {
ll.null <- logistic_model$null.deviance / -2
ll.proposed <- logistic_model$deviance / -2
r2_mcfadden <- 1 - (logistic_model$deviance / logistic_model$null.deviance)
r2_nagelkerke <- r2_mcfadden / (1 - (exp(2 * ll.null / length(logistic_model$fitted.values))))
return(r2_nagelkerke)
}
nagelkerke_r2_value <- nagelkerke_r2(logistic_model)
print(paste("Nagelkerke R²:", round(nagelkerke_r2_value, 2)))## [1] "Nagelkerke R²: 1.09"# Evaluar multicolinealidad con VIF
vif_values <- vif(logistic_model)
print(vif_values)## IVIA IDE ABASTOS POBREZA
## 1.298690 1.262854 1.116541 1.079062### first hypothesis
hipolog=formula(IDH_cat ~ IVIA + IDE + ABASTOS + POBREZA)
#regression
rlog1=glm(hipolog, data=Ceplan2,family = binomial)## Warning: glm.fit: fitted probabilities numerically 0 or 1 occurredmodelrl=list('IDHdeterm'=rlog1)