Declaración de variables
año <- 2019:2025
pib <- c(1.25, -8.21, 4.82, 3.90, 3.20, 1.40, 0.90)
fbk <- c(-4.91, -17.18, 12.41, 3.50, 3.00, 3.50, 2.50)
consumo <- c(0.8, -11.1, 7.2, 5.2, 3.5, 1.8, 1.5)
inf<- c(3.99, 3.52, 5.58, 7.80, 5.50, 3.80, 3.80)
des<- c(3.50, 4.65, 4.20, 3.30, 3.10, 3.00, 3.00)
export <- c(2.3, -8.9, 18.5, 9.5, 2.6, 1.2, 1.8)
salarios <- c(1.7, -0.5, 2.7, -0.3, 1.2, 0.5, 0.8)
informal<- c(56.2, 56.5, 55.6, 55.1, 55.8, 54.9, 55.0)
gini<- c(0.451, 0.434, 0.426, 0.423, 0.420, 0.419, 0.418)
balcom <- c(-0.10, -0.95, -0.20, 0.10, 0.30, -0.10, 0.60)
int<- c(7.84, 5.62, 4.58, 8.00, 7.50, 7.25, 7.25)
gasto<- c(1.10, 6.02, 8.28, 10.50, 10.80, 11.00, 11.00)
Creación de tabla para analisis de variables
#Creacion de tabla con los datos
macro_mx <- data.frame(
año,
pib,
fbk,
consumo,
inf,
des,
export,
salarios,
informal,
gini,
balcom,
int,
gasto
)
Correlacion de variables
cor(macro_mx[,-1], use = "pairwise.complete.obs")
## pib fbk consumo inf des export
## pib 1.0000000 0.92434875 0.9954105 0.60805282 -0.567277500 0.84886789
## fbk 0.9243487 1.00000000 0.9513533 0.49073790 -0.448921109 0.87990231
## consumo 0.9954105 0.95135333 1.0000000 0.60975976 -0.530212188 0.88238563
## inf 0.6080528 0.49073790 0.6097598 1.00000000 -0.136694154 0.63742286
## des -0.5672775 -0.44892111 -0.5302122 -0.13669415 1.000000000 -0.08251291
## export 0.8488679 0.87990231 0.8823856 0.63742286 -0.082512909 1.00000000
## salarios 0.5831646 0.60533506 0.5878142 -0.03179607 0.006249633 0.65602058
## informal -0.5801268 -0.68267496 -0.6117677 -0.29382761 0.710692100 -0.39601788
## gini -0.2984826 -0.51505372 -0.3383709 -0.26641250 0.423727941 -0.19368384
## balcom 0.7006099 0.62909684 0.6860184 0.26048767 -0.858435601 0.35079561
## int 0.2351729 -0.05051713 0.1677934 0.17793408 -0.790341353 -0.23841947
## gasto 0.3290977 0.51256446 0.3630936 0.33805718 -0.472523992 0.19515711
## salarios informal gini balcom int
## pib 0.583164583 -0.58012676 -0.29848260 0.7006099 0.23517289
## fbk 0.605335065 -0.68267496 -0.51505372 0.6290968 -0.05051713
## consumo 0.587814215 -0.61176770 -0.33837088 0.6860184 0.16779338
## inf -0.031796066 -0.29382761 -0.26641250 0.2604877 0.17793408
## des 0.006249633 0.71069210 0.42372794 -0.8584356 -0.79034135
## export 0.656020580 -0.39601788 -0.19368384 0.3507956 -0.23841947
## salarios 1.000000000 0.05206584 0.18222450 0.2551050 -0.34542088
## informal 0.052065836 1.00000000 0.73613962 -0.6663025 -0.31190401
## gini 0.182224500 0.73613962 1.00000000 -0.4626328 0.01603595
## balcom 0.255104951 -0.66630247 -0.46263282 1.0000000 0.55177517
## int -0.345420881 -0.31190401 0.01603595 0.5517752 1.00000000
## gasto -0.233492284 -0.75818715 -0.99364311 0.4862418 0.07162353
## gasto
## pib 0.32909768
## fbk 0.51256446
## consumo 0.36309363
## inf 0.33805718
## des -0.47252399
## export 0.19515711
## salarios -0.23349228
## informal -0.75818715
## gini -0.99364311
## balcom 0.48624184
## int 0.07162353
## gasto 1.00000000
# Seleccionamos solo las variables numéricas (sin el año)
vars_cor <- macro_mx[ , -1]
# Matriz de correlaciones de Pearson
cor_mat <- cor(vars_cor, use = "pairwise.complete.obs", method = "pearson")
Matriz de correlaciones
library(corrplot)
## corrplot 0.95 loaded
library(GGally)
## Cargando paquete requerido: ggplot2
## Registered S3 method overwritten by 'GGally':
## method from
## +.gg ggplot2
ggpairs(vars_cor, lower = list(continuous = "smooth"),
diag = list(continuous = "bar"), axisLabels = "none")
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value `binwidth`.
Grafo de correlaciones
library(qgraph)
vars_cor <- macro_mx[, -1]
cor_mat <- cor(vars_cor, use = "pairwise.complete.obs")
qgraph(
cor_mat,
layout = "spring",
minimum = 0.3, # mostrar correlaciones mayores a 0.3
edge.color = "black",
labels = colnames(vars_cor),
color = "white",
vsize = 7
)
