Canonical Corelation

Canonical Corelation (cca) merupakan metode korelasi untuk dua dataset

library(CCA)

## Warning: package 'CCA' was built under R version 4.3.3

## Loading required package: fda

## Loading required package: splines

## Loading required package: fds

## Warning: package 'fds' was built under R version 4.3.3

## Loading required package: rainbow

## Warning: package 'rainbow' was built under R version 4.3.3

## Loading required package: MASS

## Loading required package: pcaPP

## Warning: package 'pcaPP' was built under R version 4.3.3

## Loading required package: RCurl

## Warning: package 'RCurl' was built under R version 4.3.3

## Loading required package: deSolve

## Warning: package 'deSolve' was built under R version 4.3.3

## 
## Attaching package: 'fda'

## The following object is masked from 'package:graphics':
## 
##     matplot

## Loading required package: fields

## Warning: package 'fields' was built under R version 4.3.3

## Loading required package: spam

## Warning: package 'spam' was built under R version 4.3.3

## Spam version 2.11-1 (2025-01-20) is loaded.
## Type 'help( Spam)' or 'demo( spam)' for a short introduction 
## and overview of this package.
## Help for individual functions is also obtained by adding the
## suffix '.spam' to the function name, e.g. 'help( chol.spam)'.

## 
## Attaching package: 'spam'

## The following objects are masked from 'package:base':
## 
##     backsolve, forwardsolve

## Loading required package: viridisLite

## 
## Try help(fields) to get started.

library(CCP)
library(readr)

## Warning: package 'readr' was built under R version 4.3.3

library(readxl)

## Warning: package 'readxl' was built under R version 4.3.2

data yang digunkan merupakan data pdrb, pad, dau,jumlah penduduk, biaya rutin dan biaya modal provinsi indonesia data diambil dari:

https://sulut.bps.go.id/id/statistics-table/2/OTU4IzI=/jumlah-penduduk-menurut-provinsi-di-indonesia.html https://djpk.kemenkeu.go.id/portal/data/apbd?periode=12&tahun=2024&provinsi=32&pemda=00 https://djpk.kemenkeu.go.id/wp-content/uploads/2023/09/Rincian-Alokasi-DAU-DBH-TA-2024.pdf

dat=read_excel("kmsv2.xlsx")

data dibagi menjadi variabel pemasukan (pdrb, pad, dau) dan variabel pengeluaran (jumlah peduduk, biaya rutin, biaya modal)

tunel=dat[c("pdrb","pad","DAU")]

chungus=dat[c("penduduk","boperasi","belanjamodal")]

hasil cca

chese <- cc(tunel, chungus)

chese$cor

## [1] 0.9969015 0.8625324 0.3096998

chese[3:4]

## $xcoef
##              [,1]          [,2]          [,3]
## pdrb 2.367680e-09 -4.195291e-06  2.459547e-05
## pad  9.575304e-05 -2.142610e-05 -1.192806e-04
## DAU  1.669328e-10  9.758376e-10  1.212904e-09
## 
## $ycoef
##                      [,1]          [,2]          [,3]
## penduduk     2.992883e-05  8.531396e-05  7.719211e-05
## boperasi     6.650048e-05 -4.567455e-05 -2.785542e-04
## belanjamodal 5.906648e-05 -1.608549e-04  1.359805e-03

visualisasi cca

gage <- as.data.frame(chese$scores$xscores)
mbt <- as.data.frame(chese$scores$yscores)

n <- nrow(tunel)
p <- ncol(tunel)
q <- ncol(chungus)

pea <- p.asym(chese$cor, n, p, q, tstat = "Wilks")

## Wilks' Lambda, using F-approximation (Rao's F):
##                 stat     approx df1      df2      p.value
## 1 to 3:  0.001432253 104.281467   9 68.29525 0.000000e+00
## 2 to 3:  0.231480191  15.637768   4 58.00000 9.791640e-09
## 3 to 3:  0.904086022   3.182683   1 30.00000 8.454143e-02

loadings_health <- cor(tunel, gage)
loadings_mental <- cor(chungus, mbt)

plot(gage[,1], mbt[,1],
     xlab = "pemasukan Canonical Variate 1",
     ylab = "pengeluaran Canonical Variate 1",
     main = "Canonical Correlation between pemasukan and pengeluaran")