Performs calculations to the output of sgcca to make it easier to retrieve the information about the result.
Value
A vector with the correlation between components, AVE (both inner and outer), the canonical correlation, the weight in the design matrix, and the number of interactions that exists.
Details
Calculates the correlations between the canonical dimensions, calculates the canonical correlations, returns also the weight of each link of the model used, all of this in a tidy way.
Examples
data("Russett", package = "RGCCA")
X_agric <- as.matrix(Russett[, c("gini", "farm", "rent")])
X_ind <- as.matrix(Russett[, c("gnpr", "labo")])
X_polit <- as.matrix(Russett[ , c("inst", "ecks", "death", "demostab",
"dictator")])
A <- list(X_agric, X_ind, X_polit)
A <- lapply(A, function(x) scale2(x, bias = TRUE))
C <- matrix(c(0, 0, 1, 0, 0, 1, 1, 1, 0), 3, 3)
out <- RGCCA::rgcca(A, C, tau =rep(0, 3), scheme = "factorial",
scale = FALSE, verbose = TRUE)
#> Computation of the RGCCA block components based on the factorial scheme
#> Shrinkage intensity paramaters are chosen manually
#> Iter: 1 Fit: 1.83005079 Dif: 0.38803933
#> Iter: 2 Fit: 1.92003517 Dif: 0.08998438
#> Iter: 3 Fit: 1.93192442 Dif: 0.01188925
#> Iter: 4 Fit: 1.93354278 Dif: 0.00161836
#> Iter: 5 Fit: 1.93376871 Dif: 0.00022593
#> Iter: 6 Fit: 1.93380060 Dif: 0.00003189
#> Iter: 7 Fit: 1.93380512 Dif: 0.00000452
#> Iter: 8 Fit: 1.93380576 Dif: 0.00000064
#> Iter: 9 Fit: 1.93380585 Dif: 0.00000009
#> Iter: 10 Fit: 1.93380586 Dif: 0.00000001
#> Iter: 11 Fit: 1.93380586 Dif: 0.00000000
#> The RGCCA algorithm converged to a stationary point after 10 iterations
analyze(out)
#> vs12 vs13 vs23 AVE_inner AVE_outer cc1 var12
#> 0.4875286 -0.6270914 -0.7574030 0.4834515 0.4793766 0.9669029 0.0000000
#> var13 var23 weights
#> 1.0000000 1.0000000 2.0000000