Correlation cluster summary for a LifeCalc-style dataset — lifecalc_cor

Returns a tidy data frame of pairwise correlations for the predefined variable clusters in the lifecalc dataset. Useful as a quick diagnostic before fitting multivariate models — high within-cluster correlations signal multicollinearity that will inflate VIF and destabilise OLS coefficient estimates.

Usage

lifecalc_cor_clusters(data = lifecalc)

Arguments

data: A data frame with the same column names as lifecalc. Defaults to the bundled lifecalc dataset.

Value

A data frame with columns cluster, var1, var2, and r (Pearson correlation), sorted by descending |r| within each cluster.

Examples

data(lifecalc)
clusters <- lifecalc_cor_clusters(lifecalc)
head(clusters, 10)
#>       cluster             var1             var2         r
#> 1  employment  EmploymentScore ConsumptionScore 0.8304135
#> 2   education   EducationScore    LiteracyScore 0.8205925
#> 3  employment  EmploymentScore    MobilityScore 0.8006234
#> 4  employment  EmploymentScore     NetworkScore 0.7838297
#> 5   education   EducationScore   CuriosityScore 0.7290875
#> 6  employment ConsumptionScore    MobilityScore 0.7243490
#> 7      health     MedicalScore    RecoveryScore 0.7163789
#> 8  employment     NetworkScore ConsumptionScore 0.7001022
#> 9  employment     NetworkScore    MobilityScore 0.6956512
#> 10     health     MedicalScore       SleepScore 0.6955574

# High correlations within the education cluster
subset(clusters, cluster == "education")
#>      cluster           var1              var2         r
#> 2  education EducationScore     LiteracyScore 0.8205925
#> 5  education EducationScore    CuriosityScore 0.7290875
#> 11 education EducationScore VerificationScore 0.6778783
#> 14 education  LiteracyScore    CuriosityScore 0.6279810
#> 15 education  LiteracyScore VerificationScore 0.5686698
#> 20 education CuriosityScore VerificationScore 0.5145045