Compare TNA Clusters with Comprehensive Metrics
Usage
# S3 method for class 'group_tna'
compare(x, i = 1L, j = 2L, scaling = "none", ...)Arguments
- x
A
group_tnaobject.- i
An
integerindex or the name of the principal cluster as acharacterstring.- j
An
integerindex or the name of the secondary cluster as acharacterstring.- scaling
See
compare.tna().- ...
Additional arguments passed to
compare.tna().
Value
A tna_comparison object. See compare.tna() for details.
See also
Model comparison functions
compare(),
plot.tna_comparison(),
plot_compare(),
plot_compare.group_tna(),
print.tna_comparison()
Examples
model <- group_model(engagement_mmm)
compare(model, i = 1, j = 2)
#> Warning: There was 1 warning in `dplyr::summarize()`.
#> ℹ In argument: `correlation = corr_fun(x, y)`.
#> ℹ In group 1: `centrality = "Betweenness"`.
#> Caused by warning in `stats::cor()`:
#> ! the standard deviation is zero
#> Edge difference metrics
#> # A tibble: 9 × 16
#> source target weight_x weight_y raw_difference absolute_difference
#> <fct> <fct> <dbl> <dbl> <dbl> <dbl>
#> 1 Active Active 0.706 0.492 0.214 0.214
#> 2 Average Active 0.513 0.325 0.188 0.188
#> 3 Disengaged Active 0.333 0.333 0 0
#> 4 Active Average 0.294 0.442 -0.148 0.148
#> 5 Average Average 0.460 0.586 -0.126 0.126
#> 6 Disengaged Average 0.381 0.573 -0.192 0.192
#> 7 Active Disengaged 0 0.0657 -0.0657 0.0657
#> 8 Average Disengaged 0.0268 0.0890 -0.0622 0.0622
#> 9 Disengaged Disengaged 0.286 0.0933 0.192 0.192
#> # ℹ 10 more variables: squared_difference <dbl>, relative_difference <dbl>,
#> # similarity_strength_index <dbl>, difference_index <dbl>,
#> # rank_difference <dbl>, percentile_difference <dbl>,
#> # logarithmic_ratio <dbl>, standardized_weight_x <dbl>,
#> # standardized_weight_y <dbl>, standardized_score_inflation <dbl>
#>
#> Summary metrics of differences
#> # A tibble: 24 × 3
#> category metric value
#> <chr> <chr> <dbl>
#> 1 Weight Deviations Mean Abs. Diff. 0.132
#> 2 Weight Deviations Median Abs. Diff. 0.148
#> 3 Weight Deviations RMS Diff. 0.150
#> 4 Weight Deviations Max Abs. Diff. 0.214
#> 5 Weight Deviations Rel. Mean Abs. Diff. 0.396
#> 6 Weight Deviations CV Ratio 1.07
#> 7 Correlations Pearson 0.732
#> 8 Correlations Spearman 0.733
#> 9 Correlations Kendall 0.611
#> 10 Correlations Distance 0.596
#> # ℹ 14 more rows
#>
#> Network metrics
#> # A tibble: 13 × 3
#> metric x y
#> <chr> <dbl> <dbl>
#> 1 Node Count 3 e+ 0 3
#> 2 Edge Count 8 e+ 0 9
#> 3 Network Density 1 e+ 0 1
#> 4 Mean Distance 2.86e- 1 0.305
#> 5 Mean Out-Strength 1 e+ 0 1
#> 6 SD Out-Strength 6.31e- 1 0.689
#> 7 Mean In-Strength 1 e+ 0 1
#> 8 SD In-Strength 7.85e-17 0
#> 9 Mean Out-Degree 2.67e+ 0 3
#> 10 SD Out-Degree 5.77e- 1 0
#> 11 Centralization (Out-Degree) 2.5 e- 1 0
#> 12 Centralization (In-Degree) 2.5 e- 1 0
#> 13 Reciprocity 8 e- 1 1
#>
#> Centrality differences
#> # A tibble: 27 × 5
#> state centrality x y difference
#> <fct> <chr> <dbl> <dbl> <dbl>
#> 1 Active OutStrength 0.294 0.508 -0.214
#> 2 Active InStrength 0.847 0.658 0.188
#> 3 Active ClosenessIn 1.44 1.52 -0.0770
#> 4 Active ClosenessOut 1.63 1.97 -0.343
#> 5 Active Closeness 1.63 4.54 -2.91
#> 6 Active Betweenness 0 0 0
#> 7 Active BetweennessRSP 20 4 16
#> 8 Active Diffusion 0.503 0.885 -0.383
#> 9 Active Clustering 0.408 0.662 -0.255
#> 10 Average OutStrength 0.540 0.414 0.126
#> # ℹ 17 more rows
#>
#> Centrality correlations
#> # A tibble: 9 × 3
#> centrality Centrality correlation
#> <chr> <chr> <dbl>
#> 1 Betweenness Betweenness NA
#> 2 BetweennessRSP BetweennessRSP 0.980
#> 3 Closeness Closeness 0.198
#> 4 ClosenessIn ClosenessIn 0.994
#> 5 ClosenessOut ClosenessOut 0.865
#> 6 Clustering Clustering 0.813
#> 7 Diffusion Diffusion 0.812
#> 8 InStrength InStrength 0.811
#> 9 OutStrength OutStrength 0.695