`itemStability` for Singleton Communities
Closed this issue · 1 comments
AlexChristensen commented
Current problem
o itemStability
will not produce stability statistics for variable that are placed in singleton communities (i.e., NA
)
Desired solution
o stability is computed for NA
but also when it is placed in non-singleton communities
AlexChristensen commented
With update, allow.singleton = TRUE
argument will allow singletons in *EGA
functions. Singletons work in itemStability
with no issues:
# Bootstrap EGA
boot <- bootEGA(
data = wmt2[,7:24],
type = "parametric", iter = 500,
algorithm = "leiden",
resolution_parameter = 0.10,
allow.singleton = TRUE,
plot.typicalStructure = FALSE
)
# Print/summary
boot
# Plot
plot(boot)
# Item Stability
itemStability(boot, IS.plot = TRUE)
Output:
> boot <- bootEGA(
+ data = wmt2[,7:24],
+ type = "parametric", iter = 500,
+ algorithm = "leiden",
+ resolution_parameter = 0.10,
+ allow.singleton = TRUE,
+ plot.typicalStructure = FALSE
+ )
/ [====================] 100% elapsed: 17s ~remaining: 0s
> # Print/summary
> boot
Model: GLASSO (EBIC with gamma = 0.5)
Correlations: auto
Algorithm: Leiden with Constant Potts Model
Unidimensional Method: Louvain (Most Common for 1000 iterations)
----
EGA Type: EGA
Bootstrap Samples: 500 (Parametric)
9 8 7 10
Frequency: 0.188 0.75 0.046 0.016
Median dimensions: 8 [6.98, 9.02] 95% CI
> # Plot
> plot(boot)
> # Item Stability
> itemStability(boot, IS.plot = TRUE)
EGA Type: EGA
Bootstrap Samples: 500 (Parametric)
Proportion Replicated in Empirical Dimensions:
wmt1 wmt2 wmt3 wmt4 wmt5 wmt6 wmt7 wmt8 wmt9 wmt10
0.958 0.984 0.986 0.992 0.668 0.772 0.942 0.898 0.990 0.876
wmt11 wmt12 wmt13 wmt14 wmt15 wmt16 wmt17 wmt18
0.858 0.960 0.898 0.848 0.950 0.920 0.928 0.964
Node wmt11
is a singleton
Closing as resolved