Package 'snc'

Title: Strongest Neighbor Coherence
Description: Computes Strongest Neighbor Coherence (SNC), a structural diagnostic that replaces Cronbach's alpha using top-k correlation structure.
Authors: Kevin E. Wells [aut, cre]
Maintainer: Kevin E. Wells <[email protected]>
License: MIT + file LICENSE
Version: 0.1.0
Built: 2026-05-11 06:59:53 UTC
Source: https://github.com/theotherdrwells/snc

Help Index


Print Method for SNC Objects

Description

Prints summary output for an object of class "snc".

Usage

## S3 method for class 'snc'
print(x, ...)

Arguments

x

An object of class "snc" returned by the snc function.

...

Ignored.


Strongest Neighbor Coherence (SNC)

Description

Computes Strongest Neighbor Coherence (SNC), a rotation-free structural diagnostic that evaluates how well each item aligns with its top-k most strongly correlated neighbors.

Usage

snc(R, k = 2, factors = NULL, digits = 3)

Arguments

R

A square item correlation matrix (symmetric, 1s on the diagonal).

k

Integer. Number of strongest neighbors to use for each item (default = 2).

factors

Optional. A vector of factor assignments for items, used to compute group-level means.

digits

Number of decimal places to round to (default = 3).

Value

An object of class "snc" with:

overall

Mean SNC value across all items

items

A data frame of item-level SNC values

factors

(Optional) A data frame of factor-level mean SNC values

Examples

R <- matrix(c(1, .6, .3, .6, 1, .5, .3, .5, 1), 3, 3)
rownames(R) <- colnames(R) <- c("Item1", "Item2", "Item3")
snc(R)