Type: Package
Title: Response Item Networks
Version: 2.2.0
Maintainer: Philip Warncke <pwarncke@live.unc.edu>
Description: Contains various tools to perform and visualize Response Item Networks ('ResIN's'). 'ResIN' binarizes ordered-categorical and qualitative response choices from (survey) data, calculates pairwise associations and maps the location of each item response as a node in a force-directed network. Please refer to https://www.resinmethod.net/ for more details.
License: GPL-3
URL: https://pwarncke77.github.io/ResIN/
BugReports: https://github.com/pwarncke77/ResIN/issues
Depends: R (≥ 4.2.0)
Imports: psych, ggplot2 (≥ 3.4.4), dplyr (≥ 1.1.3), tidyr (≥ 1.3.0), fastDummies, qgraph, igraph, wCorr, Matrix, DirectedClustering, foreach, parallelly, parallel, doSNOW, readr, ggraph (≥ 2.2.0), shadowtext (≥ 0.1.4)
Encoding: UTF-8
LazyData: true
LazyDataCompression: xz
RoxygenNote: 7.3.2
Suggests: knitr, rmarkdown
VignetteBuilder: knitr
NeedsCompilation: no
Packaged: 2025-07-11 12:20:23 UTC; some0
Author: Philip Warncke [cre, aut], Dino Carpentras [aut], Adrian Lüders [aut]
Repository: CRAN
Date/Publication: 2025-07-11 12:40:10 UTC

Output example for a bootstrapping analysis conducted with the ResIN package.

Description

Output example for a bootstrapping analysis conducted with the ResIN package.

Usage

data(Bootstrap_example)

Format

An object of class "rda"

References

This dataset was made available by Lüders et.al. 2024.

Examples


data(Bootstrap_example)
str(Bootstrap_example)

Source data for Lüders, A., Carpentras, D. and Quayle, M., 2024. Attitude networks as intergroup realities: Using network‐modelling to research attitude‐identity relationships in polarized political contexts. British Journal of Social Psychology, 63(1), pp.37-51.

Description

The sample of N = 402 paid participants through the crowd working platform Prolific Academic. The core of the survey consists of A set of eight political attitude items abortion, immigration, gun control, and gay marriage. Each item followed a 5-point scale ranging from strong disagreement to strong agreement. The survey also includes items on partisanship, affective polarization, and a short vignette experiment.

Usage

data(BrJSocPsychol_2024)

Format

An object of class "data.frame"

References

This dataset was made available by Lüders et.al. 2024.

Examples


data(BrJSocPsychol_2024)
head(BrJSocPsychol_2024)

ResIN

Description

Performs Response Item-Network (ResIN) analysis

Usage

ResIN(
  df,
  node_vars = NULL,
  left_anchor = NULL,
  cor_method = "pearson",
  weights = NULL,
  method_wCorr = "Pearson",
  poly_ncor = 1,
  neg_offset = 0,
  ResIN_scores = TRUE,
  remove_negative = TRUE,
  EBICglasso = FALSE,
  EBICglasso_arglist = NULL,
  remove_nonsignificant = FALSE,
  sign_threshold = 0.05,
  node_covars = NULL,
  node_costats = NULL,
  network_stats = TRUE,
  detect_clusters = FALSE,
  cluster_method = NULL,
  cluster_arglist = NULL,
  cluster_assignment = TRUE,
  generate_ggplot = TRUE,
  plot_ggplot = TRUE,
  plot_whichstat = NULL,
  plot_edgestat = NULL,
  color_palette = "RdBu",
  direction = 1,
  plot_responselabels = TRUE,
  response_levels = NULL,
  plot_title = NULL,
  bipartite = FALSE,
  save_input = TRUE,
  seed = NULL
)

Arguments

df

A data-frame object containing the raw data.

node_vars

An optional character vector detailing the attitude item columns to be selected for ResIN analysis (i.e. the subset of attitude variables in df).

left_anchor

An optional character scalar indicating a particular response node which determines the spatial orientation of the ResIN latent space. If this response node does not appear on the left-hand side, the x-plane will be inverted. This ensures consistent interpretation of the latent space across multiple iterations (e.g. in bootstrapping analysis). Defaults to NULL (no adjustment to orientation is taken.)

cor_method

Which correlation method should be used? Defaults to "auto" which applies the cor_auto function from the qgraph package. Possible arguments are "auto", "pearson", "kendall", and "spearman".

weights

An optional continuous vector of survey weights. Should have the same length as number of observations in df. If weights are provided, weighted correlation matrix will be estimated with the weightedCorr function from the wCorr package.

method_wCorr

If weights are supplied, which method for weighted correlations should be used? Defaults to "Pearson". See wCorr::weightedCorr for all correlation options.

poly_ncor

How many CPU cores should be used to estimate polychoric correlation matrix? Only used if cor_method = "polychoric".

neg_offset

Should negative correlations be offset to avoid small correlation pairs disappearing? Defaults to 0. Any positive number between 0 and 1 may be supplied instead.

ResIN_scores

Should spatial scores be calculated for every individual. Defaults to TRUE. Function obtains the mean positional score on the major (x-axis) and minor (y-axis). Further versions of this package will include more sophisticated scoring techniques.

remove_negative

Should all negative correlations be removed? Defaults to TRUE (highly recommended). Setting to FALSE makes it impossible to estimate a force-directed network layout. Function will use igraph::layout_nicely instead.

EBICglasso

Should a sparse, Gaussian-LASSO ResIN network be estimated? Defaults to FALSE. If set to TRUE, EBICglasso function from the qgraph packages performs regularization on (nearest positive-semi-definite) ResIN correlation matrix.

EBICglasso_arglist

An argument list feeding additional instructions to the EBICglasso function if EBICglasso is set to TRUE.

remove_nonsignificant

Optionally, should non-significant edges be removed from the ResIN network? Defaults to FALSE. Note that this option is incompatible with EBICglasso and weighted correlations.

sign_threshold

At what p-value threshold should non-significant edges be removed? Defaults to 0.05.

node_covars

An optional character string selecting quantitative covariates that can be used to enhance ResIN analysis. Typically, these covariates provide grouped summary statistics for item response nodes. (E.g.: What is the average age or income level of respondents who selected a particular item response?) Variable names specified here should match existing columns in df.

node_costats

If any node_covars are selected, what summary statistics should be estimated from them? Argument should be a character vector and call a base-R function. (E.g. "mean", "median", "sd"). Each element specified in node_costats is applied to each element in node_covars and the out-put is stored as a node-level summary statistic in the ResIN_nodeframe. The extra columns in ResIN_nodeframe are labeled according to the following template: "covariate name"_"statistic". So for the respondents mean age, the corresponding column in ResIN_nodeframe would be labeled as "age_mean".

network_stats

Should common node- and graph level network statistics be extracted? Calls qgraph::centrality_auto and DirectedClustering::ClustF to the ResIN graph object to extract node-level betweenness, closeness, strength centrality, as well as the mean and standard deviation of these scores at the network level. Also estimates network expected influence, average path length, and global clustering coefficients. Defaults to TRUE. Set to FALSE if estimation takes a long time.

detect_clusters

Optional, should community detection be performed on item response network? Defaults to FALSE. If set to TRUE, performs a clustering method from the [igraph](https://igraph.org/r/doc/cluster_leading_eigen.html) library and stores the results in the ResIN_nodeframe output.

cluster_method

A character scalar specifying the [igraph-based](https://igraph.org/r/doc/communities.html) community detection function.

cluster_arglist

An optional list specifying additional arguments to the selected [igraph](https://igraph.org/r/doc/communities.html) clustering method.

cluster_assignment

Should individual (survey) respondents be assigned to different clusters? If set to TRUE, function will generate an n*c matrix of probabilities for each respondent to be assigned to one of c clusters. Furthermore, a vector of length n is generated displaying the most likely cluster respondents belong to. In case of a tie between one or more clusters, a very small amount of random noise determines assignment. Both matrix and vectors are added to the aux_objects list. Defaults to FALSE and will be ignored if detect_clusters is set to FALSE.

generate_ggplot

Should a ggplot-based visualization of the ResIN network be generated? Defaults to TRUE.

plot_ggplot

Should a basic ggplot of the ResIN network be plotted? Defaults to TRUE. If set to FALSE, the ggplot object will not be directly returned to the console. (However, if generate_ggplot=TRUE, the plot will still be generated and stored alongside the other output objects.)

plot_whichstat

Should a particular node-level metric be color-visualized in the ggplot output? For node cluster, specify "cluster". For the same Likert response choices or options, specify "choices". For a particular node-level co-variate please specify the name of the particular element in node_covars followed by a "_" and the specific node_costats you would like to visualize. For instance if you want the visualize average age at the node-level, you should specify "age_mean". To colorize by node centrality statistics, possible choices are "Strength", "Betweenness", "Closeness", and "ExpectedInfluence". Defaults to NULL. Make sure to supply appropriate choices to node_covars, node_costats, detect_clusters, and/or network_stats prior to setting this argument.

plot_edgestat

Should the thickness of the edges be adjusted according to a particular co-statistic? Defaults to NULL. Possible choices are "weight" for the bi-variate correlation strength, and "edgebetweenness"

color_palette

Optionally, you may specify the ggplot2 color palette to be applied to the plot. All options contained in [RColorBrewer](https://cran.r-project.org/web/packages/RColorBrewer/RColorBrewer.pdf) (for discrete colors such as cluster assignments) and [ggplot2::scale_colour_distiller](https://ggplot2.tidyverse.org/reference/scale_brewer.html) are supported. Defaults to "RdBu".

direction

Which direction should the color palette be applied in? Defaults to 1. Set to -1 if the palette should appear in reverse order.

plot_responselabels

Should response labels be plotted via geom_text? Defaults to TRUE. It is recommended to set to FALSE if the network possesses a lot of nodes and/or long response choice names.

response_levels

An optional character vector specifying the correct order of global response levels. Only useful if all node-items follow the same convention (e.g. ranging from "strong disagreement" to "strong agreement"). The supplied vector should have the same length as the total number of response options and supply these (matching exactly) in the correct order. E.g. c("Strongly Agree", "Somewhat Agree", "Neutral", "Somewhat Disagree", "Strongly Disagree"). Defaults to NULL.

plot_title

Optionally, a character scalar specifying the title of the ggplot output. Defaults to "ResIN plot".

bipartite

Should a bipartite graph be produced in addition to classic ResIN graph? Defaults to FALSE. If set to TRUE, an [igraph](https://igraph.org/r/doc/) bipartite graph with response options as node type 1 and participants as node type 2 will be generated and included in the output list. Further, an object called coordinate_df with spatial coordinates of respondents and a plot-able ggraph-object called bipartite_ggraph are generated if set to TRUE.

save_input

Optionally, should input data and function arguments be saved (this is necessary for running ResIN_boots_prepare function). Defaults to TRUE.

seed

Random seed for force-directed algorithm. Defaults to NULL (no seed is set.) If scalar integer is supplied, that seed will be set prior to analysis.

Value

An edge-list type data-frame, ResIN_edgelist, a node-level data-frame, ResIN_nodeframe, an n*2 data-frame of individual-level spatial scores along the major (x) and minor(y) axis, ResIN_scores a list of graph-level statistics graph_stats including (graph_structuration), and centralization (graph_centralization). Further, a bipartite_output list which includes an igraph class bipartite graph (bipartite_igraph), a data frame, coordinate_df, with spatial coordinates of respondents, and a plot-able ggraph-object called bipartite_ggraph is optionally generated. Lastly, the output includes a list of auxiliary objects, aux_objects, including the ResIN adjacency matrix (adj_matrix), a numeric vector detailing which item responses belong to which item (same_items), and the dummy-coded item-response data-frame (df_dummies).

Examples


## Load the 12-item simulated Likert-type toy dataset
data(lik_data)

# Apply the ResIN function to toy Likert data:
ResIN_obj <- ResIN(lik_data, cor_method = "spearman", network_stats = TRUE, detect_clusters = TRUE)

ResIN_boots_execute

Description

Execute prepared ResIN bootstrap analysis

Usage

ResIN_boots_execute(
  ResIN_boots_prepped,
  parallel = FALSE,
  detect_cores = TRUE,
  core_offset = 0L,
  n_cores = 2L,
  inorder = FALSE
)

Arguments

ResIN_boots_prepped

A list of prepared ResIN objects for bootstrapping (outcome of the ResIN_boots_prepare function)

parallel

Should the function be executed in parallel using the foreach package? Defaults to FALSE. If FALSE, function will execute sequentially in a simple for loop.

detect_cores

Should the number of available CPU cores be automatically detected? Defaults to TRUE and is ignored when parallel is set to FALSE.

core_offset

Optionally, specify a positive integer offset that is subtracted from the number of automatically detected cores. Defaults to 0L.

n_cores

Manually specify the number of available CPU cores. Defaults to 2L and is ignored if detect_cores is set to TRUE or if parallel is set to FALSE.

inorder

Should parallel execution be done in sequential order of the ResIN_boots_prepped object?

Value

A list object containing n (bootstrapped) ResIN list objects.

Examples

## Load the 12-item simulated Likert-type toy dataset
data(lik_data)

# Apply the ResIN function to toy Likert data:
ResIN_obj <- ResIN(lik_data, cor_method = "spearman", network_stats = TRUE,
                      generate_ggplot = FALSE)

## Not run: 
# Prepare for bootstrapping
prepped_boots <- ResIN_boots_prepare(ResIN_obj, n=5000, boots_type="permute")

# Execute the prepared bootstrap list
executed_boots <-  ResIN_boots_execute(prepped_boots, parallel = TRUE, detect_cores = TRUE)

# Extract results - here for example, the network (global)-clustering coefficient
ResIN_boots_extract(executed_boots, what = "global_clustering", summarize_results = TRUE)

## End(Not run)

ResIN_boots_extract

Description

Extract and summarize quantities from bootstrapped ResIN objects

Usage

ResIN_boots_extract(ResIN_boots_executed, what, summarize_results = FALSE)

Arguments

ResIN_boots_executed

A list of prepared ResIN objects for bootstrapping (outcome of the ResIN_boots_execute function)

what

A character vector of length one specifying the target quantity of interest. This should be a one-to-one match with the corresponding output vector (or scalar) among the bootstrapped result list (see ResIN_boots_execute). For participants' position on the x-axis of the ResIN latent space, for example, specify "scores_x".

summarize_results

Should the extracted quantities be summarized through a series of descriptive statistics? If set to true, the minimum, maximum, mean, selected quantiles, and the standard deviation are reported. If set to FALSE (default), extracted quantities are instead returned as a list.

Value

A list object containing n (bootstrapped) ResIN list objects.

Examples

## Load the 12-item simulated Likert-type toy dataset
data(lik_data)

# Apply the ResIN function to toy Likert data:
ResIN_obj <- ResIN(lik_data, cor_method = "spearman", network_stats = TRUE,
                      generate_ggplot = FALSE)

## Not run: 
# Prepare for bootstrapping
prepped_boots <- ResIN_boots_prepare(ResIN_obj, n=5000, boots_type="permute")

# Execute the prepared bootstrap list
executed_boots <-  ResIN_boots_execute(prepped_boots, parallel = TRUE, detect_cores = TRUE)

# Extract results - here for example, the network (global)-clustering coefficient
ResIN_boots_extract(executed_boots, what = "global_clustering", summarize_results = TRUE)

## End(Not run)

ResIN_boots_prepare

Description

Prepare a ResIN-based bootstrap analysis

Usage

ResIN_boots_prepare(
  ResIN_object,
  n = 10000,
  boots_type = "resample",
  resample_size = NULL,
  weights = NULL,
  save_input = FALSE,
  seed_boots = 42
)

Arguments

ResIN_object

A ResIN object to prepare bootstrapping workflow.

n

Bootstrapping sample size. Defaults to 10.000.

boots_type

What kind of bootstrapping should be performed? If set to "resample", function performs row-wise re-sampling of raw data (useful for e.g., sensitivity or power analysis). If set to "permute", function will randomly reshuffle raw item responses (useful e.g., for simulating null-hypothesis distributions). Defaults to "resample".

resample_size

Optional parameter determining sample size when boots_type is set to "resample". Defaults of to number of rows in raw data.

weights

An optional weights vector that can be used to adjust the re-sampling of observations. Should either be NULL (default) or a positive numeric vector of the same length as the original data.

save_input

Should all input information for each bootstrap iteration (including re-sampled/permuted data) be stored. Set to FALSE by default to save a lot of memory and disk storage.

seed_boots

Random seed for bootstrap samples

Value

A list object containing n re-sampled or permuted copies of the raw data, along with a list of instructions for how to perform the ResIN analysis and what outputs to generate.

Examples

## Load the 12-item simulated Likert-type toy dataset
data(lik_data)

# Apply the ResIN function to toy Likert data:
ResIN_obj <- ResIN(lik_data, cor_method = "spearman", network_stats = TRUE,
                      generate_ggplot = FALSE)

## Not run: 
# Prepare for bootstrapping
prepped_boots <- ResIN_boots_prepare(ResIN_obj, n=5000, boots_type="permute")

# Execute the prepared bootstrap list
executed_boots <-  ResIN_boots_execute(prepped_boots, parallel = TRUE, detect_cores = TRUE)

# Extract results - here for example, the network (global)-clustering coefficient
ResIN_boots_extract(executed_boots, what = "global_clustering", summarize_results = TRUE)

## End(Not run)

ResIN_to_gephi

Description

Saves a ResIN graph as a series of csv files readable by Gephi. Source code taken from RMHogervorst / gephi

Usage

ResIN_to_gephi(ResIN_object, file = "ResIN_gephi.csv")

Arguments

ResIN_object

the output of the ResIN function (a list with class ResIN).

file

the name with .csv extension for the Gephi readable file to be output at. Defaults to "ResIN_gephi.csv".

Value

A series of csv files readable by Gephi

References

Source code was taken from: https://github.com/RMHogervorst/gephi?tab=MIT-1-ov-file#readme

Examples


## Not run: 
## Load the 12-item simulated Likert-type ResIN toy dataset
data(lik_data)

## Run the function:
ResIN_to_gephi(ResIN(lik_data), file = "ResIN_gephi.csv")

## End(Not run)

ResIN_to_igraph

Description

Transforms the output of the ResIN function into an [igraph](https://igraph.org/r/doc/cluster_leading_eigen.html) object

Usage

ResIN_to_igraph(ResIN_object, igraph_arglist = NULL)

Arguments

ResIN_object

the output of the ResIN function (a list with class ResIN).

igraph_arglist

an optional argument list to be supplied to the igraph::graph_from_adjacency_matrix function. If NULL, default is: list(mode = "undirected", weighted = TRUE, diag = FALSE).

Value

A class igraph object.

References

Csardi G, Nepusz T (2006). “The igraph software package for complex network research.” InterJournal, Complex Systems, 1695. https://igraph.org.

Examples


## Load the 12-item simulated Likert-type ResIN toy dataset
data(lik_data)

## Run the function:

igraph_output <-  ResIN_to_igraph(ResIN(lik_data))


## Plot and/or investigate as you wish:
igraph::plot.igraph(igraph_output)

ResIN_to_qgraph

Description

Transforms the output of the ResIN function into an qgraph object

Usage

ResIN_to_qgraph(ResIN_object, qgraph_arglist = NULL)

Arguments

ResIN_object

the output of the ResIN function (a list with class ResIN).

qgraph_arglist

an optional argument list to be supplied to the igraph::graph_from_adjacency_matrix function. If NULL, defaults are: list(layout = "spring", maximum = 1, vsize = 6, DoNotPlot = TRUE, sampleSize = nrow(df_nodes), mar = c(3,3,3,3), normalize = FALSE)

Value

A [qgraph]https://cran.r-project.org/web/packages/qgraph/index.html graph object.

References

Epskamp S, Cramer AOJ, Waldorp LJ, Schmittmann VD, Borsboom D (2012). “qgraph: Network Visualizations of Relationships in Psychometric Data.” Journal of Statistical Software, 48(4), 1–18.

Examples



## Load the 12-item simulated Likert-type ResIN toy dataset
data(lik_data)

## Run the function:
ResIN_qgraph <-  ResIN_to_qgraph(ResIN(lik_data))

Likert-type simulated data for "ResIN" package examples

Description

An artificially created data-set (n=1000) of 12, 5-point Likert data. Modeled on the basis of a standard normal data-generating process. Likert scales contain 20 percent uncorrelated, homoscedastic measurement error. This data-set is used for the examples in the "ResIN" package vignette.

Usage

data(lik_data)

Format

An object of class "data.frame"

References

This data set was artificially created for the ResIN package.

Examples


data(lik_data)
head(lik_data)