Movatterモバイル変換

Basic Single Case Design

Description

This is the data for the Basic Single Case Design Example presented inFigure 14 of the What Works Clearinghouse Procedures and Standards Handbook,Version 5.0

Usage

basic_scd

Format

basic_scd

A data frame with 21 rows and 3 columns:

phase

Study phase

time

Time of data collection

socbehavs

Social behaviors score

Source

https://ies.ed.gov/ncee/WWC/Docs/referenceresources/Final_WWC-HandbookVer5_0-0-508.pdf

Cross-Lagged Correlation

Description

Computes cross-lagged correlations between two variables in a dataframe.

Usage

cross_lagged(  .df,  .x,  .y,  lag.max = 5,  na.action = stats::na.fail,  conf.level = 0.95,  ...)

Arguments

Details

This function calculates the cross-lagged correlation between two variablesin a given dataframe up to a specified maximum lag. It returns an objectcontaining the cross-correlation function, confidence intervals, and otherrelated information. The function calls stats::ccf() internally.

Value

An object of class "cross_lagged" containing the cross-correlation function,upper and lower confidence intervals, the number of observations used, andthe names of the variables analyzed.

Examples

# Creating a sample datasetreversal_withdrawal <- data.frame(  phase = c(rep("baseline1", 6), rep("treatment1", 5), rep("baseline2", 5), rep("treatment2", 5)),  time = 1:21,  extbehavs = c(15, 10, 14, 17, 13, 12, 2, 1, 1, 0, 0, 9, 9, 11, 15, 20, 1, 0, 4, 0, 1))reversal_withdrawal$synth <- sapply(reversal_withdrawal$time, function(x) {  stats::rpois(1, x)})reversal_withdrawal <- as.data.frame(reversal_withdrawal)# Using the cross_lagged functioncl_result <- cross_lagged(reversal_withdrawal, .x = "time", .y = "synth")

Deal a Phase of Cards

Description

This function deals a phase of cards from a given deck, consisting of 6 cards.It returns a list containing the dealt cards as a matrix, the updated deck,and the individual dealt cards.

Usage

deal_phase(.deck)

Arguments

Value

A list with the following components:

cards_matrix

A matrix of the dealt cards, with 1 row and 6 columns.

updeck

The updated deck after dealing the cards.

dealt_cards

A list of the individual dealt cards.

Fictional Single Case Design Efficacy of CBT Example

Description

This is the data set used for the clinical case example in Maric & van der Werf(2020).

Usage

efficacy_of_CBT

Format

efficacy_of_CBT

A data frame with 10 rows and 4 columns:

phase

Study phase

time

Time of data collection

Anxious

Outcome measure

CATS_N

Outcome measure

Source

doi:10.4324/9780429273872-9

References

Maric, M., & van der Werff, V. (2020). Single-Case ExperimentalDesigns in Clinical Intervention Research. In R. van de Schoot & M. Miocevic(Eds.), Small Sample Size Solutions: A Guide for Applied Researchers andPractitioners (1st ed., pp. 10). Routledge.doi:10.4324/9780429273872-9

Mixed Model Analysis

Description

Performs a mixed model analysis on a dataset, allowing for the specificationof a dependent variable, time variable, phase variable, participantidentification, and covariates. It supports reverse timing within phases,custom phase levels and labels, and adds covariates to the fixed effects model.The function fits a model using generalized least squares and returnsa list containing the modified dataset, the fitted model, and a plot ofpredicted values with phase annotations.

Usage

mixed_model_analysis(  .df,  .dv,  .time,  .phase,  .participant = NULL,  rev_time_in_phase = FALSE,  phase_levels = NULL,  phase_labels = NULL,  covs = NULL,  ...)

Arguments

Value

A list containing three elements:-data: The modified dataset with added time variables and predictedvalues.-fitted_mod: The fitted model object fromnlme::gls.-plot: A ggplot object showing the predicted values and phaseannotations.

References

Maric, M., & van der Werff, V. (2020). Single-Case ExperimentalDesigns in Clinical Intervention Research. In R. van de Schoot & M. Miocevic(Eds.), Small Sample Size Solutions: A Guide for Applied Researchers andPractitioners (1st ed., pp. 10). Routledge.doi:10.4324/9780429273872-9

Examples

res <- mixed_model_analysis(efficacy_of_CBT, .dv = "Anxious", .time = "time",                            .phase = "phase",rev_time_in_phase = TRUE,                            phase_levels = c(0, 1),                            phase_labels = c("Exposure", "Exposure + CT"))summary(res$fitted_mod)

Non-overlap of All Pairs (NAP) Analysis

Description

This function performs a Non-overlap of All Pairs (NAP) analysis on a givendata frame, considering specified phases, improvement direction, and analysistype (reversability or trend). It is designed to assess the distinctiveness ofdata across phases or trends within the data, based on the concept outlined inthe What Works Clearinghouse Procedures and Standards Handbook.

Usage

nap(  .df,  .y,  .phase,  .time,  type = c("reversability", "trend"),  last_m = NULL,  phases,  improvement = c("positive", "negative"))

Arguments

Details

The NAP analysis is a method used to evaluate the effectiveness of interventionsby analyzing the non-overlap between data points across different phases ortrends within a dataset. It is a useful statistical tool for educational researchand is detailed in the What Works Clearinghouse Procedures and Standards Handbook,Version 5.0.

Value

A numeric value representing the NAP score, reflecting the proportionof non-overlapping data points between the specified phases or trends.

References

What Works Clearinghouse. (2022). What Works Clearinghouse procedures andstandards handbook, version 5.0. U.S. Department of Education, Institute ofEducation Sciences, National Center for Education Evaluation and RegionalAssistance (NCEE). This report is available on the What Works Clearinghousewebsite athttps://ies.ed.gov/ncee/wwc/Handbooks.

Examples

nap(.df = reversal_withdrawal, .y = "extbehavs", .phase = "phase",    .time = "time", type = "reversability",    phases = list("baseline1", "baseline2"), improvement = "negative")

Nap Jack: A Single Case Design Card Game

Description

This function creates a Shiny application that implements the Nap Jack card game.Nap Jack is a single case design card game where the player deals cards in phasesand tries to achieve a winning score based on the analysis of the dealt cards.

Usage

napjack()

Details

The game consists of four phases: baseline 1, treatment 1, baseline 2, andtreatment 2. In each phase, the player deals six cards and has the option to swapcards within a row once per phase. After all four phases are completed, the gameis scored based on the analysis of the dealt cards using non-overlap of all pairs(NAP) and mixed effects modeling.

The game utilizes the following internal helper functions:

• deal_phase(): Deals a phase of cards from the game deck.

• render_card_grid(): Renders a grid of card images based on the dealt cards.

• swapper(): Allows swapping of cards within a row of the card matrix.

The game also uses the following external functions for analysis:

• raw_plot(): Plots the raw data of the dealt cards.

• nap(): Performs non-overlap of all pairs analysis.

• mixed_model_analysis(): Performs mixed effects modeling analysis.

The player's objective is to achieve a winning score by strategically dealing andswapping cards to optimize the analysis results.

Value

A Shiny application object that represents the Nap Jack game.

Examples

# To run the Shiny appif(interactive()){  napjack()}

Plot Cross-Lagged Correlation Results

Description

Plots the cross-lagged correlation results calculated by cross_lagged().This method generates a bar plot showing the autocorrelation function (ACF) valuesfor different lags, along with dashed lines indicating the upper and lower confidenceintervals. The plot is created usingggplot2.

Usage

## S3 method for class 'cross_lagged'plot(x, ...)

Arguments

Value

Aggplot object representing the cross-lagged correlation analysisresults. This plot includes bars for ACF values at different lagsand dashed lines for the upper and lower confidence intervals.

Examples

#Creating a sample datasetreversal_withdrawal <- data.frame(  phase = c(rep("baseline1", 6), rep("teratment1", 5), rep("baseline2", 5), rep("teratment2", 5)),  time = 1:21,  extbehavs = c(15, 10, 14, 17, 13, 12, 2, 1, 1, 0, 0, 9, 9, 11, 15, 20, 1, 0, 4, 0, 1))reversal_withdrawal$synth <- sapply(reversal_withdrawal$time, function(x) {  stats::rpois(1, x)})reversal_withdrawal <- as.data.frame(reversal_withdrawal)# Using the cross_lagged functioncl_result <- cross_lagged(reversal_withdrawal, .x = "time", .y = "synth")# Plot the cross-lagged correlation resultsplot(cl_result)

Plot Results from Replications and Extension of GLS Simulation

Description

This method creates a ggplot2 visualization of results from a replext_gls object.It allows for flexible plotting of different metrics across various conditions.

Usage

## S3 method for class 'replext_gls'plot(  x,  term,  metric = "rejection_rates",  x_axis = "tppp",  color = "rho",  title = NULL,  x_label = NULL,  y_label = NULL,  ...)

Arguments

Details

This method creates a line plot with points, where each line represents a differentlevel of the color variable (default is rho). If the metric is "rejection_rates",error bars are added to represent the standard error of the rejection rates.

Value

A ggplot2 object representing the plot.

Examples

results <- replext_gls(  n_timepoints_list = c(10),  rho_list = c(0.2),  iterations = 10,  betas = c("(Intercept)" = 0, "phase1" = 1),  formula = y ~ phase)plot(results, term = "phase1", metric = "rejection_rates")

Print Method for Cross-Lagged Objects

Description

Prints a summary of cross-lagged correlation analysis results. This methodformats the results into a data frame showing lags, autocorrelation function (ACF) values,and indicates significance based on the confidence intervals. Significant ACF values,which fall outside the upper or lower confidence intervals, are marked with an asterisk (*).

Usage

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

Arguments

Value

Invisibly returns a data frame with columns for lag, ACF values, and asignificance indicator. This data frame is printed to the console for the user.

Examples

#Creating a sample datasetreversal_withdrawal <- data.frame(  phase = c(rep("baseline1", 6), rep("teratment1", 5), rep("baseline2", 5), rep("teratment2", 5)),  time = 1:21,  extbehavs = c(15, 10, 14, 17, 13, 12, 2, 1, 1, 0, 0, 9, 9, 11, 15, 20, 1, 0, 4, 0, 1))reversal_withdrawal$synth <- sapply(reversal_withdrawal$time, function(x) {  stats::rpois(1, x)})reversal_withdrawal <- as.data.frame(reversal_withdrawal)# Using the cross_lagged functioncl_result <- cross_lagged(reversal_withdrawal, .x = "time", .y = "synth")# Print the summary of cross-lagged analysisprint(cl_result)

Process Condition Variable

Description

This is an internal helper function used byraw_plot andrandomization_testto process the condition variable in the input data frame. It sets the factorlevels and labels of the condition variable based on the providedcond_levelsandcond_labels parameters.

Usage

process_cond(.df, .cond, cond_levels, cond_labels)

Arguments

Value

The input data frame.df with the condition variable processed as a factorwith the specified levels and labels.

Process Phase Variable

Description

This is an internal helper function used byraw_plot andmixed_model_analysisto process the phase variable in the input data frame. It sets the factor levelsand labels of the phase variable based on the providedphase_levels andphase_labels parameters.

Usage

process_phase(.df, .phase, phase_levels, phase_labels)

Arguments

Value

The input data frame.df with the phase variable processed as a factorwith the specified levels and labels.

Randomization Test for Single-Case Experiments

Description

Performs a randomization test on data from single-case experiments. Thisfunction allows for the assessment of treatment effects by comparing the observedoutcome difference to a distribution of differences obtained through permutation.It supports various constraints on permutation sequences, such as fixed orobserved maximum and minimum consecutive sequences of a particular condition.The function also provides graphical summaries of the raw data and thedistribution of mean differences.

Usage

randomization_test(  .df,  .out,  .cond,  .time,  num_permutations = NULL,  consec = c("observed", "fixed"),  max_consec = NULL,  min_consec = NULL,  cond_levels = NULL,  cond_labels = NULL,  conf.level = 0.95,  .bins = 30)

Arguments

Value

A list containing the original difference in means, the p-value of thetest, the distribution of test statistics under the null hypothesis,confidence intervals, and plots of the distribution of mean differencesand the raw data.

References

Onghena, P. (2020). One by One: The design and analysis of replicated randomizedsingle-case experiments.In R. van de Schoot & M. Mioecvic (Eds.), Small SampleSize Solutions: A Guide for Applied Researchers and Practitioners (1st ed., pp.15). Routledge.doi:10.4324/9780429273872-8

Examples

result <- randomization_test(sleeping_pills, .out = "sever_compl",                             .cond = "treatment", .time = "day",                             num_permutations = 100,                             cond_levels = c("C", "E"))result$conf_int

Plot Raw Data with Optional Phase and Condition Annotations

Description

This function generates a plot of raw data from a specified data frame. Itsupports optional annotations based on phase and condition variables, and canfacet the plot by participant. The plot is customizable with parameters forsetting factor levels and labels for both phase and condition variables. Itutilizes ggplot2 for plotting.

Usage

raw_plot(  .df,  .out,  .time,  .phase = NULL,  .cond = NULL,  .participant = NULL,  phase_levels = NULL,  phase_labels = NULL,  cond_levels = NULL,  cond_labels = NULL,  label_raise = 2)

Arguments

Value

A ggplot object representing the raw data plot with optional annotationsfor phase and condition, and faceting by participant if specified.

Examples

rp <- raw_plot(.df = efficacy_of_CBT, .out = "Anxious", .time = "time",               .phase = "phase", phase_levels = c(0, 1),               phase_labels = c("Exposure", "Exposure + CT"))

Render a Grid of Card Images

Description

This function takes a matrix of card objects and renders them as a grid ofcard images using Shiny'srenderImage function. The resulting grid isreturned as a Shiny UI component.

Usage

render_card_grid(new_card_grid)

Arguments

Details

The function appliesrenderImage to each card object in the matrix,creating a grid of card images. The images are displayed in a fluid rowlayout, with each image occupying an equal portion of the available width.

Value

A Shiny UI component representing the grid of rendered card images.

Replications and Extension of Generalized Least Squares Simulation

Description

This function performs multiple simulations of Generalized Least Squares (GLS)models across various conditions, extending the work of Maric et al. (2014).It allows for the exploration of different numbers of timepoints per phase andautocorrelation parameters, providing a comprehensive analysis of modelperformance across these conditions.

Usage

replext_gls(  n_timepoints_list,  rho_list,  iterations,  n_phases = 2,  n_IDs = 1,  betas,  formula,  covariate_specs = NULL,  alpha_level = 0.05,  verbose = FALSE)

Arguments

Value

A data frame of class 'replext_gls' containing simulation results, including:

References

Maric, M., de Haan, E., Hogendoorn, S.M., Wolters, L.H. & Huizenga, H.M. (2014).Evaluating statistical and clinical significance of intervention effects insingle-case experimental designs: An SPSS method to analyze univariate data.Behavior Therapy. doi: 10.1016/j.beth.2014.09.009

Examples

results <- replext_gls(  n_timepoints_list = c(10),  rho_list = c(0.2),  iterations = 10,  betas = c("(Intercept)" = 0, "phase1" = 1),  formula = y ~ phase)

Generate UI Elements for GLS Simulation Parameters

Description

This internal function creates a list of Shiny UI input elements for settingparameters in the Generalized Least Squares (GLS) simulation Shiny app.

Usage

replext_gls_UIParams()

Details

This function is used internally by thereplext_pgsql Shiny app togenerate the UI elements for parameter input. It creates a standardized setof inputs with default values that users can modify to customize theirsimulation settings.

Value

A list of Shiny input elements, including:

• textInput for number of timepoints in each phase

• textInput for AR(1) parameter values

• numericInput for number of simulation iterations

• numericInput for number of phases

• numericInput for number of participants

• textAreaInput for regression coefficients

• textAreaInput for model formula

• textAreaInput for covariate specification

• numericInput for alpha level

Note

The function uses text inputs for lists (e.g., timepoints, AR(1) parameters)which should be entered as comma-separated values. The betas, formula, andcovariate specifications are entered as text areas to allow for more complexinputs.

See Also

replext_pgsql for the main Shiny app function.

Replication and Extension of Generalized Least Squares Simulation Shiny App

Description

This function creates a Shiny app for running and visualizing simulations ofGeneralized Least Squares (GLS) models, extending the work of Maric et al. (2014).It allows users to interactively set simulation parameters, run simulations,view results, and generate plots.

Usage

replext_pgsql(dbname, datatable, host, port, user, password)

Arguments

Details

The app provides a user interface for:

• Setting simulation parameters

• Running simulations based on the specified parameters

• Viewing simulation results in a table format

• Generating plots of various metrics across different conditions

• Storing and retrieving results from a PostgreSQL database

• Displaying relevant citations

The app uses thereplext_gls() function to perform the actual simulations.

Value

A Shiny app object which can be run to start the application.

References

Maric, M., de Haan, E., Hogendoorn, S.M., Wolters, L.H. & Huizenga, H.M. (2014).Evaluating statistical and clinical significance of intervention effects insingle-case experimental designs: An SPSS method to analyze univariate data.Behavior Therapy. doi: 10.1016/j.beth.2014.09.009

See Also

replext_gls for the underlying simulation function.

Examples

if(interactive()){replext_pgsql(  dbname = "my_database",  datatable = "simulation_results",  host = "localhost",  port = 5432,  user = "myuser",  password = "mypassword")}

Reversal/withdrawal Design Example

Description

This is the data for the Reversal/Withdrawal Design Example presented inFigure 17 of the What Works Clearinghouse Procedures and Standards Handbook,Version 5.0

Usage

reversal_withdrawal

Format

reversal_withdrawal

A data frame with 21 rows and 3 columns:

phase

Study phase

time

Time of data collection

extbehavs

Externalizing behaviors score

Source

https://ies.ed.gov/ncee/WWC/Docs/referenceresources/Final_WWC-HandbookVer5_0-0-508.pdf

Single Case Design Toolbox Shiny Application

Description

This Shiny application provides a toolbox for analyzing single case design data.It includes features for data upload, data type handling, raw data visualization,mixed effects analysis, cross-lagged correlation analysis, non-overlap of all pairsanalysis, and randomization tests.

Usage

scdtb()

Value

A Shiny app object which can be run to start the application.

References

Maric, M., & van der Werff, V. (2020). Single-Case Experimental Designs inClinical Intervention Research. In R. van de Schoot & M. Miocevic (Eds.),Small Sample Size Solutions: A Guide for Applied Researchers and Practitioners(1st ed., pp. 10). Routledge.doi:10.4324/9780429273872-9

What Works Clearinghouse. (2022). What Works Clearinghouse procedures andstandards handbook, version 5.0. U.S. Department of Education, Institute ofEducation Sciences, National Center for Education Evaluation and RegionalAssistance (NCEE). This report is available on the What Works Clearinghousewebsite at https://ies.ed.gov/ncee/wwc/Handbooks

Onghena, P. (2020). One by One: The design and analysis of replicated randomizedsingle-case experiments.In R. van de Schoot & M. Mioecvic (Eds.), Small SampleSize Solutions: A Guide for Applied Researchers and Practitioners (1st ed., pp.15). Routledge.doi:10.4324/9780429273872-8

Examples

# To run the Shiny appif(interactive()){  scdtb()}

Simulate and Analyze Generalized Least Squares

Description

This function simulates data and fits a Generalized Least Squares (GLS) modelto the simulated data. It can handle multiple phases, multiple subjects (IDs),and various covariate specifications.

Usage

simulate_gls_once(  n_timepoints_per_phase,  rho,  n_phases = 2,  n_IDs = 1,  betas,  formula,  covariate_specs = NULL)

Arguments

Value

A list containing:

Examples

# Simple example with 2 phases, 10 timepoints per phase, and no covariatesresult <- simulate_gls_once(  n_timepoints_per_phase = 10,  rho = 0.2,  betas = c("(Intercept)" = 0, "phase1" = 1),  formula = y ~ phase)

Sleeping Pills and Dizziness Example

Description

This is the data set used for the example in Onghena (2020).

Usage

sleeping_pills

Format

sleeping_pills

A data frame with 14 rows and 3 columns:

day

day of study

treatment

E, Experimental; C, Control

sever_compl

Severity of complaints

Source

doi:10.4324/9780429273872-8

References

Onghena, P. (2020). One by one: The design and analysis ofreplicated randomized single-case experiments. In R. van de Schoot & M. Miocevic(Eds.), Small sample size solutions: A guide for applied researchers andpractitioners (1st ed., pp. 15). Routledge.doi:10.4324/9780429273872-8

Swap Cards Within a Row of a Card Matrix

Description

This function allows swapping of cards within a row of a card matrix. It takes acard matrix and the indices of the columns to swap. The function modifies thecard matrix in-place and returns the updated matrix.

Usage

swapper(cards_matrix, swap_in_row = NULL)

Arguments

Details

The function performs the following steps:

1. Initializes a move history attribute if it doesn't exist.

2. Checks ifswap_in_row is provided and has a length of 2.

3. Verifies that swapping within a phase has not been performed more than once.

4. Swaps the cards at the specified column indices within the first row of the matrix.

5. Updates the move history attribute.

6. Adds the "swapper" class to the card matrix.

Value

The updated card matrix with the specified cards swapped within a row.

Note

The function modifies the card matrix in-place and returns the updated matrix.