SimplyAgree

SimplyAgree is an R package and jamovi module for method comparison, agreement, and reliability studies. It estimates Bland-Altman limits of agreement, tolerance limits, concordance correlation coefficients (CCC), intraclass correlation coefficients (ICC), measurement error and minimal detectable change, chance-corrected agreement for categorical ratings (kappa, Gwet’s AC1, Krippendorff’s alpha), and Deming/Passing-Bablok regression, and plans sample sizes for agreement and reliability studies. Simple paired data, replicate measurements, and nested (repeated measures) designs are supported. Full documentation and vignettes are on the package website.

Which function should I use?

Goal	Function	Data
Bland-Altman limits of agreement	`agreement_limit()`	simple, replicate, or nested
Tolerance limits (prediction-oriented agreement)	`tolerance_limit()`	simple, repeated, or nested; optional conditions
Concordance correlation coefficient (CCC)	`ccc_test()`	simple, replicate, or nested
Non-parametric limits of agreement	`agree_np()`	simple or replicate
Reliability: intraclass correlation (ICC)	`icc_test()`	repeated measures (long or wide)
Measurement error: SEM, SEE, SEP, coefficient of variation	`reli_err_test()`	repeated measures
Minimal detectable change (MDC)	`mdc_test()`	repeated measures
Reliability across facets (repeats and occasions)	`reli_facet_test()`	multi-facet designs
Categorical agreement: Gwet’s AC1, kappa, Krippendorff’s alpha	`cac_test()`	categorical or ordinal ratings
Model-based kappa for many raters	`ord_kappa_test()`	ordinal ratings
Deming / Passing-Bablok regression	`dem_reg()`, `pb_reg()`	paired, optionally with replicates
Power and sample size for agreement	`power_agreement_limit()`, `power_agreement_exact()`, `blandPowerCurve()`, `agree_expected_half()`, `agree_assurance()`	study planning
Power and sample size for reliability	`power_icc()`, `precision_icc()`	study planning
Power and sample size for Deming regression	`deming_sample_size()`	study planning

Some older functions still work but are superseded: use agreement_limit() instead of agree_test(), agree_reps(), and agree_nest(); icc_test() and reli_err_test() instead of reli_stats() and reli_aov(); and cac_test() instead of agree_coef(). loa_lme() is deprecated in favor of tolerance_limit(model = "lme"), and loa_mixed() is defunct. The jmv*() functions exist for the jamovi module and are not intended for use in R.

Background

SimplyAgree is an R package, and jamovi module, designed to simplify agreement and reliability analyses for researchers. The package implements rigorous statistical methods for method comparison studies, providing both classical and modern approaches to assessing measurement agreement.

Core Functionality

The package provides two primary approaches for assessing agreement between measurement methods:

1. Limits of Agreement: `agreement_limit()`

The agreement_limit() function implements Bland-Altman style limits of agreement analysis. This approach:

Computes confidence intervals for the range of agreement between two methods
Supports simple, replicate and nested designs
Handles design effects for clustered data
Uses the MOVER method of Zou (2013) by default, or the classic Bland-Altman (1999) intervals (loa_calc)

Exact procedures based on Shieh (2019) and Jan & Shieh (2018) are available in agree_test() and the power functions.

This is the preferred function when you want to describe what proportion of differences fall within specified bounds or when making inferences about the central region of the paired-difference distribution.

2. Tolerance Intervals: `tolerance_limit()`

The tolerance_limit() function creates statistical tolerance intervals that:

Construct intervals expected to contain a specified proportion of future observations
Implement exact equal-tailed tolerance intervals
Support confidence intervals for ranges of percentiles
Handle both simple and complex study designs

Tolerance intervals are most appropriate when making simultaneous inferences about pairs of percentile limits or when you need prediction-oriented intervals for future measurements.

Additional Features

Beyond the two core functions, SimplyAgree provides:

Concordance: ccc_test() for the concordance correlation coefficient with simple, replicate and nested data (with an optional subject bootstrap, boot = TRUE, recommended for replicate data with few subjects)
Reliability Analysis: icc_test() (intraclass correlations; replaces the superseded reli_stats() and reli_aov()), reli_err_test() (SEM, SEE, SEP and coefficients of variation) and mdc_test() (minimal detectable change)
Categorical Agreement: cac_test() for chance-corrected agreement coefficients (Gwet’s AC1, kappa, Krippendorff’s alpha and more) and ord_kappa_test() for model-based kappa with ordinal ratings and many raters
Power Analysis: power_agreement_exact() and related functions for sample size determination in agreement studies, and power_icc() / precision_icc() for reliability studies
Error-in-Variables: supports “Deming” and “Passing-Bablok” regression methods for method comparison
Visualization: Built-in plotting capabilities for Bland-Altman plots and related visualizations
Flexible Design Support: Handles simple, nested, and repeated measures designs with appropriate variance adjustments

Installing SimplyAgree

You can install the released version of SimplyAgree from CRAN with:

install.packages("SimplyAgree")

Or the most up-to-date version from GitHub with:

# devtools::install_github("arcaldwell49/SimplyAgree")
install.packages("SimplyAgree", repos = c('https://arcaldwell49.r-universe.dev', 'https://cloud.r-project.org'))

Quick Start Example

library(SimplyAgree)

# Example data: rectal (trec) and esophageal (teso) temperatures,
# several trials per subject
data(temps)

# Limits of agreement analysis
agreement_limit(x = "trec_pre",
                y = "teso_pre",
                id = "id",
                data = temps,
                data_type = "nest",
                agree.level = 0.95)

## MOVER Limits of Agreement (LoA)
## 95% LoA @ 5% Alpha-Level
## Nested Data
## 
##    Bias          Bias CI Lower LoA Upper LoA            LoA CI
##  0.1908 [0.1191, 0.2625]   -0.1507    0.5324 [-0.2307, 0.6124]
## 
## LoA CI: one-sided 95% bounds (outer ends of 90% CIs) for an intersection-union test against a maximal allowable difference;
##   not a joint 95% interval for the LoA
## SD of Differences = 0.1743

# Tolerance interval analysis
tolerance_limit(x = "trec_pre",
                y = "teso_pre",
                id = "id",
                data = temps,
                tol_level = 0.95)

## Agreement between Measures (Difference: x-y)
## 95% CI for Bias; 95% Prediction Interval
## Tolerance Limits: at least 95% of differences with 95% confidence
## Model: GLS, compound symmetry within id
## 
##    Bias          Bias CI Prediction Interval  Tolerance Limits
##  0.1908 [0.1191, 0.2625]   [-0.2098, 0.5915] [-0.2532, 0.6349]
## 
## SD of Differences = 0.1743
## Between-Subject SD = 0.0773; Within-Subject SD = 0.1562

# Concordance correlation coefficient
ccc_test(x = "trec_pre",
         y = "teso_pre",
         id = "id",
         data = temps,
         data_type = "nest")

## 
##  Concordance Correlation Coefficient (nested pairs)
## 
## data:  trec_pre and teso_pre
## 
## alternative hypothesis: two.sided
## 95 percent confidence interval:
##  0.3216463 0.7053779
## sample estimates:
##       CCC 
## 0.5410955

# Reliability analysis: Shrout & Fleiss (1979), 6 subjects rated by 4 judges
sf <- data.frame(J1 = c(9, 6, 8, 7, 10, 6), J2 = c(2, 1, 4, 1, 5, 2),
                 J3 = c(5, 3, 6, 2, 6, 4), J4 = c(8, 2, 8, 6, 9, 7))
icc_test(col.names = c("J1", "J2", "J3", "J4"), data = sf)

## 
##  Two-way, consistency, single-measure ICC [Shrout & Fleiss ICC(3,1)]
## 
## data:  J1, J2, J3, J4
## 
## alternative hypothesis: two.sided
## 95 percent confidence interval:
##  0.3424648 0.9458583
## sample estimates:
##  ICC(C,1) 
## 0.7148407

Most results have plot() methods (Bland-Altman and line-of-identity plots) and check() methods for assumption diagnostics.

Contributing

We are happy to receive bug reports, suggestions, questions, and (most of all) contributions to fix problems and add features. Pull Requests for contributions are encouraged.

Here are some simple ways in which you can contribute (in the increasing order of commitment):

Read and correct any inconsistencies in the documentation
Raise issues about bugs or wanted features
Review code
Add new functionality

Code of Conduct

Please note that the SimplyAgree project is released with a Contributor Code of Conduct. By contributing to this project, you agree to abide by its terms.

Acknowledgements

Logo artwork courtesy of Chelsea Parlett Pelleriti.

References

The functions in this package are largely based on the following works:

Bland, J. M., & Altman, D. G. (1986). Statistical methods for assessing agreement between two methods of clinical measurement. The Lancet, 327(8476), 307-310. https://doi.org/10.1016/S0140-6736(86)90837-8

Bland, J. M., & Altman, D. G. (1999). Measuring agreement in method comparison studies. Statistical Methods in Medical Research, 8(2), 135-160. https://doi.org/10.1177/096228029900800204

Carrasco, J. L., & Jover, L. (2003). Estimating the generalized concordance correlation coefficient through variance components. Biometrics, 59(4), 849-858. https://doi.org/10.1111/j.0006-341x.2003.00099.x

Carrasco, JL, et al. (2013). Estimation of the concordance correlation coefficient for repeated measures using SAS and R. Computer Methods and Programs in Biomedicine, 109, 293-304. https://doi.org/10.1016/j.cmpb.2012.09.002

Francq, B. G., Berger, M., & Boachie, C. (2020). To tolerate or to agree: A tutorial on tolerance intervals in method comparison studies with BivRegBLS R Package. Statistics in Medicine, 39(28), 4334-4349. https://doi.org/10.1002/sim.8709

Francq, B. G., Lin, D., & Hoyer, W. (2019). Confidence, prediction, and tolerance in linear mixed models. Statistics in Medicine, 38(30), 5603-5622. https://doi.org/10.1002/sim.8386

Gwet, K. L. (2014). Handbook of Inter-Rater Reliability (4th ed.). Advanced Analytics, LLC.

Jan, S. L., & Shieh, G. (2018). The Bland-Altman range of agreement: Exact interval procedure and sample size determination. Computers in Biology and Medicine, 100, 247-252. https://doi.org/10.1016/j.compbiomed.2018.06.020

Lin, L. I. (1989). A concordance correlation coefficient to evaluate reproducibility. Biometrics, 45(1), 255-268. https://doi.org/10.2307/2532051

Lu, M. J., et al. (2016). Sample Size for Assessing Agreement between Two Methods of Measurement by Bland-Altman Method. The International Journal of Biostatistics, 12(2). https://doi.org/10.1515/ijb-2015-0039

McGraw, K. O., & Wong, S. P. (1996). Forming inferences about some intraclass correlation coefficients. Psychological Methods, 1(1), 30-46. https://doi.org/10.1037/1082-989X.1.1.30

Parker, R. A., et al. (2016). Application of mixed effects limits of agreement in the presence of multiple sources of variability: exemplar from the comparison of several devices to measure respiratory rate in COPD patients. PloS One, 11(12), e0168321. https://doi.org/10.1371/journal.pone.0168321

Shieh, G. (2019). Assessing agreement between two methods of quantitative measurements: Exact test procedure and sample size calculation. Statistics in Biopharmaceutical Research, 12(3), 352-359. https://doi.org/10.1080/19466315.2019.1677495

Shrout, P. E., & Fleiss, J. L. (1979). Intraclass correlations: Uses in assessing rater reliability. Psychological Bulletin, 86(2), 420-428. https://doi.org/10.1037/0033-2909.86.2.420

Weir, J. P. (2005). Quantifying test-retest reliability using the intraclass correlation coefficient and the SEM. The Journal of Strength & Conditioning Research, 19(1), 231-240. https://doi.org/10.1519/15184.1

Zou, G. Y. (2013). Confidence interval estimation for the Bland-Altman limits of agreement with multiple observations per individual. Statistical Methods in Medical Research, 22(6), 630-642. https://doi.org/10.1177/0962280211402548