This paper is in the following e-collection/theme issue:

Peer Reviews (289)

Published on in Vol 6 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/83798, first published .
Peer Review of “Estimating Variance of Log Standardized Incidence Ratios Assessing Health Care Providers’ Performance: Comparative Analysis Using Bayesian, Bootstrap, and Delta Method Approaches”

Peer Review of “Estimating Variance of Log Standardized Incidence Ratios Assessing Health Care Providers’ Performance: Comparative Analysis Using Bayesian, Bootstrap, and Delta Method Approaches”

Peer Review of “Estimating Variance of Log Standardized Incidence Ratios Assessing Health Care Providers’ Performance: Comparative Analysis Using Bayesian, Bootstrap, and Delta Method Approaches”

Authors of this article:

Emmanuel Oluwagbade1 Author Orcid Image
Article Authors Cited by Tweetations Metrics


    This is a peer-review report for “Estimating Variance of Log Standardized Incidence Ratios Assessing Health Care Providers’ Performance: Comparative Analysis Using Bayesian, Bootstrap, and Delta Method Approaches.”


    General Comments

    This paper [1] compares 3 approaches for estimating the variance of the log standardized incidence ratio when profiling kidney replacement therapy centers in Australia: (1) the analytical delta method, (2) the nonparametric bootstrap method (5000 resamples), and (3) Bayesian Markov chain Monte Carlo (25,500 iterations, 3 chains). Using 2005‐2023 patient-level data from the Australia and New Zealand Dialysis and Transplant Registry and a random-effects logistic model, the authors evaluated bias, variance, and mean squared error (MSE) and visualized performance via funnel plots. Results indicated similar bias across methods but substantially lower variance and MSE for the Markov chain Monte Carlo method (bias≈0.019; variance=0.00005; MSE=0.00042) compared with the bootstrap method (variance=0.00027; MSE=0.00094).

    The topic is practical and timely, yet the manuscript needs clearer model specification, interval coverage evaluation, and streamlined writing before it reaches publishable quality.

    Specific Comments

    Major Comments
    1. There are some concerns around model clarity (Poisson versus logistic language mixed; appendix is missing). Provide complete model equations, a covariate list, and software/code links and justify using the Bernoulli model for a ratio outcome.
    2. Interval coverage and type I error absent. Action: add a simulation or internal bootstrap to report 95% interval coverage and false-positive rates for each method.
    3. Missing data handling unexplained.Action: quantify missingness, describe any imputation, and list all risk-adjustment covariates.
    Minor Comments

    In Table 1, add units and align decimals.

    Conflicts of Interest

    None declared.

    1. Woldeyohannes S, Jones Y, Lawton P. Estimating variance of log standardized incidence ratios assessing health care providers’ performance: comparative analysis using Bayesian, bootstrap, and delta method approaches. JMIRx Med. 2025;6:e77415. [CrossRef]

    Edited by Songphol Tungjitviboonkun; This is a non–peer-reviewed article. submitted 08.Sep.2025; accepted 08.Sep.2025; published 09.Oct.2025.

    Copyright

    © Emmanuel Oluwagbade. Originally published in JMIRx Med (https://med.jmirx.org), 9.Oct.2025.

    This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIRx Med, is properly cited. The complete bibliographic information, a link to the original publication on https://med.jmirx.org/, as well as this copyright and license information must be included.