Volume 22, Issue 15
Research Article

Analysis of clustered matched‐pair data

Valerie L. Durkalski

Corresponding Author

E-mail address: durkalsv@musc.edu

TCIG*STATS, The Clinical Innovation Group (TCIG), Medical University of South Carolina, Foundation for Research Development, Charleston, U.S.A.

TCIG*STATS, The Clinical Innovation Group, 261 Calhoun Street, Suite 304, P.O. Box 250188, Charleston, SC 29401, U.S.A.Search for more papers by this author
Yuko Y. Palesch

TCIG*STATS, The Clinical Innovation Group (TCIG), Medical University of South Carolina, Foundation for Research Development, Charleston, U.S.A.

Department of Biometry & Epidemiology, Medical University of South Carolina, Charleston, U.S.A.

Search for more papers by this author
Stuart R. Lipsitz

Department of Biometry & Epidemiology, Medical University of South Carolina, Charleston, U.S.A.

Search for more papers by this author
Philip F. Rust

Department of Biometry & Epidemiology, Medical University of South Carolina, Charleston, U.S.A.

Search for more papers by this author
First published: 14 July 2003
Citations: 70

Abstract

Evaluation of the performance of a new diagnostic procedure with respect to a standard procedure arises frequently in practice. The response of interest, often in a dichotomous form, is measured twice, once with each procedure. The two procedures are administered to either two matched individuals, or when practical, to the same individual. A large sample test for matched‐pair data is the McNemar test. The main assumption of this test is independent paired responses; however, when more than one outcome from an individual is measured by each procedure, the data are clustered. Examples of such cases can be seen in dental and ophthalmology studies. Variance adjustment methods for the analysis of clustered matched‐pair data have been proposed; however, because of unequal cluster sizes, variability of correlation structures within a cluster (within paired responses in a cluster as well as between paired responses in a cluster), and unequal success probabilities among the clusters, the performances of some available methods are not consistent. This research proposes a simple adjustment to the McNemar test for the analysis of clustered matched‐pair data. Method of moments is used to calculate a consistent variance estimator. Using Monte Carlo simulation, the size and power of the proposed test are compared to those of two currently available methods. To illustrate practical application, clustered matched‐pair data from two clinical studies are analysed. Copyright © 2003 John Wiley & Sons, Ltd.

Number of times cited according to CrossRef: 70

  • Effect of airway management strategies during resuscitation from out-of-hospital cardiac arrest on clinical outcome: A registry-based analysis, Resuscitation, 10.1016/j.resuscitation.2020.04.015, 152, (157-164), (2020).
  • Evaluation of the Accuracy of 99DOTS, a Novel Cellphone-based Strategy for Monitoring Adherence to Tuberculosis Medications: Comparison of DigitalAdherence Data With Urine Isoniazid Testing, Clinical Infectious Diseases, 10.1093/cid/ciaa333, (2020).
  • Variance estimation in tests of clustered categorical data with informative cluster size, Statistical Methods in Medical Research, 10.1177/0962280220928572, (096228022092857), (2020).
  • Comparison of urine, self-collected vaginal swab, and cervical swab samples for detecting human papillomavirus (HPV) with Roche Cobas HPV, Anyplex II HPV, and RealTime HR-S HPV assay, Journal of Virological Methods, 10.1016/j.jviromet.2019.04.012, (2019).
  • Toward Understanding the Relationship between Prioritized Values and Preferences for Cardiopulmonary Resuscitation Among Seriously Ill Adults, Journal of Pain and Symptom Management, 10.1016/j.jpainsymman.2019.06.011, (2019).
  • Environmental surveillance and spatio-temporal analysis of Legionella spp. in a region of northeastern Italy (2002–2017), PLOS ONE, 10.1371/journal.pone.0218687, 14, 7, (e0218687), (2019).
  • A robust adjustment to McNemar test when the data are clustered, Communications in Statistics - Theory and Methods, 10.1080/03610926.2019.1651864, (1-15), (2019).
  • Two-Tier Lyme Disease Serology Test Results Can Vary According to the Specific First-Tier Test Used, Journal of the Pediatric Infectious Diseases Society, 10.1093/jpids/piy133, (2019).
  • Intrapatient Comparison of the Hepatobiliary Phase of Gd‐BOPTA and Gd‐EOB‐DTPA in the Differentiation of Hepatocellular Adenoma From Focal Nodular Hyperplasia, Journal of Magnetic Resonance Imaging, 10.1002/jmri.26227, 49, 3, (700-710), (2018).
  • Comparison of [68Ga]Ga-PSMA-11 PET/CT with [18F]NaF PET/CT in the evaluation of bone metastases in metastatic prostate cancer patients prior to radionuclide therapy, European Journal of Nuclear Medicine and Molecular Imaging, 10.1007/s00259-018-4048-6, 45, 11, (1873-1883), (2018).
  • Improved Interobserver Reliability of the Sanders Classification in Calcaneal Fractures Using Segmented Three-Dimensional Prints, The Journal of Foot and Ankle Surgery, 10.1053/j.jfas.2017.10.014, 57, 3, (440-444), (2018).
  • Statistical evaluation of corner detectors: does the statistical test have an effect?, IET Computer Vision, 10.1049/iet-cvi.2017.0256, 12, 7, (1018-1030), (2018).
  • Corrigendum: Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition, Frontiers in Psychology, 10.3389/fpsyg.2018.01695, 9, (2018).
  • A comparison of standard two-dimensional ultrasound to three-dimensional volume sonography for routine second-trimester fetal imaging, Journal of Perinatology, 10.1038/jp.2016.212, 37, 4, (380-386), (2017).
  • Comparing self- and provider-collected swabbing for HPV DNA testing in female-to-male transgender adult patients: a mixed-methods biobehavioral study protocol, BMC Infectious Diseases, 10.1186/s12879-017-2539-x, 17, 1, (2017).
  • Designing image segmentation studies: Statistical power, sample size and reference standard quality, Medical Image Analysis, 10.1016/j.media.2017.07.004, 42, (44-59), (2017).
  • A simple method for analyzing matched designs with double controls: McNemar's test can be extended, Journal of Clinical Epidemiology, 10.1016/j.jclinepi.2016.08.006, 81, (51-55.e2), (2017).
  • A reinterpretation and extension of McNemar’s test, Journal of Modern Applied Statistical Methods, 10.22237/jmasm/1493596860, 16, 1, (20-33), (2017).
  • Recurrent Convolutional Neural Networks: A Better Model of Biological Object Recognition, Frontiers in Psychology, 10.3389/fpsyg.2017.01551, 8, (2017).
  • Improving and extending the McNemar test using the Bayesian method, Statistics in Medicine, 10.1002/sim.6875, 35, 14, (2455-2466), (2016).
  • Evaluation Method, Dataset Size or Dataset Content: How to Evaluate Algorithms for Image Matching?, Journal of Mathematical Imaging and Vision, 10.1007/s10851-015-0626-4, 55, 3, (378-400), (2016).
  • Longitudinal changes in developmental defects of enamel, Community Dentistry and Oral Epidemiology, 10.1111/cdoe.12213, 44, 3, (255-262), (2016).
  • Modeling the decoy effect with context-RUM Models: Diagrammatic analysis and empirical evidence from route choice SP and mode choice RP case studies, Transportation Research Part B: Methodological, 10.1016/j.trb.2016.07.012, 93, (318-337), (2016).
  • Multiple trends in interspecific crop diversity: a longitudinal case study from the Ecuadorian Andes, Genetic Resources and Crop Evolution, 10.1007/s10722-015-0320-9, 63, 8, (1319-1343), (2015).
  • Revealed reputations in the finitely repeated prisoners’ dilemma, Economic Theory, 10.1007/s00199-015-0863-1, 58, 3, (441-484), (2015).
  • Neoadjuvant Radiotherapy Improves Survival in Patients With T2b/T3 Bladder Cancer: A Population-Based Analysis, Clinical Genitourinary Cancer, 10.1016/j.clgc.2015.02.014, 13, 4, (378-384.e1), (2015).
  • Aggregate Features in Multisample Classification Problems, IEEE Journal of Biomedical and Health Informatics, 10.1109/JBHI.2014.2314856, 19, 2, (486-492), (2015).
  • Preoperative 3-T Diffusion-Weighted MRI for the Qualitative and Quantitative Assessment of Extracapsular Extension in Patients With Intermediate- or High-Risk Prostate Cancer, American Journal of Roentgenology, 10.2214/AJR.13.11754, 203, 3, (W280-W286), (2014).
  • Learning Features for Tissue Classification with the Classification Restricted Boltzmann Machine, Medical Computer Vision: Algorithms for Big Data, 10.1007/978-3-319-13972-2_5, (47-58), (2014).
  • References, How to Design, Analyse and Report Cluster Randomised Trials in Medicine and Health Related Research, 10.1002/9781118763452, (234-242), (2014).
  • A statistical approach to bioclimatic trend detection in the airborne pollen records of Catalonia (NE Spain), International Journal of Biometeorology, 10.1007/s00484-013-0632-4, 58, 3, (371-382), (2013).
  • Comparative analysis of triplex nucleic acid test assays in United States blood donors, Transfusion, 10.1111/trf.12178, 53, 10pt2, (2525-2537), (2013).
  • Enterococcal bacteraemia: factors influencing mortality, length of stay and costs of hospitalization, Clinical Microbiology and Infection, 10.1111/1469-0691.12132, 19, 4, (E181-E189), (2013).
  • Exactitude diagnostique de l’angioscanner multibarrettes associé à un logiciel de post-traitement dans la sténose athéromateuse des artères rénales, Journal de Radiologie Diagnostique et Interventionnelle, 10.1016/j.jradio.2012.12.009, 94, 11, (1127-1136), (2013).
  • Consistency and Efficiency of CT Analysis of Metastatic Disease: Semiautomated Lesion Management Application Within a PACS, American Journal of Roentgenology, 10.2214/AJR.12.10136, 201, 3, (618-625), (2013).
  • A prospective comparison of integrated FDG-PET/contrast-enhanced CT and contrast-enhanced CT for pretreatment imaging of advanced epithelial ovarian cancer, Gynecologic Oncology, 10.1016/j.ygyno.2013.08.023, 131, 2, (389-394), (2013).
  • Accuracy of multi-detector computed tomographic angiography assisted by post-processing software for diagnosis atheromatous renal artery stenosis, Diagnostic and Interventional Imaging, 10.1016/j.diii.2013.05.001, 94, 11, (1123-1131), (2013).
  • Molecular sputum analysis for the diagnosis of lung cancer, British Journal of Cancer, 10.1038/bjc.2013.393, 109, 3, (530-537), (2013).
  • Reliability of Family Proxy Data for Studies of Malignant Mesothelioma: Results from the ATSDR Pilot Surveillance, ISRN Oncology, 10.1155/2013/325409, 2013, (1-5), (2013).
  • Inhibitors of mTOR and Risks of Allograft Failure and Mortality in Kidney Transplantation, American Journal of Transplantation, 10.1111/j.1600-6143.2012.04281.x, 13, 1, (100-110), (2012).
  • Referring physicians underestimate the extent of abnormalities in final reports from myocardial perfusion imaging, EJNMMI Research, 10.1186/2191-219X-2-27, 2, 1, (27), (2012).
  • Testing ratio of marginal probabilities in clustered matched-pair binary data, Computational Statistics & Data Analysis, 10.1016/j.csda.2011.10.025, 56, 6, (1829-1836), (2012).
  • Flat-panel versus 64-channel computed tomography for in vivo quantitative characterization of aortic atherosclerotic plaques, International Journal of Cardiology, 10.1016/j.ijcard.2010.11.011, 156, 3, (295-302), (2012).
  • Analysis of Clustered Binary Data, Encyclopedia of Biopharmaceutical Statistics, Third Edition, 10.1201/b14674, (58-62), (2012).
  • undefined, 2012 19th IEEE International Conference on Image Processing, 10.1109/ICIP.2012.6467069, (1153-1156), (2012).
  • Confidence intervals for the difference of marginal probabilities in clustered matched‐pair binary data, Pharmaceutical Statistics, 10.1002/pst.1523, 11, 5, (386-393), (2012).
  • Multiperson Visual Focus of Attention from Head Pose and Meeting Contextual Cues, IEEE Transactions on Pattern Analysis and Machine Intelligence, 10.1109/TPAMI.2010.69, 33, 1, (101-116), (2011).
  • Testing marginal homogeneity in clustered matched-pair data, Journal of Statistical Planning and Inference, 10.1016/j.jspi.2010.10.002, 141, 3, (1313-1318), (2011).
  • Clinical Performance of Two Fluorescence-Based Methods in Detecting Occlusal Caries Lesions in Primary Teeth, Caries Research, 10.1159/000328673, 45, 3, (294-302), (2011).
  • Detection of Pancreatic Carcinoma and Liver Metastases with Gadoxetic Acid–enhanced MR Imaging: Comparison with Contrast-enhanced Multi–Detector Row CT, Radiology, 10.1148/radiol.11103548, 260, 2, (446-453), (2011).
  • Real-World Lessons From the Implementation of a Depression Screening Protocol in Acute Myocardial Infarction Patients, Circulation: Cardiovascular Quality and Outcomes, 10.1161/CIRCOUTCOMES.110.960013, 4, 3, (283-292), (2011).
  • Temporal bone imaging using digital volume tomography and computed tomography: a comparative cadaveric radiological study, Surgical and Radiologic Anatomy, 10.1007/s00276-010-0713-6, 33, 2, (123-128), (2010).
  • Multiple McNemar Tests, Biometrics, 10.1111/j.1541-0420.2010.01408.x, 66, 4, (1185-1191), (2010).
  • A note on the tests for clustered matched‐pair binary data, Biometrical Journal, 10.1002/bimj.201000035, 52, 5, (638-652), (2010).
  • Patient satisfaction with GP-led melanoma follow-up: a randomised controlled trial, British Journal of Cancer, 10.1038/sj.bjc.6605638, 102, 10, (1447-1455), (2010).
  • McNemar's Test, Encyclopedia of Biopharmaceutical Statistics, 10.3109/9781439822463, (740-744), (2010).
  • Detecting depression in medically ill patients: Comparative accuracy of four screening questionnaires and physicians' diagnoses in Spanish population, Journal of Psychosomatic Research, 10.1016/j.jpsychores.2010.04.007, 69, 4, (399-406), (2010).
  • Analysis of Clustered Binary Data, Encyclopedia of Biopharmaceutical Statistics, 10.3109/9781439822463, (58-62), (2010).
  • Bayesian aggregation versus majority vote in the characterization of non-specific arm pain based on quantitative needle electromyography, Journal of NeuroEngineering and Rehabilitation, 10.1186/1743-0003-7-8, 7, 1, (2010).
  • Unipolar depression does not moderate responses to the Sweet Taste Test, Depression and Anxiety, 10.1002/da.20690, 27, 9, (859-863), (2010).
  • Comments on ‘Non‐inferiority tests for clustered matched‐pair data’ by J. Nam and D. Kwon, Statistics in Medicine 2009; 28:1668–1679, Statistics in Medicine, 10.1002/sim.3910, 29, 17, (1857-1858), (2010).
  • Foreign Travel Is a Major Risk Factor for Colonization with Escherichia coli Producing CTX-M-Type Extended-Spectrum β-Lactamases: a Prospective Study with Swedish Volunteers, Antimicrobial Agents and Chemotherapy, 10.1128/AAC.00220-10, 54, 9, (3564-3568), (2010).
  • Detection, location, and severity assessment of left anterior descending coronary artery stenoses by means of contrast-enhanced transthoracic harmonic echo Doppler, European Heart Journal, 10.1093/eurheartj/ehp163, 30, 14, (1797-1806), (2009).
  • Non‐inferiority tests for clustered matched‐pair data, Statistics in Medicine, 10.1002/sim.3580, 28, 12, (1668-1679), (2009).
  • Short-Term Impact of an Educational Program Promoting Live Donor Kidney Transplantation in Dialysis Centers, Progress in Transplantation, 10.1177/152692480801800409, 18, 4, (263-272), (2008).
  • Short-term impact of an educational program promoting live donor kidney transplantation in dialysis centers, Progress in Transplantation, 10.7182/prtr.18.4.7333557214wp36k5, 18, 4, (263-272), (2008).
  • The Hip Impact Protection Project: design and methods, Clinical Trials: Journal of the Society for Clinical Trials, 10.1177/1740774508095120, 5, 4, (347-355), (2008).
  • Comparing the caries‐preventive effect of two fissure sealing modalities in public health care: a single application of glass ionomer and a routine resin‐based sealant programme. A randomized split‐mouth clinical trial, International Journal of Paediatric Dentistry, 10.1111/j.1365-263X.2007.00855.x, 18, 1, (56-61), (2007).
  • Concordance of Self-Collected and Clinician-Collected Swab Samples for Detecting Human Papillomavirus DNA in Women 18 to 32 Years of Age, Sexually Transmitted Diseases, 10.1097/01.olq.0000240315.19652.59, PAP, (2006).
  • Inter‐rater reliability of nursing home surveys: a Bayesian latent class approach, Statistics in Medicine, 10.1002/sim.2224, 25, 2, (325-344), (2005).

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.