Volume 30, Issue 27
Research Article

Marginal association measures for clustered data

Douglas J. Lorenz

Corresponding Author

E-mail address: djlore01@louisville.edu

Department of Bioinformatics and Biostatistics, School of Public Health and Information Science, University of Louisville, Louisville, KY, USA

Douglas J. Lorenz, Department of Bioinformatics and Biostatistics, School of Public Health and Information Science, University of Louisville, Louisville, KY 40292, USA.

E‐mail: djlore01@louisville.edu

Search for more papers by this author
Somnath Datta

Department of Bioinformatics and Biostatistics, School of Public Health and Information Science, University of Louisville, Louisville, KY, USA

Search for more papers by this author
Susan J. Harkema

Department of Neurological Surgery, University of Louisville, Louisville, KY, USA

Frazier Rehab Institute, Louisville, KY, USA

Search for more papers by this author
First published: 27 September 2011
Citations: 23

The code used for the simulation study and application to real data in this paper is available upon request to the corresponding author, or can be downloaded from http://www.somnathdatta.org/software/.

Abstract

The use of correlation coefficients in measuring the association between two continuous variables is common, but regular methods of calculating correlations have not been extended to the clustered data framework. For clustered data in which observations within a cluster may be correlated, regular inferential procedures for calculating marginal association between two variables can be biased. This is particularly true for data in which the number of observations in a given cluster is informative for the association being measured. In this paper, we apply the principle of inverse cluster size reweighting to develop estimators of marginal correlation that remain valid in the clustered data framework when cluster size is informative for the correlation being measured. These correlations are derived as analogs to regular correlation estimators for continuous, independent data, namely, Pearson's ρ and Kendall's τ. We present the results of a simple simulation study demonstrating the appropriateness of our proposed estimators and the inherent bias of other inferential procedures for clustered data. We illustrate their use through an application to data from patients with incomplete spinal cord injury in the USA. Copyright © 2011 John Wiley & Sons, Ltd.

Number of times cited according to CrossRef: 23

  • Molecular imaging to identify patients with metastatic breast cancer who benefit from endocrine treatment combined with cyclin-dependent kinase inhibition, European Journal of Cancer, 10.1016/j.ejca.2019.10.024, 126, (11-20), (2020).
  • Variance estimation in tests of clustered categorical data with informative cluster size, Statistical Methods in Medical Research, 10.1177/0962280220928572, (096228022092857), (2020).
  • Results of a Study Comparing Glycated Albumin to Other Glycemic Indices, The Journal of Clinical Endocrinology & Metabolism, 10.1210/clinem/dgz087, 105, 3, (677-687), (2019).
  • HIV-Specific T Cell Responses Are Highly Stable on Antiretroviral Therapy, Molecular Therapy - Methods & Clinical Development, 10.1016/j.omtm.2019.07.008, 15, (9-17), (2019).
  • Rectal Organoids Enable Personalized Treatment of Cystic Fibrosis, Cell Reports, 10.1016/j.celrep.2019.01.068, 26, 7, (1701-1708.e3), (2019).
  • Using Primer-ID Deep Sequencing to Detect Recent Human Immunodeficiency Virus Type 1 Infection, The Journal of Infectious Diseases, 10.1093/infdis/jiy426, 218, 11, (1777-1782), (2018).
  • Classifying Injuries in Young Children as Abusive or Accidental: Reliability and Accuracy of an Expert Panel Approach, The Journal of Pediatrics, 10.1016/j.jpeds.2018.01.033, 198, (144-150.e4), (2018).
  • A log rank test for clustered data with informative within‐cluster group size, Statistics in Medicine, 10.1002/sim.7899, 37, 27, (4071-4082), (2018).
  • Ultra-long-acting removable drug delivery system for HIV treatment and prevention, Nature Communications, 10.1038/s41467-018-06490-w, 9, 1, (2018).
  • Examining the Psychometric Properties of Maximally Efficient Items From the Social Skills Improvement System–Teacher Rating Scale, Journal of Psychoeducational Assessment, 10.1177/0734282917743335, 37, 3, (307-319), (2017).
  • International variations in the gestational age distribution of births: an ecological study in 34 high-income countries, European Journal of Public Health, 10.1093/eurpub/ckx131, 28, 2, (303-309), (2017).
  • 2-D and 3-D Ultrasound for Tumor Volume Analysis: A Prospective Study, Ultrasound in Medicine & Biology, 10.1016/j.ultrasmedbio.2016.12.009, 43, 4, (775-781), (2017).
  • Estimation of rank correlation for clustered data, Statistics in Medicine, 10.1002/sim.7257, 36, 14, (2163-2186), (2017).
  • Pearson's chi‐square test and rank correlation inferences for clustered data, Biometrics, 10.1111/biom.12653, 73, 3, (822-834), (2017).
  • Metabolomic analysis of CSF indicates brain metabolic impairment precedes hematological indices of anemia in the iron-deficient infant monkey, Nutritional Neuroscience, 10.1080/1028415X.2016.1217119, 21, 1, (40-48), (2016).
  • Assessment of Functional Improvement without Compensation for Human Spinal Cord Injury: Extending the Neuromuscular Recovery Scale to the Upper Extremities, Journal of Neurotrauma, 10.1089/neu.2015.4213, 33, 24, (2181-2190), (2016).
  • Inferring marginal association with paired and unpaired clustered data, Statistical Methods in Medical Research, 10.1177/0962280216669184, (096228021666918), (2016).
  • Bivariate correlation coefficients in family‐type clustered studies, Biometrical Journal, 10.1002/bimj.201400131, 57, 6, (1084-1109), (2015).
  • Compensatory muscle activation during forced respiratory tasks in individuals with chronic spinal cord injury, Respiratory Physiology & Neurobiology, 10.1016/j.resp.2015.07.001, 217, (54-62), (2015).
  • Approximate U-Statistics for State Waiting Times Under Right Censoring, Modern Nonparametric, Robust and Multivariate Methods, 10.1007/978-3-319-22404-6, (31-46), (2015).
  • Laboratory validation of a new gas-enhanced dentine liquid permeation evaluation system, Clinical Oral Investigations, 10.1007/s00784-014-1186-5, 18, 9, (2067-2075), (2014).
  • Inference on the marginal distribution of clustered data with informative cluster size, Statistical Papers, 10.1007/s00362-013-0504-3, 55, 1, (71-92), (2013).
  • Quantitative and sensitive assessment of neurophysiological status after human spinal cord injury, Journal of Neurosurgery: Spine, 10.3171/2012.6.AOSPINE12117, 17, Suppl1, (77-86), (2012).

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