Correlation analysis for longitudinal data: applications to HIV and psychosocial research

Department of Biostatistics and Computational Biology, University of Rochester, Rochester, NY 14642, USA.
Statistics in Medicine (Impact Factor: 1.83). 09/2007; 26(22):4116-38. DOI: 10.1002/sim.2857
Source: PubMed


Correlation analysis is widely used in biomedical and psychosocial research for assessing rater reliability, precision of diagnosis and accuracy of proxy outcomes. The popularity of longitudinal study designs has propelled the proliferation in recent years of new methods for longitudinal and other multi-level clustered data designs, such as the mixed-effect models and generalized estimating equations. Despite these advances, research and methodological development on addressing missing data for correlation analysis is woefully lacking. In this paper, we consider non-parametric inference for the product-moment correlation within a longitudinal data setting and address missing data under both the missing completely at random and missing at random assumptions. We illustrate the approach with real study data in mental health and HIV prevention research.

4 Reads
  • [Show abstract] [Hide abstract]
    ABSTRACT: Measures of agreement are used in a wide range of behavioral, biomedical, psychosocial, and health-care related research to assess reliability of diagnostic test, psychometric properties of instrument, fidelity of psychosocial intervention, and accuracy of proxy outcome. The concordance correlation coefficient (CCC) is a popular measure of agreement for continuous outcomes. In modern-day applications, data are often clustered, making inference difficult to perform using existing methods. In addition, as longitudinal study designs become increasingly popular, missing data have become a serious issue, and the lack of methods to systematically address this problem has hampered the progress of research in the aforementioned fields. In this paper, we develop a novel approach to tackle the complexities involved in addressing missing data and other related issues for performing CCC analysis within a longitudinal data setting. The approach is illustrated with both real and simulated data. diagnostic test-inverse probability weighted estimates-missing data-monotone missing data pattern-U-statistics
    Psychometrika 03/2010; 75(1):99-119. DOI:10.1007/s11336-009-9142-z · 1.09 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The analysis of a baseline predictor with a longitudinally measured outcome is well established and sample size calculations are reasonably well understood. Analysis of bivariate longitudinally measured outcomes is gaining in popularity and methods to address design issues are required. The focus in a random effects model for bivariate longitudinal outcomes is on the correlations that arise between the random effects and between the bivariate residuals. In the bivariate random effects model, we estimate the asymptotic variances of the correlations and we propose power calculations for testing and estimating the correlations. We compare asymptotic variance estimates to variance estimates obtained from simulation studies and compare our proposed power calculations for correlations on bivariate longitudinal data to power calculations for correlations on cross-sectional data.
    Statistics in Medicine 11/2010; 29(27):2811-24. DOI:10.1002/sim.4064 · 1.83 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: U-statistics represent an important class of statistics arising from modeling quantities of interest defined by multi-subject responses such as the classic Mann–Whitney–Wilcoxon rank tests. However, classic applications of U-statistics are largely limited to univariate outcomes within a cross-sectional data setting. As longitudinal study designs become increasingly popular in today's research, it is imperative to generalize the classic theory of U-statistics to such a study setting to meet the challenges of modern clinical and translational research. In this article, we focus on applications of U-statistics to longitudinal study data. We first give a brief overview of U-statistics and then discuss how to apply this powerful class of statistics to model quantities of interest with a longitudinal data setting. In addition to generalizing U-statistics and associated inference theory to longitudinal data analysis, we also discuss a class of function response models (FRM) to bring the power of U-statistics to uncharted territory. We illustrate applications of generalized U-statistics and FRM with data from some real longitudinal studies. WIREs Comp Stat 2011 3 457–471 DOI: 10.1002/wics.178 For further resources related to this article, please visit the WIREs website.
    09/2011; 3(5). DOI:10.1002/wics.178
Show more