Multivariate meta-analysis on correlation coefficients

Authors

  • Arvind Shah Medical Communications Medical Support Group Clinical Biostatistics, Merck Research Laboratories, Rahway, NJ 07065, USA
  • Jianxin Lin Medical Communications Medical Support Group Clinical Biostatistics, Merck Research Laboratories, Rahway, NJ 07065, USA
  • Thomas Mathew Department of Mathematics and Statistics, University of Maryland, Baltimore 20250, USA
  • Bimal Sinha Department of Mathematics and Statistics, University of Maryland, Baltimore 20250, USA
  • Gaurav Sharma Department of Mathematics and Statistics, University of Maryland, Baltimore 20250, USA
  • Dihua Xu Department of Mathematics and Statistics, University of Maryland, Baltimore 20250, USA

Keywords:

Correlation matrix, hypercholesterolemia, meta-analysis, multivariate CLT, Type I error

Abstract

In this paper a large sample test is derived for testing the homogeneity of correlation matrices based on Fisher’s z-transformation, and it is demonstrated that the test maintains the type I error rate satisfactorily. Towards this, the asymptotic joint distribution of the sample correlations is derived when the samples come from a multivariate population that could be non-normal. Assuming that the homogeneity hypothesis holds, methodology is provided to perform a meta-analysis of the common correlation matrix. An application to the correlations among the three cholesterol related variables: low-density lipoprotein (LDL), non-high density lipoprotein (NHDL) and Apolipoprotein B (APOB), in an investigation of the efficacy of cholesterol lowering drug, Ezetimibe, in combination with statins in patients with hypercholesterolemia, is provided.

Downloads

How to Cite

Shah, A., Lin, J., Mathew, T., Sinha, B., Sharma, G., & Xu, D. (2015). Multivariate meta-analysis on correlation coefficients. Thailand Statistician, 11(2), 97–110. Retrieved from https://ph02.tci-thaijo.org/index.php/thaistat/article/view/34204

Issue

Section

Articles