Testing the independence of two random vectors where only one dimension is large. (English) Zbl 1369.62123
Summary: For testing the independence of two vectors with respective dimensions \(p_1\) and \(p_2\), the existing literature in high-dimensional statistics all assume that both dimensions \(p_1\) and \(p_2\) grow to infinity with the sample size. However, as evidenced in RNA-sequencing data analysis, it happens frequently that one of the dimension is quite small and the other quite large compared to the sample size. In this paper, we address this new asymptotic framework for the independence test. A new test procedure is introduced and its asymptotic normality is established when the vectors are normally distributed. A Monte-Carlo study demonstrates the consistency of the procedure and exhibits its superiority over some existing high-dimensional procedures. It is also shown that the procedure is robust against the normality assumption on the population vectors. Applied to a set of RNA-sequencing data, we obtain very convincing results on pairwise independence/dependence of gene isoform expressions as attested by prior knowledge established in that field.
MSC:
| 62H15 | Hypothesis testing in multivariate analysis |
| 62J15 | Paired and multiple comparisons; multiple testing |
| 62P10 | Applications of statistics to biology and medical sciences; meta analysis |
| 92D20 | Protein sequences, DNA sequences |
Keywords:
covariance matrix; gene network; high-dimensional testing; independence test; asymptotic normality; Monte-Carlo studyReferences:
| [1] | DOI: 10.1016/j.canlet.2012.11.010 · doi:10.1016/j.canlet.2012.11.010 |
| [2] | Anderson TW, An introduction to multivariate statistical analysis, 3. ed. (2003) |
| [3] | DOI: 10.2307/1905324 · Zbl 0012.02903 · doi:10.2307/1905324 |
| [4] | DOI: 10.1214/aos/1031689018 · Zbl 1029.62049 · doi:10.1214/aos/1031689018 |
| [5] | DOI: 10.1214/09-AOS694 · Zbl 1360.62286 · doi:10.1214/09-AOS694 |
| [6] | DOI: 10.1214/09-AOS716 · Zbl 1183.62095 · doi:10.1214/09-AOS716 |
| [7] | DOI: 10.1214/13-EJS842 · Zbl 1293.62127 · doi:10.1214/13-EJS842 |
| [8] | DOI: 10.1007/s11425-012-4501-0 · Zbl 1256.62033 · doi:10.1007/s11425-012-4501-0 |
| [9] | DOI: 10.1016/j.jmva.2012.06.004 · Zbl 1273.62128 · doi:10.1016/j.jmva.2012.06.004 |
| [10] | DOI: 10.1214/14-AOS1284 · Zbl 1344.60027 · doi:10.1214/14-AOS1284 |
| [11] | DOI: 10.14490/jjss.35.251 · doi:10.14490/jjss.35.251 |
| [12] | DOI: 10.1038/nrg1272 · doi:10.1038/nrg1272 |
| [13] | DOI: 10.1093/nar/gkt145 · doi:10.1093/nar/gkt145 |
| [14] | Yalamanchili HK, Li ZY, Wang P, et al. SpliceNet: recovering splicing isoform-specific differential gene networks from RNA-Seq data of normal and diseased samples. Nucl Acids Res. 2014, doi: 10.1093/nar/gku577. · doi:10.1093/nar/gku577 |
| [15] | Powers DWM, J Mach Learn Technol 2 pp 37– (2007) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
