A Comparative Study of Tests for Homogeneity of Variances with Application to DNA Methylation Data

Variable DNA methylation has been associated with cancers and complex diseases. Researchers have identified many DNA methylation markers that have different mean methylation levels between diseased subjects and normal subjects. Recently, researchers found that DNA methylation markers with different variabilities between subject groups could also have biological meaning. In this article, we aimed to help researchers choose the right test of equal variance in DNA methylation data analysis. We performed systematic simulation studies and a real data analysis to compare the performances of 7 equal-variance tests, including 2 tests recently proposed in the DNA methylation analysis literature. Our results showed that the Brown-Forsythe test and trimmed-mean-based Levene's test had good performance in testing for equality of variance in our simulation studies and real data analyses. Our results also showed that outlier profiles could be biologically very important.

[1]  H. Levene.  Robust tests for equality of variances , 1961 .

[2]  Morton B. Brown,et al.  Robust Tests for the Equality of Variances , 1974 .

[3]  M. E. Johnson,et al.  A Comparative Study of Tests for Homogeneity of Variances, with Applications to the Outer Continental Shelf Bidding Data , 1981 .

[4]  M. Bartlett.  Properties of Sufficiency and Statistical Tests , 1992 .

[5]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[6]  Gordon K Smyth,et al.  Statistical Applications in Genetics and Molecular Biology Linear Models and Empirical Bayes Methods for Assessing Differential Expression in Microarray Experiments , 2011 .

[7]  Martin J. Aryee,et al.  Personalized Epigenomic Signatures That Are Stable Over Time and Covary with Body Mass Index , 2010, Science Translational Medicine.

[8]  Wolfgang Wagner,et al.  Age-dependent DNA methylation of genes that are suppressed in stem cells is a hallmark of cancer. , 2010, Genome research.

[9]  A. Feinberg,et al.  Stochastic epigenetic variation as a driving force of development, evolutionary adaptation, and disease , 2010, Proceedings of the National Academy of Sciences.

[10]  Xiao Zhang,et al.  Comparison of Beta-value and M-value methods for quantifying methylation levels by microarray analysis , 2010, BMC Bioinformatics.

[11]  J. Issa,et al.  Epigenetic variation and cellular Darwinism , 2011, Nature Genetics.

[12]  A. Feinberg,et al.  Increased methylation variation in epigenetic domains across cancer types , 2011, Nature Genetics.

[13]  H. Kitchener,et al.  Epigenetic variability in cells of normal cytology is associated with the risk of future morphological transformation , 2012, Genome Medicine.

[14]  Andrew E. Teschendorff,et al.  Differential variability improves the identification of cancer risk markers in DNA methylation studies profiling precursor cancer lesions , 2012, Bioinform..

[15]  Jeffrey T Leek,et al.  Significance analysis and statistical dissection of variably methylated regions. , 2012, Biostatistics.

[16]  Tao Wang,et al.  A Powerful Statistical Method for Identifying Differentially Methylated Markers in Complex Diseases , 2012, Pacific Symposium on Biocomputing.

[17]  A. Oshlack,et al.  DiffVar: a new method for detecting differential variability with application to methylation in cancer and aging , 2014, bioRxiv.

[18]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .