MKMR {MSKAT} | R Documentation |
Return the variant set association test statistic and p-value. Aadapted from Maity et. al (2012) approach for rare variant set association test using weighted linear kernel.
MKMR(Y, X.list, Sigma = NULL, Gm, W = NULL, W.beta = c(1, 25), n.sim = NULL)
Y |
pxn matrix, each row is one response, each column is one subject |
X.list |
a list where each item of list is a qxn matricx (parametric design matrix), where each row is one covariate (possiblly different for all items in Y), intercept must be included! |
Sigma |
covariance matrix of multivariate outcomes; estimate from data if NULL |
Gm |
genotype matrix with SNPs in column |
W |
variant weight; use Beta dist weight if NULL |
W.beta |
Beta distribution parameters for the variant weight. Default to Beta(1,25). |
n.sim |
number of simulation to obtain the null distribution of the test statistic; using analytical method if NULL |
Maity,A., Sullivan,P.F., Tzeng,J. (2012) Multivariate Phenotype Association Analysis by Marker-Set Kernel Machine Regression. Genetic Epidemiology, 36, 686-695.
Original R codes posted at http://www4.stat.ncsu.edu/~maity/software/Multivariate_Response_KMTest.txt