score.linker.cpp: Calculte -log10(p) by score test (fast, for limited cases)
In KosukeHamazaki/RAINBOW: Genome-Wide Association Study with SNP-Set Methods

Calculte -log10(p) by score test (fast, for limited cases)

score.linker.cpp(
  y,
  Ws,
  Gammas,
  gammas.diag = TRUE,
  Gu,
  Ge,
  P0,
  chi0.mixture = 0.5
)

`y`	A n \times 1 vector. A vector of phenotypic values should be used. NA is allowed.
`Ws`	A list of low rank matrices (ZW; n \times k matrix). This forms linear kernel ZKZ' = ZW Γ (ZW)'. For example, Ws = list(A.part = ZW.A, D.part = ZW.D)
`Gammas`	A list of matrices for weighting SNPs (Gamma; k \times k matrix). This forms linear kernel ZKZ' = ZW Γ (ZW)'. For example, if there is no weighting, Gammas = lapply(Ws, function(x) diag(ncol(x)))
`gammas.diag`	If each Gamma is the diagonal matrix, please set this argument TRUE. The calculation time can be saved.
`Gu`	A n \times n matrix. You should assign ZKZ', where K is covariance (relationship) matrix and Z is its design matrix.
`Ge`	A n \times n matrix. You should assign identity matrix I (diag(n)).
`P0`	A n \times n matrix. The Moore-Penrose generalized inverse of SV0S, where S = X(X'X)^{-1}X' and V0 = σ^2_u Gu + σ^2_e Ge. σ^2_u and σ^2_e are estimators of the null model.
`chi0.mixture`	RAINBOW assumes the statistic l1' F l1 follows the mixture of χ^2_0 and χ^2_r, where l1 is the first derivative of the log-likelihood and F is the Fisher information. And r is the degree of freedom. chi0.mixture determins the proportion of χ^2_0