lassosumR: Function to obtain LASSO estimates of a regression problem...

In tshmak/lassosum: LASSO with summary statistics and a reference panel

Description

Function to obtain LASSO estimates of a regression problem given summary statistics and a reference panel (without PLINK bfile)

Usage

lassosumR(cor, refpanel, lambda = exp(seq(log(0.001), log(0.1),
  length.out = 20)), shrink = 0.9, ridge = F, thr = 1e-04,
  init = NULL, trace = 0, maxiter = 10000, blocks = NULL)

Arguments

cor	A vector of correlations (r)
refpanel	reference panel as data.frame or matrix
lambda	A vector of λs (the tuning parameter)
shrink	The shrinkage parameter s for the correlation matrix R
ridge	Produce ridge regression results also (slow if nrow(refpanel) > 2000)
thr	convergence threshold for β
init	Initial values for β
trace	An integer controlling the amount of output generated.
maxiter	Maximum number of iterations
blocks	A vector to split the genome by blocks (coded as c(1,1,..., 2, 2, ..., etc.))

Details

A function to find the minimum of β in

f(β)=β'Rβ - 2β'r + 2λ||β||_1

where

R=(1-s)X'X/n + sI

is a shrunken correlation matrix, with X being standardized reference panel. s should take values in (0,1]. r is a vector of correlations.

Value

A list with the following

lambda	same as the lambda input
beta	A matrix of estimated coefficients
conv	A vector of convergence indicators. 1 means converged. 0 not converged.
pred	=(1-s)Xβ
loss	=(1-s)β'X'Xβ/n - 2β'r
fbeta	=β'Rβ - 2β'r + 2λ||β||_1
sd	The standard deviation of the reference panel SNPs
shrink	same as input
nparams	Number of non-zero coefficients
ridge	ridge regression estimates

Note

• Missing values in refpanel are filled with 0.

• Unlike lassosum, we do not provide the options keep/remove/extract/exclude. It is thus up to the user to ensure the SNPs in the reference panel corresponds to those in the correlations.

tshmak/lassosum documentation built on Sept. 24, 2020, 9:41 a.m.