EM.starting.point: Randomly assigns a starting point for the EM algorithm
Description
This function should be invisible to most users, and is part of our
the fitting routine using the EM algorithm.
Our maximum likelihood procedure uses an iterative algorithm called
Expectation-Maximization. This requires a starting point, chosen at
random. EM.starting point randomly assigns this starting point.
Usage
EM.starting.point(d, trait = "binary")
Arguments
d
The dataframe that needs to be initialized
trait
Can be either ``binary'' or ''eQTL''
Value
Returns the input data frame with reasonable random starting values.
References
A. P. Dempster, N. M. Laird, and D. B. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. Royal Stat. Soc., vol. 39, pp. 1--38, 1977.