Double Gauss function used in fitting nlme curve for observations but now even better since it samples across a sensible distribution for starting parameters
doubleGauss_sac(dat, y, time, params = NULL, startSamp = 8, ...)subject data to be used
outcome variable, character vector
time variable, character vector
NULL unless user wants to specify starting parameters for gnls
how many samples from distribution should we use to investigate
just in case
User should only have to worry about setting concavity of this function
y ~ (time < mu) * (exp(-1 * (time - mu) ^ 2
/ (2 * sig1 ^ 2)) * (ht - base1) + base1)
+ (mu <= time) * (exp(-1 * (time - mu) ^ 2
/ (2 * sig2 ^ 2)) * (ht - base2) + base2)