NEWS

nls2 0.3-4 (2024-07-14)

add lhs (Latin Hypercube Sampling) and plinear-lhs sampling algorithms
if all iterations fail return NULL
add README file
add INSTALL file
fix Example 5 in help file and change it to use plinear-lhs
fix number of iterations. Previously 1 iteration could display incorrectly.
fix weights. Do not ignore weights (includes contribution by Ben Bolker)
fix subset. Do not ignore subset argument. Note that if subset is specified then data must be specified as a data.frame.
add caveat to help file regarding start argument not supporting the nls grouped data list of vector format

algoirthm can be "plinear-brute" or "plinear-random"
corrected one nls2 example
trace is now used by nls2 to control printing. Previously it was only used to pass to nls.

as.lm and as.lm.nls can be used to convert an "nls" object to an "lm" object which is tangent to the nls object. Untested.
as.lm.nls uses proto package hence new dependency
added algorithm = "random" which samples maxiter rows from start if start is a data frame with more than 2 rows whereas if start is a data frame with exactly 2 rows it will take maxiter random points from the rectangle whose boundary is defined by the rows.
if nls exits with an error nls2 uses NA as the return value of that nls call instead of stopping with an error

fixed problem with update not working with objects produced by nls2.
fixed number of iterations and tolerance displayed when using algorithm = "brute-force".
if there are exactly two rows in start= then a grid of starting values is formed so that there are at least maxiter points on the grid.
start can be an nls object in which case coef(nls) is used.