Skip to content

Non-linear regression with latent variable

2 messages · Samiul Hasan, Spencer Graves

Samiul Hasan
# 
Hi 
Can anyone please suggest me a package where I can estimate a non-linear
regression model? One of the independent variables is latent or unobserved.
I have an indicator variable for this unobserved variable; however the
relationship is known to be non-linear also. In terms of equations my
problem is

y=f(latent, fixed) 
q=g(latent) where q is the indicator variable

For me both f and g are non-linear.

Thanks
Samiul Hasan
1 day later
Spencer Graves
# 
If you have the "RSiteSearch" package installed, you can do the 
following: 


library(RSiteSearch)
nrow(nll <- RSiteSearch.function("nonlinear regression with latent"))
HTML(nll)


      This just produced 8 hits for me.  If this doesn't solve your 
problem, you might  try other search terms.  If all those fail, you 
could write your own likelihood function and use the "maxLik" package. 


      Hope this helps. 
      Spencer
Samiul Hasan wrote: