[R] out of sample forecast

Hello I have model that is: lm(y~ lag(x, -1) + lag(z, -1) so basically a time series regression with exogen variables And I want to make rolling out of sample forecasts, meaning that: I first use a subsample (e.g. 1990 -1995) for estimating, then I perform a one step ahead forecast, then I a

[R] Is the Diebold Mariano Test in forecast package adjusted?

Hello I would like to know if the Diebold Mariano Test in the forecast Package is adjusted to small samples (as Harvey, Leybourne, Newbold suggest) If not, how can I do that manually? Paka __ R-help@r-project.org mailing list https://stat.ethz.ch

[R] little help with Nonlinear regression needed

Hello as the subject says I need a little help with following nonlinear regression y(t) = a + b*x(t-1)+c*y_(t-1)+G*(a+b*x_(t-1)) where G=[1 + exp(-s(x_(t-1) - k)]^(-1) (In reality there are more variables) Please could anybody give me a hint how I can estimate this?? Should I use nls()? w