
Dear list,
I am using the np package. With the npindex function I estimate a semiparametric single index model using the method of KleinSpady.
P(Z=1X) = G(X’b)
I don’t have any problems to calculated the fitted values and standard errors X’b:
bw = npindexbw(xdat=x, ydat=y_bi, method="kleinspady", nmulti=2)
model = npindex(bws= bw3, gradients= TRUE, residuals = TRUE, boot.num = 50)
x_fit = predict(model, se.fit = TRUE)
x_fit_bi= x_fit$fit
x_fit_bi_se = x_fit$se.fit
However, I also would like to obtain an estimate of G(X’b). For example, after estimating a probit model, it would simply be
G_hat=pnorm(x_fit)
Any help would be very much appreciated!
