Dear R-Help,
I am Deniz.
I am currently trying to replicate a semiparametric sample selection paper
and I am working on Klein and Spady estimator. I am using the npindex() and
npindexbw() functions.
The problem is, I need results for single bandwidth and when I set bandwidth
computation to "FALSE" mode, R is not optimizing anything. Here is the
code
I am using:
rp_ksbw<-npindexbw(bws=c(1, -0.1, -0.08, 0.06, -0.14, -0.02, 0.3),
formula=(rp$participation ~ (AGE + rp$CHILD + rp$YCHILD + rp$HW + rp$EDU +
AGE2)), bandwidth.compute=FALSE, optim.method="Nelder-Mead",
method="kleinspady")
and it is giving me exactly the same values I specified. Here is the result
I got:
Single Index Model
Regression data (2339 observations, 6 variable(s)):
AGE rp$CHILD rp$YCHILD rp$HW rp$EDU AGE2
Beta: 1 -0.1 -0.08 0.06 -0.14 -0.02
Bandwidth: 0.3
Optimisation Method: NA
Regression Type: Local-Constant
Bandwidth Selection Method: Manual
Formula: rp$participation ~ (AGE + rp$CHILD + rp$YCHILD + rp$HW + rp$EDU +
AGE2)
Continuous Kernel Type: Second-Order Gaussian
No. Continuous Explanatory Vars.: 1
I would be most grateful if you could share your ideas with me.
Thanks a lot in advance
Deniz
[[alternative HTML version deleted]]