[R] pointwise nonparametric estimation of odds-ratios of continuous predictors

[environ]

Dear listers,

I am doing an time-series analysis on the relationship fo daily air
pollutants and mortality using generalized additive models. I have two
questions as followed:

Question 1:
How can I get the relative risk estimates from the smoothing spines ? I have
found a paper which focused on this problem. The paper is "np.OR: an s-plus
function for pointwise nonparametric estimation of odds ratios of continuous
predictors". Please see the attached files.

Question 2: 
Is there some functions in package mgcv ? If not, can I use the method
described in the above reference?

Thanks a lot in advance

Yanshen Zhang
http://www.nabble.com/file/p14165792/an%2Bs-plus%2Bfunction%2Bfor%2Bpointwise%2Bnonparametric%2Bestimation%2Bof%2Bodds-ratios%2Bof%2Bcontinuous%2Bpredictors.pdf
an+s-plus+function+for+pointwise+nonparametric+estimation+of+odds-ratios+of+continuous+predictors.pdf 
http://www.nabble.com/file/p14165792/an%2Bs-plus%2Bfunction%2Bfor%2Bpointwise%2Bnonparametric%2Bestimation%2Bof%2Bodds-ratios%2Bof%2Bcontinuous%2Bpredictors.pdf
an+s-plus+function+for+pointwise+nonparametric+estimation+of+odds-ratios+of+continuous+predictors.pdf 
-- 
View this message in context: http://www.nabble.com/pointwise-nonparametric-estimation-of-odds-ratios-of-continuous-predictors-tf4947653.html#a14165792
Sent from the R help mailing list archive at Nabble.com.