Takes a fitted asp object produced by
asp2() and summarises the fit, including tests for significance of nonparametric effects as well as their deviation from a parametric fit.
# S3 method for asp
summary(object,test1=FALSE,test2=FALSE,signif=0.05,...)The function generates summary tables.
a fitted asp object as produced by asp2().
TRUE in order to include a test for significance of a nonparametrically estimated effect. The test correpsonds to checking whether the zero line is entirely inside the simultaneous confidence band.
TRUE in order to inlcude the nonparametric specification test proposed in Wiesenfarth et al. (2012). Only works with B-splines. The function under the null hypothesis is a polynomial of degree q-1 where q is the penalty order.
the significance level.
other arguments.
Produces tables for the linear (parametric) and non-linear (nonparametric) components. The linear table provides coefficient estimates, standard errors and p-values. The non-linear table provides degrees of freedom values and other information including tests for significance of nonparametric effects as well as their deviation from a parametric fit. See Wiesenfarth et al (2011, 2012) and Wiesenfarth (2012) for details on the hypothesis tests.
Ruppert, D., Wand, M.P. and Carroll, R.J. (2003)
Semiparametric Regression Cambridge University Press.
https://web.stat.tamu.edu/~carroll/semiregbook/
Wiesenfarth, M., Krivobokova, T., & Sperlich, S. (2011)
A Volume-of-tube based Test for Penalized Splines Estimators. Int. Statistical Inst.: Proc. 58th World Statistical Congress, 2011, Dublin. http://www.2011.isiproceedings.org/papers/950754.pdf
Wiesenfarth, M., Krivobokova, T., Klasen, S., Sperlich, S. (2012).
Direct Simultaneous Inference in Additive Models and its Application to Model Undernutrition.
Journal of the American Statistical Association, 107(500): 1286-1296.
Wiesenfarth, M. (2012). Estimation and Inference in Special Nonparametric Models. Doctoral dissertation, Goettingen, Georg-August Universitaet, Diss., 2012. http://d-nb.info/104297182X/34
plot.asp, predict.asp
data(onions,package="SemiPar")
attach(onions)
log.yield <- log(yield)
fit <- asp2(log.yield~location+f(dens, degree=c(3,2)))
summary(fit,test1=TRUE,test2=TRUE)
Run the code above in your browser using DataLab