parameter_estimate_prediction: Estimate the parameters and do prediction

In BIG-S2/GFPLVCM: Genealized functional partinal linear varying-coefficient models

Description

Estimate the parameters and predict the reponse when given new samples.

Usage

parameter_estimate_prediction(y, x, z, lambda_s, lambda_u, bd, order_1, order_2, breaks,  pois_par,len_k, gamma_real, pre_n, B)

Arguments

y	q list of the response with the elements y_ID, y_time_point and y_value.
x	q list of the functional covariate with the elements x_ID, x_time_point and x_value.
z	q list of the scalar covariate with the elements z_ID, z_time_point and z_value.
lambda_s	the tuning parameter in the s direction.
lambda_u	the tuning parameter in the u direction.
bd	the bandwidth of the kernel function.
order_1	order of the B-splines in the s direction.
order_2	order of the B-splines in the u direction.
breaks	knots of the B-splines.
pois_par	intensity of the Possion distribution when generating the time points of the functional parameter.
len_k	number of the basis function used when generating the functional parameter.
gamma_real	true value of the scalar parameters.
pre_n	sample size to be predicted in the prediction.
B	true signal of the functional parameter.

Value

gamma_est	estimates of the salcar parameters.
b_est	estimates of the B-splines coefficients.
beta_true	true value of the functional parameter.
beta_est	estimate of the functional parameter.
mse_beta	Mean squared error of the functional parameter.
Rmse_beta	Relative mean squared error of the functional parameter.
mse_gamma	Mean squared error of the scalar parameters.
PMSE	Prediction mean squared error.
gamma_stat	Statistic with respect to testing the nullity of the scalar parameters.
b_stat	Statistic with respect to testing the nullity of the functional parameter.

References

see the paper "Generalized functional partial varying-coefficient model".

BIG-S2/GFPLVCM documentation built on May 23, 2019, 5:01 a.m.