SPPcomb (version 0.1)

DA_AllEE5: Data Analysis for Combining (N1,M1) + (N1,M2) + (N2,M1) + (N2,M2)

Description

The main function is to solve the estimating equations constructed by combining all pairs (N1,M1), (N1,M2), (N2,M1) and (N2,M2) with selection bias probility $\pi(s,\eta)$ included.

Usage

DA_AllEE5(realdata_covariates, realdata_alpha, beta0)

Arguments

realdata_covariates

a list contains the following data matrics: CASEZ_1, CASEZ_2, CASEZhat_1, CASEZhat_2, CASEZhat_22, CONTZ_1, CONTZ_2, CONTZhat_1, CONTZhat_2, CONTZhat_22. For details please see definition in the help of realdata_covariates. Please be noted that all the variables have to use the same name as listed above.

realdata_alpha

a list contains the following data matrics: prob_case_1, prob_case_11, prob_case_2, prob_case_22, prob_cont_1, prob_cont_2, pwt_cont_2. details please see definition in the help of realdata_alpha. Please be noted that all the variables have to use the same name as listed above.

beta0

We need an initial parameter for solver "nleqslv". Default value is beta0=c(-5.4163,0.7790,-0.1289,0.2773,-0.5510,0.1568,0.4353,-0.6895)

Value

A list of estimator and its standard deviation.

Details

The function solves GMM combined estimating equation with handling selection bias, see Huang(2014).

References

Huang, H., Ma, X., Waagepetersen, R., Holford, T.R. , Wang, R., Risch, H., Mueller, L. & Guan, Y. (2014). A New Estimation Approach for Combining Epidemiological Data From Multiple Sources, Journal of the American Statistical Association, 109:505, 11-23.

Examples

#you can use glm to get the estimate as the initial value of beta0
#beta0=c(-5.4163,0.7790,-0.1289,0.2773,-0.5510,0.1568,0.4353,-0.6895)
#DA_AllEE5(realdata_covariates,realdata_alpha,beta0=beta0)