Description Usage Arguments Examples
This function calculates the values of valid moment combinations for two-step Generalized Method of Moments with user-defined types of time-dependent covariates, applied to longitudinal data with count (0-n) outcomes. It is assumed that the count represents the number of events from n identical trials, and that n is equal for all subjects and times. This is modeled similarly to a Logistic Regression for Binomial responses. It allows for unbalanced longitudinal data, meaning subjects can be observed for different numbers of times. The function returns a vector "types" indicating validity of different moments conditions.
1 2 | validMCBinom_Types(ymat, subjectIndex, Zmat, Xmat, covTypeVec, betaI, T, Tmax,
Count)
|
ymat |
The matrix of responses, ordered by subject, time within subject. The first column is the number of successes, the second the number of failures. |
Zmat |
The design matrix for time-independent covariates. |
Xmat |
The design matrix for time-dependent covariates. |
covTypeVec |
The vector indicating the type of each time-dependent covariate. |
betaI |
The current or initial estimates of the model parameters. |
T |
The number of time points for subject i. |
Tmax |
The maximum number of times of observation among all subjects. |
Count |
A vector of running counts of the number of valid moment conditions for all subjects. |
1 |
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.