format_data: Format the data in the appropriate way for the algorithm

In cgaillac/MarginalFElogit: Estimation of Average Marginal Effects in Fixed Effect Logit Models

Format the data in the appropriate way for the algorithm

Description

Format the data in the appropriate way for the algorithm

Usage

format_data(data, beta = NULL)

Arguments

data

is an environment containing the observed data: - data$Y is a matrix of size n x Tmax containing the values of the dependent variable Y, - data$X is an array of size n x Tmax x dimX containing the values of the covariates X -data$clusterIndexes is a vector of size n x 1 that specifies the cluster each observation pertains to. If it does not exist, the function enforces the default setting of i.i.d. observations - the parameter takes value 1:n so that each observation is its own cluster.

beta

(default NULL) the slope parameter for the FE logit model. If specified, computes a few extra variables from the data.

Value

The algorithm does not return anything but data has been modified so that: - data$Y is a matrix of size n x Tmax containing the values of the dependent variable Y, - data$X is an array of size n x Tmax x dimX containing the values of the covariates X - data$S is a vector of size n x 1 that counts, for each row (individual), the number of columns (periods) for which Y is 1. - data$Tobsd is a vector of size n x 1 that counts, for each row (individual), the number of columns (periods) that are not NAs (observed). - data$clusterIndexes is a vector of size n x 1 that specifies the cluster each observation pertains to. If it does not exist, the function enforces the default setting of i.i.d. observations - the parameter takes value 1:n so that each observation is its own cluster. - data$V is a matrix of size n x Tmax containing, for each individual-period pair, the value of X'beta. It is NA for unobserved individual-period pairs. This parameter is undefined if beta was NULL (or not specified as input). - data$C_S_tab is a matrix of size n x (Tmax + 1). Each row (individual) has, in the j_th column, the value of C_(j-1)(X, beta). It is NA when j - 1 is larger than Tobsd. This parameter is undefined if beta was NULL (or not specified as input). - data$C_S_minus_one_one_period_out_array is a matrix of size n x Tmax x Tmax. Each row (individual) has, in its t-th third-dimensional slice and j-th column (period), the value of C_(j-1)(Z, beta) where Z is the same as the relevant row of X deprived from its t-th period.

cgaillac/MarginalFElogit documentation built on Dec. 24, 2024, 3:23 p.m.