R: Calculate shares using data from regression model

lambda.reg {eiPack}

R Documentation

Calculate shares using data from regression model

Calculates the population share of row members in a particular column

lambda.reg(object, columns)

`object`	An R object of class `eiReg`, the output from `ei.reg`
`columns`	a character vector of column names to be included in calculating the shares

Standard errors are calculated using the delta method as implemented in the library msm. The arguments passed to deltamethod in msm include

ga list of transformations of the form ~ x1 / (x1 + x2 + + ... + xk), ~ x2 / (x1 + x2 + ... + xk), etc.. Each x_c is the estimated proportion of all row members in column c, \hat{\beta}_{rc}
meanthe estimated proportions of the row members in the specified columns, as a proportion of the total number of row members, (\hat{\beta}_{r1}, \hat{\beta}_{r2}, ..., \hat{\beta}_{rk}).
cova diagonal matrix with the estimated variance of each \hat{\beta}_{rc} on the diagonal. Each column marginal is assumed to be independent, such that the off-diagonal elements of this matrix are zero. Estimates come from object$cov.matrices, the estimated covariance matrix from the regression of the relevant column. Thus,

Returns a list with the following elements

`call`	the call to `lambda.reg`
`lambda`	an `R \times k` matrix where `k` is the number of columns included in the share calculation
`se`	standard errors calculated using the delta method as implemented in the library `msm`