How can i transform Logistic regression output into data frame?

[oktayozden]

hi friends,
I need to transform regression output into dataframe in order to use regression coefficient to calculate marjinal effect. In the output of Marginal effects, are below, coefficient of dF/dx is neccesary to calculate marginal effect of every subscribtion. So. How can i transform this result into data frame in order to use these coefficient to multiply "automatically" for each variables of each subscribtion ID

In code's details:

library(mfx)
pmodel3<-probitmfx(formula=CHURN~ HS+SS+TD+MB+IO
                     ,data = dat, 
                   atmean = TRUE, robust = FALSE, clustervar1 = NULL, 
                   clustervar2 = NULL, start = NULL, control = list())

Result:

Call:
probitmfx(formula = CHURN ~ HS+ SS+ TD+ 
    MD+ IO, data = dat, atmean = TRUE, 
    robust = FALSE, clustervar1 = NULL, clustervar2 = NULL, start = NULL, 
    control = list())

Marginal Effects:
                  dF/dx             Std. Err.           z         P>|z|    
HS        -0.03978638  0.00038181 -104.204 < 2.2e-16 ***
SS         0.05661538  0.00258346   21.915 < 2.2e-16 ***
TD        -0.07554999  0.00240007  -31.478 < 2.2e-16 ***
MD       -0.39882822  0.00504727  -79.019 < 2.2e-16 ***
IO         -0.45453780  0.00273034 -166.476 < 2.2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

dF/dx is for discrete change for the following variables:

[1] "SS"      "TD" "MB" "IO"      

[FJCC]

If I understand the documentation correctly, you can get a matrix with the Marginal Effects values like this:

MAT <- pmodel13$mfxest

That can be transformed into a data frame with

DFmfx <- as.data.frame(MAT)