The beta-zero coefficient (BZC) for a logistic regression analysis can be estimated if the other coefficients and the probability are known.
probability for an outcome =
= 1 / (1 + EXP((-1) * ((SUM of coefficients) + (BZC))))
If the probability is X
BZC =
= (-1) * ((SUM of coefficients) + LN((1 – X) / X))
If the probability is 50%
BZC =
= (-1) * ((SUM of coefficients) + LN((1 – 0.5) / 0.5)) =
= (-1) * (SUM of coefficients)
If the probability is 99%
BZC =
= (-1) * ((SUM of coefficients) + LN((1 – 0.99) / 0.99)) =
= (-1) * ((SUM of coefficients) – 4.595) =
= 4.595 – (SUM of coefficients)
