I would like to know how the constant -1.694 was gotten in the image below by hand. The outcome variable is contraceptive usage, while the predictors are age group and desire. For a single predictor, I can get the constant by just dividing the number of women using contraceptives and taking the log using one of the factor as a reference, but in this situation, I don't know how to calculate the 2 predictors. I tried to pool all the value for a factor under each variable but I am getting -1.51.
