Interpretation of the coefficient in the logistic regression model is opposite of what we expect
I am running a logistic regression model where the counts/ frequencies are as follows: enter image description here. the rows are predictor (0, 1) and column is outcome (0, 1). Based on this relationship, predictor should have a negative relationship with the outcome from the results i am suspecting. but once i run a multiple logistic regression with covariates, I am getting an estimate that is opposite of what i am expecting.