Both models are non-linear, so the estimated coefficients
indicate only the sign of the relation between the outcome and
explanatory variables. To compare the magnitude of the
relations, we estimated the marginal effects of the explanatory
variables on the probability of observing a certain outcome,
i.e., the change in the probability as a result of a one unit
increase in the explanatory variable holding all other variables
constant. The marginal effects can be evaluated at the sample
means of the variables, but one could also evaluate them at
each observation and report the average of those figures,
i.e., the average marginal effects (AME), as we do in this paper.
The AME represents an average impact of the variable on the
probability of adoption and has the advantage of being unique
(i.e., not taken at a particular point).