I hope that my question is clear enough to understand.
If we need to calculate the probability of an event and we have historical data regarding our parameter of interest - When we have to assume distribution in order to calculate the probability of an event, or it is safe just to calculate the probability from a simple frequency distribution.
To put the question into context here is an example:
We want to calculate the probability of X numbers of sales in a certain period of time. Assume Poisson distribution? Or it is enough and "safer" just to calculate the probability of X sales from the historical frequency of sales during that period?
Thank you very much!