Now that 3DR has a sample dataset of the attendees that visited their booth during Day 1 of the conference (i.e. Marketing Data by Company Responsibility), they can now perform a variety of different analyzes on the data to answer some questions that may or may not arise during the event. For instance, what if a legal concern was raised by some of the attendees that expressed that a disproportionate number of sampled attendees that were entered into 3DR’s lottery to win a trip to Hawaii are men?
If an attendee is randomly selected from 3DR’s Marketing Data pool, what is the probability that the attendee is a woman? Based on marginal probability (Black, 2020), 3DR can take the total number of recorded Female attendees (i.e. 185) that stopped by the booth and divide that number by total attendees that visited the booth (i.e. 584); P(F) = 185/584 = .316.
P(F) = 185/584 = .316 = 31.6%
In this example, the marginal probability that a female would be randomly selected out of the Marketing Data pool is 31.6% (male probability = 68.3%). This could bring some bias between the probability of male versus females being selected simply due to the numbers outlined. However, 3DR can easily justify their position stating that there was no bias and the selection process was fair.
In this case, although 3DR could use specific factors to help them decide who to select for the lottery based on other interests or their responsibilities given an unknown weight of importance, they will not use this approach to ensure the selected attendee was chosen based on inferential statistics. According to Black (2020), “inferential statistics involves taking a sample from a population, computing a statistic on the sample, and inferring from the statistic the value of the corresponding parameter of the population.”