Screen Link:
https://app.dataquest.io/m/1015/probability-rules-practice-problems/3/mutually-exclusive-events
I was working on the 3rd question in this screen and I’m confused by the hint provided, specifically the second point:

The way I see the problem is, 132 customers were given travel forms respectively to fill, with two options:
- summer vacation
- winter vacation
Of those 132, 64 selected the first option, 21 selected the second option and 15 selected both options. The remaining selected neither . So it seems straightforward that the number of people who didn’t buy a vacation at all must be 132-64-21-15.
What is the hint trying to get to?
Cheers
For a simple example, out of 15 people -
So, what you are assuming is that there are 3 distinct categories here -
- 2 people bought a summer vacation
- 3 people bought a winter vacation
- 1 person bought both
The above is correct if the events are mutually exclusive.
In the content they specify that the events are mutually non-exclusive they are calculating it as -
- 3 people in total bought a summer vacation (2 individual S, and 1 from S, W)
- 4 people in total bought a summer vacation (3 individual W, and 1 from S, W)
- 1 person bought both
In your case, when you try to calculate who didn’t buy a vacation it would be 15 - 2 - 3 - 1
.
In their case, it would be 15 - (3 + 4 - 1)
. We subtract 1
because we already included that person for both of the individual categories (so twice).
But the content makes the distinction by stating that the events are mutually non-exclusive. It can be a bit confusing because the experiment design and the results (survey) make it seem that 3 categories are being tracked separately and values are being accumulated exclusively for each category. And, as per me, how the data was collected/tracked/stored could be better clarified to help beginners better understand the topic.
Since it’s specified they are mutually non-exclusive, then that’s what you should work with. If it’s not specified, then that’s when other things should be taken into account instead of making assumptions.
1 Like
@the_doctor thank you very much! 
It can be a bit confusing because the experiment design and the results (survey) make it seem that 3 categories are being tracked separately and values are being accumulated exclusively for each category.
As you mentioned, the problem is with the way the question is framed. I saw it as three mutually exclusive categories. I did not connect it with the topic at hand.
Your explanation is perfect and makes sense.
1 Like