I am testing out a Binomial distributed dataset in excel.
The dataset is litterally a "RANDBETWEEN(1;2)" So it simply randomizes between the number 1 and the number 2 with 50% chance of each, on a range of 10.000 cells.
The standard deviation for 10.000 = n and a probability of success of 50% = p
I get a Std Dev of: 50
What I don't understand is why the spread of the dataset is way larger than 50. often times it is even more than 200 (as opposed to the Std Dev of 50). Actually by continually refreshing all the 10.000 cells, the spread is surprisingly often above 150, (3x standard deviations). Just about every 1/3 times I refresh the data is goes above 150 spread.
By my understanding, a bigger spread than 3x Standard Deviation should occur very rarely (0,03% of the time) every 333rd time of refreshing the data in excel. Or am I wrong here?