To measure the fluctuation of this set of data, it is called the variance of this set of data. For the sake of simplicity.
(where x is the average of this set of data).
Extended data
The logic behind the concept of variance is that the "distance" between the value and the expected value is expressed by the square of the difference between the two. The square value indicates the degree of deviation between this value and the distribution center. The minimum value of the square is 0.
When the value is the same as the expected value, it is not discrete at this time, and the square is 0, that is, the "distance" is the smallest; When the random variable deviates from the expected value, the square increases. Because the numerical values are random and the probabilities of different numerical values are different, the weighted average of the squares according to the probability can get the overall dispersion.
If the value of x is concentrated, the variance is small; If the value of x is scattered, the variance is large; If the variance D(X)=0, the random variable X takes a constant, and the probability is 1. At this time, X is not a random variable.
Baidu encyclopedia-variance calculation formula