If sample representativeness is not considered, variance has nothing to do with sample size. There is no implicit condition such as "same sample size".

For the random variable x, the variance varx = e {[x-e (x)] 2} = e (x 2)-(ex) 2.

For a group of samples with n sample size, variance = [σ (I = 1, n) (xi-t) 2)]/n, and t is the average value of this group of samples.

Note that n is removed from the denominator in the above formula, so under the same "fluctuation condition", the sum of variance does not increase with the increase of n.

For example, sample A is 0.9 and 1. 1, and sample B is 0.9 and 1. 1, each with ten. Obviously, the average values of sample A and sample B are both 1. Intuitively, the "fluctuation conditions" of the two samples are the same. According to the variance formula, the variance of the two samples is the same, not because the sample size of B is ten times that of A, so the variance of B is larger.