There is a question in the Math for Data Scientist → Central Limit Theorem:
“Based on the resulting mean of the sampling distribution, would you say that variance is a biased or unbiased estimator?”
The answer that is provided in the course is:
"Since the mean of the sampling distribution of the variance is not equal to the variance of the population, it is a biased estimator. However, you may notice that it is close! If we set
ddof=1 in the
np.var() function, we can calculate sample variance, which is very similar to “population variance” except that the formula has
sample_size - 1 in the denominator instead of just
sample_size. Sample variance is an unbiased estimator of population variance. "
By my understanding the answer saying both - yes, it’s biased and no, it’s unbiased - at the same time))
Could you explain please, what’s going on here? Is sample variance biased or unbiased estimator?