A probability distribution tells us the probability that a random variable takes on certain values.

For example, the following probability distribution tells us the probability that a certain soccer team scores a certain number of goals in a given game:

To find the **variance **of a probability distribution, we can use the following formula:

**σ ^{2} = Σ(x_{i}-μ)^{2} * P(x_{i})**

where:

**x**The i_{i}:^{th}value**μ:**The mean of the distribution**P(x**The probability of the i_{i}):^{th}value

For example, consider our probability distribution for the soccer team:

The mean number of goals for the soccer team would be calculated as:

μ = 0*0.18 + 1*0.34 + 2*0.35 + 3*0.11 + 4*0.02 = **1.45** goals.

We could then calculate the variance as:

The variance is simply the sum of the values in the third column. Thus, we would calculate it as:

σ^{2} = .3785 + .0689 + .1059 + .2643 + .1301 = **0.9475**

The following examples show how to calculate the variance of a probability distribution in a few other scenarios.

**Example 1: Variance of Vehicle Failures**

The following probability distribution tells us the probability that a given vehicle experiences a certain number of battery failures during a 10-year span:

To find the variance of this probability distribution, we need to first calculate the mean number of expected failures:

μ = 0*0.24 + 1*0.57 + 2*0.16 + 3*0.03 = **0.98 **failures.

We could then calculate the variance as:

The variance is the sum of the values in the third column. Thus, we would calculate it as:

σ^{2} = .2305 + .0002 + .1665 + .1224 = **0.5196**

**Example 2: Variance of Sales**

The following probability distribution tells us the probability that a given salesman will make a certain number of sales in the upcoming month:

To find the variance of this probability distribution, we need to first calculate the mean number of expected sales:

μ = 10*.24 + 20*.31 + 30*0.39 + 40*0.06 = **22.7 **sales.

We could then calculate the variance as:

The variance is the sum of the values in the third column. Thus, we would calculate it as:

σ^{2} = 38.7096 + 2.2599 + 20.7831 + 17.9574 =** 79.71**

Note that we could also use the Probability Distribution Calculator to automatically calculate the variance of this distribution:

The variance is **79.71**. This matches the value that we calculated by hand.

No sure how to ask this. The distribution is tabular – that it doesn’t fit any known distribution, and your method looks reasonable. How do you extends this to more than one variable?

I think I know. I think this would be like a normal covariance calculation. If I’m given a joint distribtion of let’s say 2 variables, I’d get 2d table of probabilities (P(x1[i], x2[i])) – that’d add up to one. I think I’d compute the marginal mean for variable 1 and variable 2 and make it a vector MU. Then define DX(i) = (x1[i], x2[i]) – MU. Then cov = sum_i P(x1[i], x2[i]) DX DX^T. I think that’d work.

the queen died rip