What is Sample Covariance?
The sample covariance(SC) estimator uses the sample data for the expectation operator. You can generate the SC from the sample covariance. It assesses the intensity and direction of the association between the elements of two samples.
Example of Sample Covariance:
$ \sigma _{x,y}=\frac{1}{n}\sum_{i=1}^{n}\left ( Xi-\mu _{X} \right )\left ( Yi-\mu _{Y} \right ) $
Where
μX is the sample mean of X, and μY is the sample mean of Y. Like the sample variance estimator, the SC estimator is biased toward zero. Dividing by n — 1 rather than n produces an unbiased covariance estimate.
Computing the Sample Covariance
Year | Excelsior Corp Annual Annual Return (percent) | Adirondack Corp Annual Annual Return (percent) | (Xi – $ \overline{X} $) | (Yi – $ \overline{Y} $)) | (Xi – $ \overline{X} $)(Yi – $ \overline{Y} $)) |
2008 | 1 | 3 | 1-1= 0 | 3-3= 0 | (0)(0) = 0 |
2009 | -2 | 2 | -2-1= -3 | 2-3= -1 | (-3)(-1) = 3 |
2010 | 3 | 4 | 3-1 = 2 | 4-3 = 1 | (2)(1) = 2 |
2011 | 0 | 6 | 0-1= -1 | 6-3 = 3 | (-1)(3) = -3 |
2012 | 3 | 0 | 3-1 = 2 | 0-3 = -3 | (2)(-3) = -6 |
Mean | 1 | 3 | Sum | -4 |
Why is Sample Covariance important?
The SC helps judge the reliability of the sample means as estimators. It is also helpful in estimating the population covariance matrix.
Owais Siddiqui
1 min read