Covariance

Covariance

Covariance

Description

  • Covariance is a statistical measure of the variability of two random variables with each other.
  • Covariance between two variables hints towards a linear relationship between them.

Why to use

To determine the relationship between two variables.

When to use

For numerical variables

When not to use

For textual data

Prerequisites

The data should not contain any missing values.

Input

Numerical variable having any positive or negative value.

Output

  • Scatter Plot
  • Heat Map

Statistical Methods used

Covariance Score

Limitations

  • Covariance gives the directional relationship between the variables. However, the magnitude of covariance (covariance score) is not very informative.
  • The variable variance is largely affected by the presence of even a small number of outliers in the data. This may lead to misleading statistics and interpretations.

Covariance indicates a relationship between two variables when there is a change in their values. In case of positive covariance, an increase in one variable increases the other variable. Thus, both the variables move in the same direction. The positive covariance is denoted by a positive number.
When there is a negative covariance, an increase in one variable decreases the other variable. Thus, both the variables move in opposite directions. The negative covariance is denoted by a negative number.
The values of covariance between two random variables can lie between positive infinity and negative infinity (+∞ to -∞) limits.
    • Related Articles

    • Rubiscape Spring '23

      New Features Studio Rubiscape Desktop All your favorite Rubiscape features, functions, and powerful dashboarding capabilities are now available in Rubiscape Desktop for Windows. With a completely new setup wizard, you can now customize your ...
    • Shapiro-Wilk Test

      Shapiro-Wilk Test Description The Shapiro-Wilk test is a normality test in probability determination statistics. It is used to determine whether a simple random sample of a variable’s values has been derived from a normal distribution. Why to use For ...
    • Statistical Concepts

      Accuracy Accuracy (of classification) of a predictive model is the ratio of the total number of correct predictions made by the model to the total predictions made. Thus, Accuracy = (TP + TN) / (TP + TN + FP + FN) Where, TP, TN, FP, and FN indicate ...