In this lesson we learned about:

• The probability density function for the multivariate normal distribution
• The definition of a prediction ellipse
• How the shape of the multivariate normal distribution depends on the variances and covariances
• The definitions of eigenvalues and eigenvectors of a matrix, and how they may be computed
• How to determine the shape of the multivariate normal distribution from the eigenvalues and eigenvectors of the variance-covariance matrix