Posts

Showing posts from January, 2024

Marginal distributions of the multinomial normal distribution

Image
 Marginal distributions of a multivariate normal distribution are also normal distributions. Let's prove this. See also : Multivariate normal distribution [Wikipedia] The density function of a multivariate normal distribution is given as f(x)=1(2π)n|Σ|exp[12(xμ)Σ1(xμ)] where xRn is the random vector, μ is the mean vector and Σ is the covariance matrix. By changing the variables xμx, we can assume the mean is zero without losing generality. So, in the following, we only consider f(x)=1(2π)n|Σ|exp[12xΣ1x]. We need the following theorems from linear algebra. Theorem 1 Let A be an n×n regular, D be m×m regular, \(B\...