Some Conclusions on Markov Matrices and Transformations

Markov matrices have an important role in the filed of stochastic processes. In this paper, we will show and prove a series of conclusions on Markov matrices and transformations rather than pay attention to stochastic processes although these conclusions are useful for studying stochastic processes. These conclusions we come to, which will make us have a deeper understanding of Markov matrices and transformations, refer to eigenvalues, eigenvectors and the structure of invariant subspaces. At the same time, we account for the corresponding significances of the conclusions. For any Markov matrix and the corresponding transformation, we decompose the space as a direct sum of an eigenvector and an invariant subspace. Enlightened by this, we achieve two theorems about Markov matrices and transformations inspired by which we conclude that Markov transformations may be a defective matrix--in other words, may be a nondiagonalizable one. Specifically, we construct a nondiagonalizable Markov matrix to exhibit our train of thought.