The limiting spectral distribution of the noncentral unified matrix model

We investigate the limiting spectral distribution of a noncentral unified matrix model defined by Ω(X) = ((XP₁+A)(XP₁+A)'/n₁) (XP₂X'/n₂)⁻¹ , where X=(Xᵢⱼ)p× n is a random matrix with independent and identically distributed real entries having zero mean and finite second moment. A is a p× n nonrandom matrix. The matrices P₁ and P₂ are projection matrices satisfying rank(P₁)=n₁ , rank(P₂)=n₂ , and P₁P₂=0 . When P₁ and P₂ are random, they are assumed to be independent of X . When p/n₁→ c₁∈(0,∞) and p/n₂→ c₂∈(0,1) , we establish the almost sure convergence of the empirical spectral distribution of Ω to a deterministic limiting distribution. Furthermore, we show that this limiting distribution coincides with that of the noncentral F-matrix, thus revealing a deep connection between the proposed model and classical multivariate analysis.