STRUCTURE SELECTION FOR BOUNDED-PARAMETER MODELS - CONSISTENCY CONDITIONS AND SELECTION CRITERION

The paper studies strong-consistency conditions for structure selection in bounded-parameter models. A new robust selection criterion, based on the volume of the exact parameter-bounding polytope, is proposed for linear regression models. Its strong consistency is proved for a large class of noise distributions; the usual assumptions on the noise, namely independence, constant variance, or martingale difference properties, need not be made but asymptotic independence is assumed.